System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving photograph data taken by a user with a terminal; means for automatically generating a background and applying the background to the photograph data; means for detecting a face portion of a person and correcting makeup deterioration and wrinkles; means for optimizing and storing the corrected photograph; and means for transmitting the optimized photograph data to the terminal.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The technology of the present disclosure relates to a system. [Background technology]

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Today, many people require professional techniques and special locations for photography and editing. This has led to a growing demand for systems that allow users to easily create high-quality photos, but achieving this goal is difficult. In particular, advanced editing tasks such as setting the background and correcting makeup smudges and wrinkles require specialized knowledge and equipment. There is a demand for a system that overcomes these limitations and allows anyone to easily create professional-quality photos. [Means for solving the problem]

[0005] The system includes a means for receiving photo data taken by a user on a device, a means for automatically generating a background and applying it to the photo data, a means for detecting a person's face and correcting smudged makeup and wrinkles, a means for optimizing and saving the corrected photo, and a means for transmitting the optimized photo data to the device. This system enables users to easily create high-quality photos without requiring special skills or equipment. Furthermore, by including a means for generating multiple background candidates when generating a background and selecting the most suitable one from among them, and a means for analyzing facial features when correcting smudged makeup and wrinkles on the face, the system can automatically achieve even more advanced photo editing.

[0006] "User" refers to a person who takes photos using a terminal and uses the photo studio system.

[0007] "Terminal" refers to a device such as a smartphone, tablet, or camera that takes photos and sends the data to a server.

[0008] "Photo data" refers to image information taken by a user on a device.

[0009] "Server" refers to a central processing unit that receives photo data and performs background generation and correction processing.

[0010] "Means for automatically generating backgrounds" refers to algorithms or programs that identify the background portion of photo data within the server and generate new backgrounds.

[0011] "Means for detecting a person's face" refers to an algorithm or program for identifying a person's face in photographic data and analyzing its position and features.

[0012] "Means for correcting smudged makeup and wrinkles" refers to algorithms or programs for automatically correcting smudged makeup and wrinkles on detected facial areas.

[0013] "Means for optimizing photos" refers to algorithms or programs that convert photo data that has been corrected and background generated into the optimal format and image quality.

[0014] "Means for transmitting photo data to the terminal" refers to a communication means for transmitting the finally generated high-quality photo data from the server to the terminal.

[0015] "Means for generating background candidates" refers to an algorithm or program for creating multiple background candidates and selecting the most suitable one from among them.

[0016] "Means for analyzing facial features" refers to algorithms or programs for identifying and analyzing facial features such as the eyes, nose, and mouth. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[0039] 1. User photo taking and uploading

[0040] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0041] 2. Automatic background generation

[0042] The server receives the uploaded photo data. After receiving it, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates. The server selects the best one from these background candidates and applies it to the photo data.

[0043] For example, if a user takes a photo indoors, the server can automatically change it to a beach or park background.

[0044] 3. Face detection and correction

[0045] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful photo.

[0046] Specifically, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[0047] 4. Optimize and save

[0048] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0049] 5. Photo distribution

[0050] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[0051] For example, a photo taken at home can be automatically changed to a beach background, and any smudged makeup on the face can be corrected, resulting in a high-quality photo sent to the user's smartphone. After this, the user can share the photo on Instagram or other platforms.

[0052] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[0053] The processing flow will be explained below.

[0054] Step 1:

[0055] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[0056] Step 2:

[0057] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[0058] Step 3:

[0059] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[0060] Step 4:

[0061] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[0062] Step 5:

[0063] The server generates multiple background candidates for the detected background portion, and then selects the best one from the generated background candidates.

[0064] Step 6:

[0065] The server applies the selected background to the photo data, and then performs the processing to replace the background.

[0066] Step 7:

[0067] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[0068] Step 8:

[0069] The server detects smudges and wrinkles on the face, and applies an automatic correction algorithm to the detected areas.

[0070] Step 9:

[0071] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[0072] Step 10:

[0073] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[0074] Step 11:

[0075] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[0076] Example 1

[0077] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0078] Conventional image editing systems require advanced skills and specialized software to perform complex processes on photos taken by users, such as changing the background, smoothing out makeup, or correcting wrinkles. This makes it difficult for average users to easily create professional-quality photos. Furthermore, there is no function to automatically select the optimal background from multiple background candidates, making manual selection a time-consuming process.

[0079] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0080] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for identifying a background portion of the image data and selecting an optimal background from a plurality of automatically generated background candidates and applying it to the image data, means for detecting the user's face in the image data and analyzing facial feature points to correct smudged makeup and wrinkles, means for optimizing and saving the image data after correction and background generation is complete, and means for transmitting the optimized image data to the terminal. This enables users to easily obtain high-quality photos with automatically selected backgrounds and corrected smudged makeup and wrinkles, even without special skills or equipment.

[0081] "User" means an individual or end user who uses the System.

[0082] "Device" refers to a computing device such as a smartphone, tablet, or PC.

[0083] "Image data" refers to digital image files that users take with their devices and upload to the server.

[0084] A "server" is a remote computer system that receives, processes, stores, and distributes image data.

[0085] "Background" refers to the area of ​​the image data other than the user's face or other people.

[0086] "Background candidates" are multiple background image options generated by the system.

[0087] "Facial area" refers to the area in the image data that is occupied by the user's face.

[0088] "Feature points" refer to notable points on the face, such as the eyes, nose, and mouth.

[0089] "Makeup breakdown" refers to the phenomenon of makeup becoming smudged, thinned, or messy.

[0090] "Wrinkles" refer to the fine folds and lines that form in the skin of the face.

[0091] "Optimization" refers to the process of adjusting the resolution and format of image data to reduce data size while maintaining maximum quality.

[0092] "Storage" refers to the act of recording processed image data in digital storage.

[0093] "Transmit" refers to the act of transferring stored image data to a user's device via digital communication.

[0094] The present invention relates to a photo studio system that automatically generates a background for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face.

[0095] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to a server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0096] The server receives the uploaded photo data. In particular, the server uses a server cluster with powerful computing power as its hardware, and frameworks such as Python and TensorFlow as its software for executing AI algorithms. For the received photo data, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates.

[0097] For example, if a user takes a photo indoors, the server can automatically change the background to a beach or park. This process uses a generative AI model such as GAN (generative adversarial network) to automatically generate the background.

[0098] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). Specifically, it utilizes OpenCV, an open-source computer vision library. This makes it possible to detect makeup smudges and wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful face photo.

[0099] For example, if a user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone. After correction and background generation are complete, the photo data is optimized by the server. This optimization process adjusts the resolution and format of the photo and saves it at the optimal quality. Adobe Photoshop's API and other image processing libraries can be used as image processing software.

[0100] Finally, the server sends the optimized, high-quality photo data to the user's device. The user receives this data and can view it through the application. The completed photo can then be downloaded or shared on social media. For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges corrected can be sent to the user's smartphone. The user can then share the photo on Instagram and other platforms.

[0101] Examples of prompts include:

[0102] User: Upload a photo from home and automatically generate a beautiful beach background. Also, smooth out facial wrinkles and send us your high-quality photo.

[0103] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1:

[0106] A user takes a photo on a device such as a smartphone. The user opens the camera app, composes the image, and presses the shutter button. As a result of this operation, the photo data is saved on the device.

[0107] Input: A photo taken by the user

[0108] Output: Photo data stored on the device

[0109] Step 2:

[0110] The device uses a dedicated application to upload the captured photo data to the server. The user launches the dedicated application, selects the photo, and presses the "Upload" button. The application then sends the photo data to the server via the network.

[0111] Input: Photo data stored on the device

[0112] Output: Photo data sent to the server

[0113] Step 3:

[0114] The server receives the uploaded photo data. The server receives the HTTP request and saves the sent photo file in local storage.

[0115] Input: Photo data sent from the device

[0116] Output: Photo data saved in local storage

[0117] Step 4:

[0118] The server runs an AI algorithm to identify the background of the photo data. The AI ​​algorithm uses segmentation models such as DeepLab or U-Net to distinguish between the background and foreground in the image. Specifically, it uses Python and TensorFlow.

[0119] Input: Photo data stored in local storage

[0120] Output: Image data with background identified

[0121] Step 5:

[0122] The server automatically generates multiple background candidates based on the identified background areas. The server generates new backgrounds using a generative adversarial network (GAN) or retrieves suitable background images from an existing background library.

[0123] Input: Image data with background identified

[0124] Output: Multiple background candidate images

[0125] Step 6:

[0126] The server selects the best background from the generated background candidates and applies it to the photo data. It uses an AI algorithm to select the background that best suits the background color and context. It then uses an image processing library such as the Photoshop API to change the background.

[0127] Input: Multiple background candidate images, original photo data

[0128] Output: Photo data with new background applied

[0129] Step 7:

[0130] The server uses the OpenCV library to analyze facial feature points to detect the user's face in the photo data, thereby identifying the position of the face and important points (eyes, nose, mouth, etc.).

[0131] Input: Photo data with new background applied

[0132] Output: Image data with face detected

[0133] Step 8:

[0134] The server automatically corrects smudged makeup and wrinkles, and uses an AI model to correct the detected areas, resulting in a smooth, beautiful facial photo.

[0135] Input: Image data with face detected

[0136] Output: Image data with makeup smudges and wrinkles corrected

[0137] Step 9:

[0138] The server optimizes the photo data after correction and background generation is complete, adjusting the resolution and format to provide high-quality photos.

[0139] Input: Image data with makeup smudges and wrinkles corrected

[0140] Output: Optimized image data

[0141] Step 10:

[0142] The server sends the optimized photo data to the device, which then transfers the photo data to the user's device via email or a dedicated application.

[0143] Input: Optimized image data

[0144] Output: Photo data sent to the user's device

[0145] Step 11:

[0146] Users receive high-quality photos, review them, open them in a dedicated application, and download or share them on social media.

[0147] Input: Photo data sent to the user's device

[0148] Output: User confirmed photo data, and downloaded or shared photo data

[0149] (Application example 1)

[0150] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0151] Conventional photo data and user image processing systems only allowed limited changes to backgrounds and facial image corrections, making it difficult to easily and highly accurately provide users with the scenes and aesthetics they desired. Furthermore, particularly in online shopping, they lacked the realistic simulation functionality required when users try on products. This resulted in the time and inconvenience involved when users selected products through a virtual try-on experience.

[0152] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0153] In this invention, the server includes means for receiving photo data taken by a user on a terminal, means for automatically generating a background and applying it to the photo data, means for detecting a person's face and correcting makeup smudges and wrinkles, and means for overlaying a product image on the user's photo to simulate trying on the product. This not only enables the user to obtain a high-quality image of the desired background and corrected face, but also enables the user to check the product in a more realistic manner through a virtual try-on simulation of the desired product.

[0154] "Device" means an electronic device used by a user to take and process photographic data. Examples include smartphones and tablets.

[0155] "Photo data" refers to image files taken using a device, including the user's face image and background.

[0156] The "means for automatically generating background" is a technology that identifies elements behind photographic data and generates or selects and applies any new background image.

[0157] "Means for detecting a person's face" refers to an algorithm for identifying the facial area of ​​a person in the photograph data, which can then identify the location of smudged makeup or wrinkles on the face.

[0158] "Means for correcting smudged makeup and wrinkles" refers to image processing technology for correcting smudged makeup and wrinkles on detected facial areas, thereby improving the appearance of facial images in photographs.

[0159] "Optimization and storage means" refers to the technology that adjusts the resolution and format of processed photo data and stores it on a server or cloud storage, thereby enabling the provision of high-quality photos.

[0160] "Means for simulating trying on a product by overlaying a product image on a user's photograph" refers to a technology that overlays an image of a selected product on a user's photograph, visually simulating the user wearing the product.

[0161] The "means for generating background candidates and selecting the most appropriate background" refers to an algorithm that automatically generates multiple background images and selects the most appropriate background from among them.

[0162] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[0163] System configuration

[0164] This system consists of a device used by the user and a server that processes and stores data. Users take photos with their smartphones, tablets, or other devices and upload the photo data to the server using a dedicated application. The system has the following main functions:

[0165] User photo taking and uploading

[0166] The user takes a photo of themselves using their device. After taking the photo, they upload it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0167] Automatic background generation

[0168] When the server receives photo data, it uses a generative AI model to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates, selects the most suitable one from them, and applies it to the photo data. For example, a photo taken by a user indoors can be automatically changed to a beach or park background.

[0169] Facial detection and correction

[0170] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server then automatically corrects the detected areas, resulting in a smooth, beautiful photo. For example, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[0171] Product image try-on simulation

[0172] The image of the product selected by the user is overlaid on the photo to simulate trying on the item. This allows users to have a virtual try-on experience without visiting a store. The product image is naturally composited onto the user's photo, resulting in a more realistic try-on simulation.

[0173] Optimize and save

[0174] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0175] Photo distribution

[0176] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[0177] For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges fixed will be sent to the user's smartphone. After this, the user can share the photo on Instagram and other platforms.

[0178] Hardware and software used

[0179] The server is equipped with a high-performance processor (e.g., Intel Xeon processor) and a large amount of memory (e.g., 32GB or more) to process data quickly. Software such as Python, OpenCV, TensorFlow, or Pytorch is used to efficiently perform processes such as face detection, background identification, and makeup correction.

[0180] An example prompt is:

[0181] "Please add a park background to a photo I took at home and fix any wrinkles."

[0182] "Fix the makeup smudges in this photo and add a boutique as a new background."

[0183] The above is a specific embodiment of this photo studio system, which allows anyone to easily create professional-quality photographs without having special skills or equipment.

[0184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0185] Step 1:

[0186] Users take photos and upload them to the server through a dedicated application.

[0187] Specific operation: The user takes a photo of themselves using the camera app on their smartphone. The photo is then sent to the server by opening a dedicated application and pressing the upload button.

[0188] Input: Photo data taken by the user.

[0189] Output: Photo data received by the server.

[0190] Step 2:

[0191] The server processes the received photo data and identifies the background portion.

[0192] How it works: The server inputs the received photo data into a deep learning model (e.g., TensorFlow or Pytorch) to identify the background. The AI ​​model identifies the background area of ​​the image.

[0193] Input: Photo data received by the server.

[0194] Output: Photo data with background areas identified.

[0195] Step 3:

[0196] The server generates multiple new background candidates based on the identified background portions.

[0197] Specific operation: The server generates or selects multiple background images and lists them as new background candidates. For example, background images such as beaches, parks, and cafes are generated.

[0198] Input: Identified background parts.

[0199] Output: Multiple generated background candidates.

[0200] Step 4:

[0201] The server selects the most suitable background and applies it to the photo data.

[0202] Specific operation: The server selects the most suitable background from the generated background candidates and combines it with the user's photo data. The background selection is performed using an algorithm to evaluate the suitability.

[0203] Input: Multiple generated background candidates.

[0204] Output: Photo data with background applied.

[0205] Step 5:

[0206] The server detects the user's face in the photo data and corrects smudged makeup and wrinkles.

[0207] Specific operation: The server uses a face detection algorithm (e.g., OpenCV) to detect facial features (eyes, nose, mouth, etc.) in the photo data, then corrects smudged makeup and wrinkles.

[0208] Input: Photo data with background applied.

[0209] Output: Photo data with makeup smudges and wrinkles corrected.

[0210] Step 6:

[0211] The server overlays product images onto the user's photo to simulate trying them on.

[0212] How it works: The server retrieves the product image selected by the user and naturally combines it with the user's photo, creating an image that looks as if the user is actually trying on the product.

[0213] Input: Photo data with makeup smudges and wrinkles corrected, and product images selected by the user.

[0214] Output: Photo data with product images overlaid.

[0215] Step 7:

[0216] The server optimizes and stores the photo data after correction, background generation, and product composition are completed.

[0217] Specific operation: The server adjusts the resolution and format of the photo data to optimize the data size, and stores high-quality photo data.

[0218] Input: Photo data with product images overlaid.

[0219] Output: Optimized, high-quality photo data.

[0220] Step 8:

[0221] The server sends optimized, high-quality photo data to the user's device.

[0222] How it works: The server sends the optimized photo data to the user's device via a dedicated application, and the user can open the application to view the edited, high-quality photo.

[0223] Input: Optimized, high-quality photo data.

[0224] Output: Photo data delivered to the user's device.

[0225] This allows users to easily create photos with high-quality backgrounds, photos with makeup smudges and wrinkles corrected, and even perform virtual try-on simulations.

[0226] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0227] The present invention combines an emotion engine with a photo studio system that automatically generates backgrounds for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention, with specific examples.

[0228] 1. User photo taking and uploading

[0229] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0230] 2. Emotional Recognition

[0231] When the server receives the uploaded photo data, the emotion engine analyzes the user's face in the photo. The emotion engine recognizes the emotion based on the user's facial expression. This recognized emotion information is used in the subsequent background generation and correction process.

[0232] 3. Automatic background generation

[0233] The server detects the background of the photo data. The emotion engine generates multiple background candidates based on the analyzed emotion information. These background candidates vary depending on the user's recognized emotion. For example, if the user's emotion is "happy," a bright and open background is generated.

[0234] The server selects the best background from the generated candidates and applies it to the photo data. When applying the background, it performs adjustments to ensure a natural blend.

[0235] 4. Face detection and correction

[0236] The server detects the user's face in the photo data and uses an algorithm to analyze facial features (eyes, nose, mouth, etc.). Based on the analysis results of the emotion engine, smudged makeup and wrinkles on the face are corrected. For example, if the user's emotion is "tired," corrections are made, focusing on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0237] 5. Optimize and save

[0238] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0239] 6. Photo distribution

[0240] Finally, the server sends the optimized, high-quality photo data to the user's device, where it can be viewed through the app, and the finished photo can be downloaded or shared on social media.

[0241] For example, the app recognizes happiness in photos taken at home, automatically changes the background to a beach, and fixes smudged makeup on the face, resulting in a high-quality photo sent to the user's smartphone. The user can then share the photo on Instagram or other platforms.

[0242] In this way, the combination of the emotion engine enables more personalized photo editing based on the user's emotions, allowing users to easily create professional-quality, individualized photos without the need for special skills or equipment.

[0243] The processing flow will be explained below.

[0244] Step 1:

[0245] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[0246] Step 2:

[0247] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[0248] Step 3:

[0249] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[0250] Step 4:

[0251] The server uses an emotion engine to analyze the user's face in the photo. The emotion engine recognizes the user's emotion based on their facial expression. For example, the emotion engine analyzes the user's face to detect emotions such as "happiness" or "sadness."

[0252] Step 5:

[0253] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[0254] Step 6:

[0255] The server generates multiple background candidates based on the emotion information obtained from the emotion engine. For example, if the user's emotion is "happy," a bright and open background will be suggested.

[0256] Step 7:

[0257] The server selects the most suitable background from the generated background candidates. The server applies the selected background to the photo data. When applying the background, adjustments are made to ensure a natural blend.

[0258] Step 8:

[0259] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[0260] Step 9:

[0261] The server detects smudged makeup and wrinkles on the face. Based on emotion information, it focuses on areas that require particular correction. For example, if the emotion "fatigue" is detected, it focuses on correcting the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0262] Step 10:

[0263] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[0264] Step 11:

[0265] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[0266] Step 12:

[0267] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[0268] Example 2

[0269] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0270] Editing photos taken by users with professional quality requires advanced skills and specialized knowledge. It is particularly difficult for average users to change backgrounds, modify facial features, or perform personalized editing based on the user's emotions. The present invention aims to solve the above-mentioned problems by providing a system that allows users to easily perform high-quality photo editing.

[0271] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0272] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for analyzing the user's facial expression contained in the received image data and recognizing emotions, means for automatically generating a background based on the emotion information and applying it to the image data, means for detecting a person's face from the image data and analyzing facial features to correct makeup smudges and wrinkles, means for optimizing and saving the corrected image data, and means for transmitting the optimized image data to the terminal. This enables users to easily create photos that combine professional quality and individual response, even without special skills or equipment.

[0273] A "terminal" is an electronic device that a user uses to take pictures and receive processed image data.

[0274] A "server" is a central computer system that receives and processes image data sent by users.

[0275] "Image data" refers to photographic data taken by a user using a device.

[0276] An "emotion engine" is an algorithm and software that analyzes the user's facial expressions contained in image data and recognizes emotions.

[0277] The "automatic background generation means" is a means for automatically generating a background image based on the user's emotional information and applying it to image data.

[0278] The "face part detection means" refers to an algorithm and software for detecting and analyzing a person's face part from image data.

[0279] The "facial feature point analysis means" is a means for analyzing the position and shape of each part of the face (eyes, nose, mouth, etc.).

[0280] The "means for correcting makeup smudges and wrinkles" refers to algorithms and software for automatically correcting makeup smudges and wrinkles on detected facial areas.

[0281] The "optimization means" is a means for adjusting the resolution and format of the corrected image data and saving it with optimal quality.

[0282] "Emotional information" refers to the emotional data recognized by the emotion engine after analyzing the user's facial expressions.

[0283] System Overview

[0284] This system uses an emotion engine to automatically generate backgrounds for image data taken by a user on a device, and corrects makeup smudges and wrinkles on the face. This system provides high-quality photo editing personalized according to the user's emotions.

[0285] Hardware and Software Configuration

[0286] Terminal

[0287] Hardware: Smartphones, tablets, etc.

[0288] Software: Dedicated application

[0289] server

[0290] Hardware: high-performance computers, cloud servers

[0291] Software: Emotion engine, image processing algorithms, generative AI models

[0292] Specific processing explanation

[0293] User Actions

[0294] Users take a photo of their face using a device such as a smartphone. After taking the photo, they upload it to the server using a dedicated application. For example, when a user opens the app and presses the "upload photo" button, the device sends the photo data to the server.

[0295] Emotion recognition

[0296] When the server receives the photo data, the emotion engine analyzes the user's face in the photo. The emotion engine detects facial features (eyes, nose, mouth, eyebrows, etc.) and recognizes emotions from facial expressions. The recognized emotion information is generated as emotion labels such as "happiness," "sadness," and "surprise," and is used in the background generation and face correction processes.

[0297] Automatic background generation

[0298] The server generates multiple background candidates based on the emotion information from the emotion engine. Using a generative AI model, for example, in the case of "happiness," it generates a bright, open background image such as a beach or park. The server selects the most suitable background from the generated candidates and applies it to the photo data. When compositing the photo, color correction and border smoothing processes are performed.

[0299] Facial detection and correction

[0300] The server detects the user's face in the photo data and analyzes facial features. It then automatically corrects smudged makeup and wrinkles in the detected facial areas. In particular, if the "fatigue" emotion is recognized, corrections are made to make the area around the eyes clearer and the cheeks brighter.

[0301] Optimize and save

[0302] Once the photo data has been retouched, it is sent to a server where it is optimized for resolution and format, and then stored in high quality in cloud storage or a database.

[0303] Photo distribution

[0304] Finally, the server sends the optimized, high-quality photo data to the user's device, where the user can view the edited photo through a dedicated application. The finished photo can then be downloaded or shared on social media.

[0305] Examples and prompts

[0306] Examples:

[0307] For example, if you upload a photo taken at home, the system will recognize your sense of happiness, automatically change the background to a beach, fix any makeup smudges, and send the high-quality photo to your smartphone. Users can then share the photo on Instagram and other platforms.

[0308] Example prompt:

[0309] "A user takes a photo of themselves and uploads it to the server. The server automatically changes the background of the photo to a beach and fixes any makeup that has been smudged on the user's face."

[0310] In this way, the system can automatically perform high-level photo editing based on the user's emotions, making it possible for users without special skills or equipment to easily create photos that combine professional quality with individual responsiveness.

[0311] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0312] Step 1: User takes and uploads a photo

[0313] Input: Photo data taken by the user using the smartphone camera app

[0314] Specific operation: The user launches the camera app on their smartphone, takes a selfie, and then opens the dedicated application and presses the "Upload photo" button.

[0315] Output: The device sends the photo data to the server.

[0316] Step 2: The server receives the photo data

[0317] Input: Photo data sent from the device

[0318] Specific operation: The server receives the HTTP request and stores the photo data in an internal database.

[0319] Output: Photo data stored on the server

[0320] Step 3: The emotion engine analyzes the face and recognizes the emotion

[0321] Input: Photo data stored on the server

[0322] Specific operation: The server starts the emotion engine and analyzes the face in the photo. It detects facial features (eyes, nose, mouth, eyebrows, etc.) and infers emotions from facial expressions.

[0323] Output: Generate emotion information (e.g., emotion labels such as "happiness," "sadness," and "surprise").

[0324] Step 4: The server automatically generates the background

[0325] Input: Emotional information and photo data

[0326] How it works: Based on the emotion information from the emotion engine, the generative AI model is used to generate multiple background candidates. For example, for "happiness," background images of a beach or park are generated. Then, the most suitable background is selected.

[0327] Output: Optimal background image

[0328] Step 5: The server applies the background to the photo data

[0329] Input: Ideal background image and photo data

[0330] How it works: The server detects the background of the photo data and applies the generated background image. It also performs color correction and border smoothing to achieve a natural composite.

[0331] Output: Photo data with background applied

[0332] Step 6: The server detects the face and corrects any smudges or wrinkles.

[0333] Input: Photo data with background applied

[0334] What it does: The server uses a face detection algorithm to identify faces in the photo. It analyzes facial features and corrects smudged makeup and wrinkles. For example, if it detects a "tired" emotion, it brightens the area around the eyes and cheeks.

[0335] Output: Photo data with face correction

[0336] Step 7: The server optimizes and stores the photo data

[0337] Input: Photo data with face correction

[0338] What it does: The server optimizes the resolution and adjusts the format, then stores it in cloud storage or a database.

[0339] Output: Optimized photo data

[0340] Step 8: The server sends the optimized photo data to the device.

[0341] Input: Optimized photo data

[0342] Specific operation: Export the completed photo data in an appropriate format such as JSON and send it to the user's device.

[0343] Output: High-quality photo data sent to your device

[0344] Step 9: User reviews and shares optimized photo data

[0345] Input: High-quality photo data sent to the device

[0346] What it does: A user opens the app, taps on a photo preview to view it, and then uses the "Download" and "Share" buttons to post the photo to Instagram and Facebook.

[0347] Output: User's social media photos

[0348] (Application example 2)

[0349] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0350] Existing photo editing systems require users to manually change backgrounds and modify faces in photos they take, which requires a significant amount of time and expertise. Furthermore, they are unable to take user emotions into account when modifying images, resulting in often unsatisfactory results. Therefore, there is a need for a system that allows users to easily and quickly create professional-quality photos that match their emotions.

[0351] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photo data taken by a user with a terminal, means for automatically generating a background and applying it to the photo data, means for analyzing the user's facial expression using an emotion engine and recognizing the emotion, means for detecting the person's face and correcting makeup smudges and wrinkles based on the emotion, means for optimizing and saving the corrected photo, and means for transmitting the optimized photo data to the terminal. This enables users to easily create high-quality photos that reflect their emotions in a short amount of time, without having special skills or equipment.

[0352] A "terminal" is an electronic device with communication capabilities that a user owns, including smartphones and tablets.

[0353] "Photo data" refers to image information that a user takes with a device and stores in digital format.

[0354] "Means for automatically generating backgrounds" refers to technology that recognizes the background portion of photo data and generates a new background image using an algorithm.

[0355] An "emotion engine" is a software or hardware component that analyzes a user's facial expressions and recognizes their emotions.

[0356] "Methods for correcting smudged makeup and wrinkles" refers to technology that uses an algorithm to automatically correct smudged makeup and wrinkles on the face in a photo.

[0357] "Optimization means" refers to a technique that performs resolution and data compression on the edited photographs to appropriately adjust the data size while maintaining quality.

[0358] "Emotion-based correction method" refers to a technology that optimizes the correction pattern for facial makeup smudges and wrinkles based on the user's recognized emotional information.

[0359] "Background candidates" refer to multiple options for background images that can be applied to photo data.

[0360] "Facial feature points" refer to major points such as the eyes, nose, and mouth that are detected during facial analysis.

[0361] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[0362] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads the photo data to a server using a dedicated application. The device then sends the photo data to the server, which then moves on to the next processing step.

[0363] The server receives the uploaded photo data. The received photo data is analyzed using an emotion engine to recognize the user's facial expression and the emotion it conveys. The recognized emotion information is used in subsequent background generation and facial correction processes. Machine learning libraries such as TensorFlow are used to implement the emotion engine.

[0364] The server then detects the background of the photo data and generates multiple background candidates based on the emotional information analyzed by the emotion engine. These background candidates vary depending on the user's recognized emotion; for example, if the emotion is "happiness," multiple bright and open backgrounds are generated. The optimal background is selected from these and applied to the photo data to create a natural look.

[0365] Next, the server detects the user's face in the photo data and analyzes facial features (eyes, nose, mouth, etc.). Based on the emotion engine's analysis results, it corrects smudged makeup and wrinkles on the face. For example, if the user's emotion is "tired," corrections are made that focus particularly on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0366] Once the photo data has been corrected and background generation is complete, it is optimized by the server. Optimization involves adjusting the photo resolution and data format to provide high-quality photos while keeping the data size appropriately low. This optimization process uses the image processing library OpenCV.

[0367] Finally, the server sends the optimized, high-quality photo data to the user's device, where they can view it and download it through the app or share it on social media.

[0368] In a real-world example, when a user uploads a photo taken at home, the emotion engine recognizes the feeling of happiness, changes the background to a beach, fixes makeup smudges, and sends the high-quality photo to the user's smartphone. The user can then share the photo on social media such as Instagram.

[0369] An example prompt is:

[0370] "Based on pre-entered user photos, use a generative AI model to recognize emotions, and then optimally modify the photo background and face based on the emotions. Use TensorFlow for emotion recognition."

[0371] In this way, by combining the emotion engine, it is possible to achieve more personalized photo editing according to the user's emotions, allowing users to easily create high-quality photos in a short amount of time, even without specialized skills or equipment.

[0372] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0373] Step 1:

[0374] Users take their own photos using a device such as a smartphone. After taking the photo, the photo is uploaded to a server via a dedicated application. The input here is the photo data taken by the user, and the output is the uploaded photo data.

[0375] Step 2:

[0376] The server receives uploaded photo data. The received data is stored for processing by the emotion engine. The input here is the uploaded photo data, and the output is the photo data stored on the server.

[0377] Step 3:

[0378] The server uses an emotion engine to analyze the user's facial expressions in the photo data and recognize emotions. The input is the photo data, and the output is the user's emotional information. Generative AI models such as TensorFlow are used for emotion analysis.

[0379] Step 4:

[0380] The server recognizes the background of the photo data and generates multiple background candidates based on the emotion information. It then selects the most suitable background from among them. The input here is the user's emotion information and the photo data, and the output is the most suitable background.

[0381] Step 5:

[0382] The server applies the optimal background to the photo data, creating a natural composite. The input is the selected background and the photo data, and the output is the new photo data with the background applied.

[0383] Step 6:

[0384] The server detects the user's face in the photo data and analyzes facial feature points (eyes, nose, mouth, etc.). It then corrects makeup smudges and wrinkles based on the emotion. The input here is the photo data and facial feature points, and the output is the corrected face. Image processing libraries such as OpenCV are used to analyze and correct facial feature points.

[0385] Step 7:

[0386] The server optimizes the modified photo data. The input is the modified photo data, and the output is optimized high-quality photo data. This optimization includes data compression and resolution adjustment.

[0387] Step 8:

[0388] The server sends the optimized photo data to the user's device, where the user can view the data through the application, download it, or share it on social media. The input here is the optimized photo data, and the output is the photo data sent to the device.

[0389] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0390] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0391] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0392] [Second embodiment]

[0393] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0394] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0395] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0396] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0397] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0398] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0399] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0400] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0401] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0402] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0403] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0404] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0405] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[0406] 1. User photo taking and uploading

[0407] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0408] 2. Automatic background generation

[0409] The server receives the uploaded photo data. After receiving it, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates. The server selects the best one from these background candidates and applies it to the photo data.

[0410] For example, if a user takes a photo indoors, the server can automatically change it to a beach or park background.

[0411] 3. Face detection and correction

[0412] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful photo.

[0413] Specifically, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[0414] 4. Optimize and save

[0415] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0416] 5. Photo distribution

[0417] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[0418] For example, a photo taken at home can be automatically changed to a beach background, and any smudged makeup on the face can be corrected, resulting in a high-quality photo sent to the user's smartphone. After this, the user can share the photo on Instagram or other platforms.

[0419] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[0420] The processing flow will be explained below.

[0421] Step 1:

[0422] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[0423] Step 2:

[0424] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[0425] Step 3:

[0426] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[0427] Step 4:

[0428] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[0429] Step 5:

[0430] The server generates multiple background candidates for the detected background portion, and then selects the best one from the generated background candidates.

[0431] Step 6:

[0432] The server applies the selected background to the photo data, and then performs the processing to replace the background.

[0433] Step 7:

[0434] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[0435] Step 8:

[0436] The server detects smudges and wrinkles on the face, and applies an automatic correction algorithm to the detected areas.

[0437] Step 9:

[0438] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[0439] Step 10:

[0440] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[0441] Step 11:

[0442] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[0443] Example 1

[0444] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0445] Conventional image editing systems require advanced skills and specialized software to perform complex processes on photos taken by users, such as changing the background, smoothing out makeup, or correcting wrinkles. This makes it difficult for average users to easily create professional-quality photos. Furthermore, there is no function to automatically select the optimal background from multiple background candidates, making manual selection a time-consuming process.

[0446] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0447] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for identifying a background portion of the image data and selecting an optimal background from a plurality of automatically generated background candidates and applying it to the image data, means for detecting the user's face in the image data and analyzing facial feature points to correct smudged makeup and wrinkles, means for optimizing and saving the image data after correction and background generation is complete, and means for transmitting the optimized image data to the terminal. This enables users to easily obtain high-quality photos with automatically selected backgrounds and corrected smudged makeup and wrinkles, even without special skills or equipment.

[0448] "User" means an individual or end user who uses the System.

[0449] "Device" refers to a computing device such as a smartphone, tablet, or PC.

[0450] "Image data" refers to digital image files that users take with their devices and upload to the server.

[0451] A "server" is a remote computer system that receives, processes, stores, and distributes image data.

[0452] "Background" refers to the area of ​​the image data other than the user's face or other people.

[0453] "Background candidates" are multiple background image options generated by the system.

[0454] "Facial area" refers to the area in the image data that is occupied by the user's face.

[0455] "Feature points" refer to notable points on the face, such as the eyes, nose, and mouth.

[0456] "Makeup breakdown" refers to the phenomenon of makeup becoming smudged, thinned, or messy.

[0457] "Wrinkles" refer to the fine folds and lines that form in the skin of the face.

[0458] "Optimization" refers to the process of adjusting the resolution and format of image data to reduce data size while maintaining maximum quality.

[0459] "Storage" refers to the act of recording processed image data in digital storage.

[0460] "Transmit" refers to the act of transferring stored image data to a user's device via digital communication.

[0461] The present invention relates to a photo studio system that automatically generates a background for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face.

[0462] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to a server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0463] The server receives the uploaded photo data. In particular, the server uses a server cluster with powerful computing power as its hardware, and frameworks such as Python and TensorFlow as its software for executing AI algorithms. For the received photo data, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates.

[0464] For example, if a user takes a photo indoors, the server can automatically change the background to a beach or park. This process uses a generative AI model such as GAN (generative adversarial network) to automatically generate the background.

[0465] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). Specifically, it utilizes OpenCV, an open-source computer vision library. This makes it possible to detect makeup smudges and wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful face photo.

[0466] For example, if a user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone. After correction and background generation are complete, the photo data is optimized by the server. This optimization process adjusts the resolution and format of the photo and saves it at the optimal quality. Adobe Photoshop's API and other image processing libraries can be used as image processing software.

[0467] Finally, the server sends the optimized, high-quality photo data to the user's device. The user receives this data and can view it through the application. The completed photo can then be downloaded or shared on social media. For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges corrected can be sent to the user's smartphone. The user can then share the photo on Instagram and other platforms.

[0468] Examples of prompts include:

[0469] User: Upload a photo from home and automatically generate a beautiful beach background. Also, smooth out facial wrinkles and send us your high-quality photo.

[0470] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[0471] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0472] Step 1:

[0473] A user takes a photo on a device such as a smartphone. The user opens the camera app, composes the image, and presses the shutter button. As a result of this operation, the photo data is saved on the device.

[0474] Input: A photo taken by the user

[0475] Output: Photo data stored on the device

[0476] Step 2:

[0477] The device uses a dedicated application to upload the captured photo data to the server. The user launches the dedicated application, selects the photo, and presses the "Upload" button. The application then sends the photo data to the server via the network.

[0478] Input: Photo data stored on the device

[0479] Output: Photo data sent to the server

[0480] Step 3:

[0481] The server receives the uploaded photo data. The server receives the HTTP request and saves the sent photo file in local storage.

[0482] Input: Photo data sent from the device

[0483] Output: Photo data saved in local storage

[0484] Step 4:

[0485] The server runs an AI algorithm to identify the background of the photo data. The AI ​​algorithm uses segmentation models such as DeepLab or U-Net to distinguish between the background and foreground in the image. Specifically, it uses Python and TensorFlow.

[0486] Input: Photo data stored in local storage

[0487] Output: Image data with background identified

[0488] Step 5:

[0489] The server automatically generates multiple background candidates based on the identified background areas. The server generates new backgrounds using a generative adversarial network (GAN) or retrieves suitable background images from an existing background library.

[0490] Input: Image data with background identified

[0491] Output: Multiple background candidate images

[0492] Step 6:

[0493] The server selects the best background from the generated background candidates and applies it to the photo data. It uses an AI algorithm to select the background that best suits the background color and context. It then uses an image processing library such as the Photoshop API to change the background.

[0494] Input: Multiple background candidate images, original photo data

[0495] Output: Photo data with new background applied

[0496] Step 7:

[0497] The server uses the OpenCV library to analyze facial feature points to detect the user's face in the photo data, thereby identifying the position of the face and important points (eyes, nose, mouth, etc.).

[0498] Input: Photo data with new background applied

[0499] Output: Image data with face detected

[0500] Step 8:

[0501] The server automatically corrects smudged makeup and wrinkles, and uses an AI model to correct the detected areas, resulting in a smooth, beautiful facial photo.

[0502] Input: Image data with face detected

[0503] Output: Image data with makeup smudges and wrinkles corrected

[0504] Step 9:

[0505] The server optimizes the photo data after correction and background generation is complete, adjusting the resolution and format to provide high-quality photos.

[0506] Input: Image data with makeup smudges and wrinkles corrected

[0507] Output: Optimized image data

[0508] Step 10:

[0509] The server sends the optimized photo data to the device, which then transfers the photo data to the user's device via email or a dedicated application.

[0510] Input: Optimized image data

[0511] Output: Photo data sent to the user's device

[0512] Step 11:

[0513] Users receive high-quality photos, review them, open them in a dedicated application, and download or share them on social media.

[0514] Input: Photo data sent to the user's device

[0515] Output: User confirmed photo data, and downloaded or shared photo data

[0516] (Application example 1)

[0517] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0518] Conventional photo data and user image processing systems only allowed limited changes to backgrounds and facial image corrections, making it difficult to easily and highly accurately provide users with the scenes and aesthetics they desired. Furthermore, particularly in online shopping, they lacked the realistic simulation functionality required when users try on products. This resulted in the time and inconvenience involved when users selected products through a virtual try-on experience.

[0519] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0520] In this invention, the server includes means for receiving photo data taken by a user on a terminal, means for automatically generating a background and applying it to the photo data, means for detecting a person's face and correcting makeup smudges and wrinkles, and means for overlaying a product image on the user's photo to simulate trying on the product. This not only enables the user to obtain a high-quality image of the desired background and corrected face, but also enables the user to check the product in a more realistic manner through a virtual try-on simulation of the desired product.

[0521] "Device" means an electronic device used by a user to take and process photographic data. Examples include smartphones and tablets.

[0522] "Photo data" refers to image files taken using a device, including the user's face image and background.

[0523] The "means for automatically generating background" is a technology that identifies elements behind photographic data and generates or selects and applies any new background image.

[0524] "Means for detecting a person's face" refers to an algorithm for identifying the facial area of ​​a person in the photograph data, which can then identify the location of smudged makeup or wrinkles on the face.

[0525] "Means for correcting smudged makeup and wrinkles" refers to image processing technology for correcting smudged makeup and wrinkles on detected facial areas, thereby improving the appearance of facial images in photographs.

[0526] "Optimization and storage means" refers to the technology that adjusts the resolution and format of processed photo data and stores it on a server or cloud storage, thereby enabling the provision of high-quality photos.

[0527] "Means for simulating trying on a product by overlaying a product image on a user's photograph" refers to a technology that overlays an image of a selected product on a user's photograph, visually simulating the user wearing the product.

[0528] The "means for generating background candidates and selecting the most appropriate background" refers to an algorithm that automatically generates multiple background images and selects the most appropriate background from among them.

[0529] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[0530] System configuration

[0531] This system consists of a device used by the user and a server that processes and stores data. Users take photos with their smartphones, tablets, or other devices and upload the photo data to the server using a dedicated application. The system has the following main functions:

[0532] User photo taking and uploading

[0533] The user takes a photo of themselves using their device. After taking the photo, they upload it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0534] Automatic background generation

[0535] When the server receives photo data, it uses a generative AI model to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates, selects the most suitable one from them, and applies it to the photo data. For example, a photo taken by a user indoors can be automatically changed to a beach or park background.

[0536] Facial detection and correction

[0537] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server then automatically corrects the detected areas, resulting in a smooth, beautiful photo. For example, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[0538] Product image try-on simulation

[0539] The image of the product selected by the user is overlaid on the photo to simulate trying on the item. This allows users to have a virtual try-on experience without visiting a store. The product image is naturally composited onto the user's photo, resulting in a more realistic try-on simulation.

[0540] Optimize and save

[0541] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0542] Photo distribution

[0543] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[0544] For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges fixed will be sent to the user's smartphone. After this, the user can share the photo on Instagram and other platforms.

[0545] Hardware and software used

[0546] The server is equipped with a high-performance processor (e.g., Intel Xeon processor) and a large amount of memory (e.g., 32GB or more) to process data quickly. Software such as Python, OpenCV, TensorFlow, or Pytorch is used to efficiently perform processes such as face detection, background identification, and makeup correction.

[0547] An example prompt is:

[0548] "Please add a park background to a photo I took at home and fix any wrinkles."

[0549] "Fix the makeup smudges in this photo and add a boutique as a new background."

[0550] The above is a specific embodiment of this photo studio system, which allows anyone to easily create professional-quality photographs without having special skills or equipment.

[0551] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0552] Step 1:

[0553] Users take photos and upload them to the server through a dedicated application.

[0554] Specific operation: The user takes a photo of themselves using the camera app on their smartphone. The photo is then sent to the server by opening a dedicated application and pressing the upload button.

[0555] Input: Photo data taken by the user.

[0556] Output: Photo data received by the server.

[0557] Step 2:

[0558] The server processes the received photo data and identifies the background portion.

[0559] How it works: The server inputs the received photo data into a deep learning model (e.g., TensorFlow or Pytorch) to identify the background. The AI ​​model identifies the background area of ​​the image.

[0560] Input: Photo data received by the server.

[0561] Output: Photo data with background areas identified.

[0562] Step 3:

[0563] The server generates multiple new background candidates based on the identified background portions.

[0564] Specific operation: The server generates or selects multiple background images and lists them as new background candidates. For example, background images such as beaches, parks, and cafes are generated.

[0565] Input: Identified background parts.

[0566] Output: Multiple generated background candidates.

[0567] Step 4:

[0568] The server selects the most suitable background and applies it to the photo data.

[0569] Specific operation: The server selects the most suitable background from the generated background candidates and combines it with the user's photo data. The background selection is performed using an algorithm to evaluate the suitability.

[0570] Input: Multiple generated background candidates.

[0571] Output: Photo data with background applied.

[0572] Step 5:

[0573] The server detects the user's face in the photo data and corrects smudged makeup and wrinkles.

[0574] Specific operation: The server uses a face detection algorithm (e.g., OpenCV) to detect facial features (eyes, nose, mouth, etc.) in the photo data, then corrects smudged makeup and wrinkles.

[0575] Input: Photo data with background applied.

[0576] Output: Photo data with makeup smudges and wrinkles corrected.

[0577] Step 6:

[0578] The server overlays product images onto the user's photo to simulate trying them on.

[0579] How it works: The server retrieves the product image selected by the user and naturally combines it with the user's photo, creating an image that looks as if the user is actually trying on the product.

[0580] Input: Photo data with makeup smudges and wrinkles corrected, and product images selected by the user.

[0581] Output: Photo data with product images overlaid.

[0582] Step 7:

[0583] The server optimizes and stores the photo data after correction, background generation, and product composition are completed.

[0584] Specific operation: The server adjusts the resolution and format of the photo data to optimize the data size, and stores high-quality photo data.

[0585] Input: Photo data with product images overlaid.

[0586] Output: Optimized, high-quality photo data.

[0587] Step 8:

[0588] The server sends optimized, high-quality photo data to the user's device.

[0589] How it works: The server sends the optimized photo data to the user's device via a dedicated application, and the user can open the application to view the edited, high-quality photo.

[0590] Input: Optimized, high-quality photo data.

[0591] Output: Photo data delivered to the user's device.

[0592] This allows users to easily create photos with high-quality backgrounds, photos with makeup smudges and wrinkles corrected, and even perform virtual try-on simulations.

[0593] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0594] The present invention combines an emotion engine with a photo studio system that automatically generates backgrounds for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention, with specific examples.

[0595] 1. User photo taking and uploading

[0596] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0597] 2. Emotional Recognition

[0598] When the server receives the uploaded photo data, the emotion engine analyzes the user's face in the photo. The emotion engine recognizes the emotion based on the user's facial expression. This recognized emotion information is used in the subsequent background generation and correction process.

[0599] 3. Automatic background generation

[0600] The server detects the background of the photo data. The emotion engine generates multiple background candidates based on the analyzed emotion information. These background candidates vary depending on the user's recognized emotion. For example, if the user's emotion is "happy," a bright and open background is generated.

[0601] The server selects the best background from the generated candidates and applies it to the photo data. When applying the background, it performs adjustments to ensure a natural blend.

[0602] 4. Face detection and correction

[0603] The server detects the user's face in the photo data and uses an algorithm to analyze facial features (eyes, nose, mouth, etc.). Based on the analysis results of the emotion engine, smudged makeup and wrinkles on the face are corrected. For example, if the user's emotion is "tired," corrections are made, focusing on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0604] 5. Optimize and save

[0605] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0606] 6. Photo distribution

[0607] Finally, the server sends the optimized, high-quality photo data to the user's device, where it can be viewed through the app, and the finished photo can be downloaded or shared on social media.

[0608] For example, the app recognizes happiness in photos taken at home, automatically changes the background to a beach, and fixes smudged makeup on the face, resulting in a high-quality photo sent to the user's smartphone. The user can then share the photo on Instagram or other platforms.

[0609] In this way, the combination of the emotion engine enables more personalized photo editing based on the user's emotions, allowing users to easily create professional-quality, individualized photos without the need for special skills or equipment.

[0610] The processing flow will be explained below.

[0611] Step 1:

[0612] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[0613] Step 2:

[0614] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[0615] Step 3:

[0616] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[0617] Step 4:

[0618] The server uses an emotion engine to analyze the user's face in the photo. The emotion engine recognizes the user's emotion based on their facial expression. For example, the emotion engine analyzes the user's face to detect emotions such as "happiness" or "sadness."

[0619] Step 5:

[0620] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[0621] Step 6:

[0622] The server generates multiple background candidates based on the emotion information obtained from the emotion engine. For example, if the user's emotion is "happy," a bright and open background will be suggested.

[0623] Step 7:

[0624] The server selects the most suitable background from the generated background candidates. The server applies the selected background to the photo data. When applying the background, adjustments are made to ensure a natural blend.

[0625] Step 8:

[0626] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[0627] Step 9:

[0628] The server detects smudged makeup and wrinkles on the face. Based on emotion information, it focuses on areas that require particular correction. For example, if the emotion "fatigue" is detected, it focuses on correcting the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0629] Step 10:

[0630] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[0631] Step 11:

[0632] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[0633] Step 12:

[0634] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[0635] Example 2

[0636] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0637] Editing photos taken by users with professional quality requires advanced skills and specialized knowledge. It is particularly difficult for average users to change backgrounds, modify facial features, or perform personalized editing based on the user's emotions. The present invention aims to solve the above-mentioned problems by providing a system that allows users to easily perform high-quality photo editing.

[0638] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0639] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for analyzing the user's facial expression contained in the received image data and recognizing emotions, means for automatically generating a background based on the emotion information and applying it to the image data, means for detecting a person's face from the image data and analyzing facial features to correct makeup smudges and wrinkles, means for optimizing and saving the corrected image data, and means for transmitting the optimized image data to the terminal. This enables users to easily create photos that combine professional quality and individual response, even without special skills or equipment.

[0640] A "terminal" is an electronic device that a user uses to take pictures and receive processed image data.

[0641] A "server" is a central computer system that receives and processes image data sent by users.

[0642] "Image data" refers to photographic data taken by a user using a device.

[0643] An "emotion engine" is an algorithm and software that analyzes the user's facial expressions contained in image data and recognizes emotions.

[0644] The "automatic background generation means" is a means for automatically generating a background image based on the user's emotional information and applying it to image data.

[0645] The "face part detection means" refers to an algorithm and software for detecting and analyzing a person's face part from image data.

[0646] The "facial feature point analysis means" is a means for analyzing the position and shape of each part of the face (eyes, nose, mouth, etc.).

[0647] The "means for correcting makeup smudges and wrinkles" refers to algorithms and software for automatically correcting makeup smudges and wrinkles on detected facial areas.

[0648] The "optimization means" is a means for adjusting the resolution and format of the corrected image data and saving it with optimal quality.

[0649] "Emotional information" refers to the emotional data recognized by the emotion engine after analyzing the user's facial expressions.

[0650] System Overview

[0651] This system uses an emotion engine to automatically generate backgrounds for image data taken by a user on a device, and corrects makeup smudges and wrinkles on the face. This system provides high-quality photo editing personalized according to the user's emotions.

[0652] Hardware and Software Configuration

[0653] Terminal

[0654] Hardware: Smartphones, tablets, etc.

[0655] Software: Dedicated application

[0656] server

[0657] Hardware: high-performance computers, cloud servers

[0658] Software: Emotion engine, image processing algorithms, generative AI models

[0659] Specific processing explanation

[0660] User Actions

[0661] Users take a photo of their face using a device such as a smartphone. After taking the photo, they upload it to the server using a dedicated application. For example, when a user opens the app and presses the "upload photo" button, the device sends the photo data to the server.

[0662] Emotion recognition

[0663] When the server receives the photo data, the emotion engine analyzes the user's face in the photo. The emotion engine detects facial features (eyes, nose, mouth, eyebrows, etc.) and recognizes emotions from facial expressions. The recognized emotion information is generated as emotion labels such as "happiness," "sadness," and "surprise," and is used in the background generation and face correction processes.

[0664] Automatic background generation

[0665] The server generates multiple background candidates based on the emotion information from the emotion engine. Using a generative AI model, for example, in the case of "happiness," it generates a bright, open background image such as a beach or park. The server selects the most suitable background from the generated candidates and applies it to the photo data. When compositing the photo, color correction and border smoothing processes are performed.

[0666] Facial detection and correction

[0667] The server detects the user's face in the photo data and analyzes facial features. It then automatically corrects smudged makeup and wrinkles in the detected facial areas. In particular, if the "fatigue" emotion is recognized, corrections are made to make the area around the eyes clearer and the cheeks brighter.

[0668] Optimize and save

[0669] Once the photo data has been retouched, it is sent to a server where it is optimized for resolution and format, and then stored in high quality in cloud storage or a database.

[0670] Photo distribution

[0671] Finally, the server sends the optimized, high-quality photo data to the user's device, where the user can view the edited photo through a dedicated application. The finished photo can then be downloaded or shared on social media.

[0672] Examples and prompts

[0673] Examples:

[0674] For example, if you upload a photo taken at home, the system will recognize your sense of happiness, automatically change the background to a beach, fix any makeup smudges, and send the high-quality photo to your smartphone. Users can then share the photo on Instagram and other platforms.

[0675] Example prompt:

[0676] "A user takes a photo of themselves and uploads it to the server. The server automatically changes the background of the photo to a beach and fixes any makeup that has been smudged on the user's face."

[0677] In this way, the system can automatically perform high-level photo editing based on the user's emotions, making it possible for users without special skills or equipment to easily create photos that combine professional quality with individual responsiveness.

[0678] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0679] Step 1: User takes and uploads a photo

[0680] Input: Photo data taken by the user using the smartphone camera app

[0681] Specific operation: The user launches the camera app on their smartphone, takes a selfie, and then opens the dedicated application and presses the "Upload photo" button.

[0682] Output: The device sends the photo data to the server.

[0683] Step 2: The server receives the photo data

[0684] Input: Photo data sent from the device

[0685] Specific operation: The server receives the HTTP request and stores the photo data in an internal database.

[0686] Output: Photo data stored on the server

[0687] Step 3: The emotion engine analyzes the face and recognizes the emotion

[0688] Input: Photo data stored on the server

[0689] Specific operation: The server starts the emotion engine and analyzes the face in the photo. It detects facial features (eyes, nose, mouth, eyebrows, etc.) and infers emotions from facial expressions.

[0690] Output: Generate emotion information (e.g., emotion labels such as "happiness," "sadness," and "surprise").

[0691] Step 4: The server automatically generates the background

[0692] Input: Emotional information and photo data

[0693] How it works: Based on the emotion information from the emotion engine, the generative AI model is used to generate multiple background candidates. For example, for "happiness," background images of a beach or park are generated. Then, the most suitable background is selected.

[0694] Output: Optimal background image

[0695] Step 5: The server applies the background to the photo data

[0696] Input: Ideal background image and photo data

[0697] How it works: The server detects the background of the photo data and applies the generated background image. It also performs color correction and border smoothing to achieve a natural composite.

[0698] Output: Photo data with background applied

[0699] Step 6: The server detects the face and corrects any smudges or wrinkles.

[0700] Input: Photo data with background applied

[0701] What it does: The server uses a face detection algorithm to identify faces in the photo. It analyzes facial features and corrects smudged makeup and wrinkles. For example, if it detects a "tired" emotion, it brightens the area around the eyes and cheeks.

[0702] Output: Photo data with face correction

[0703] Step 7: The server optimizes and stores the photo data

[0704] Input: Photo data with face correction

[0705] What it does: The server optimizes the resolution and adjusts the format, then stores it in cloud storage or a database.

[0706] Output: Optimized photo data

[0707] Step 8: The server sends the optimized photo data to the device.

[0708] Input: Optimized photo data

[0709] Specific operation: Export the completed photo data in an appropriate format such as JSON and send it to the user's device.

[0710] Output: High-quality photo data sent to your device

[0711] Step 9: User reviews and shares optimized photo data

[0712] Input: High-quality photo data sent to the device

[0713] What it does: A user opens the app, taps on a photo preview to view it, and then uses the "Download" and "Share" buttons to post the photo to Instagram and Facebook.

[0714] Output: User's social media photos

[0715] (Application example 2)

[0716] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0717] Existing photo editing systems require users to manually change backgrounds and modify faces in photos they take, which requires a significant amount of time and expertise. Furthermore, they are unable to take user emotions into account when modifying images, resulting in often unsatisfactory results. Therefore, there is a need for a system that allows users to easily and quickly create professional-quality photos that match their emotions.

[0718] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photo data taken by a user with a terminal, means for automatically generating a background and applying it to the photo data, means for analyzing the user's facial expression using an emotion engine and recognizing the emotion, means for detecting the person's face and correcting makeup smudges and wrinkles based on the emotion, means for optimizing and saving the corrected photo, and means for transmitting the optimized photo data to the terminal. This enables users to easily create high-quality photos that reflect their emotions in a short amount of time, without having special skills or equipment.

[0719] A "terminal" is an electronic device with communication capabilities that a user owns, including smartphones and tablets.

[0720] "Photo data" refers to image information that a user takes with a device and stores in digital format.

[0721] "Means for automatically generating backgrounds" refers to technology that recognizes the background portion of photo data and generates a new background image using an algorithm.

[0722] An "emotion engine" is a software or hardware component that analyzes a user's facial expressions and recognizes their emotions.

[0723] "Methods for correcting smudged makeup and wrinkles" refers to technology that uses an algorithm to automatically correct smudged makeup and wrinkles on the face in a photo.

[0724] "Optimization means" refers to a technique that performs resolution and data compression on the edited photographs to appropriately adjust the data size while maintaining quality.

[0725] "Emotion-based correction method" refers to a technology that optimizes the correction pattern for facial makeup smudges and wrinkles based on the user's recognized emotional information.

[0726] "Background candidates" refer to multiple options for background images that can be applied to photo data.

[0727] "Facial feature points" refer to major points such as the eyes, nose, and mouth that are detected during facial analysis.

[0728] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[0729] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads the photo data to a server using a dedicated application. The device then sends the photo data to the server, which then moves on to the next processing step.

[0730] The server receives the uploaded photo data. The received photo data is analyzed using an emotion engine to recognize the user's facial expression and the emotion it conveys. The recognized emotion information is used in subsequent background generation and facial correction processes. Machine learning libraries such as TensorFlow are used to implement the emotion engine.

[0731] The server then detects the background of the photo data and generates multiple background candidates based on the emotional information analyzed by the emotion engine. These background candidates vary depending on the user's recognized emotion; for example, if the emotion is "happiness," multiple bright and open backgrounds are generated. The optimal background is selected from these and applied to the photo data to create a natural look.

[0732] Next, the server detects the user's face in the photo data and analyzes facial features (eyes, nose, mouth, etc.). Based on the emotion engine's analysis results, it corrects smudged makeup and wrinkles on the face. For example, if the user's emotion is "tired," corrections are made that focus particularly on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0733] Once the photo data has been corrected and background generation is complete, it is optimized by the server. Optimization involves adjusting the photo resolution and data format to provide high-quality photos while keeping the data size appropriately low. This optimization process uses the image processing library OpenCV.

[0734] Finally, the server sends the optimized, high-quality photo data to the user's device, where they can view it and download it through the app or share it on social media.

[0735] In a real-world example, when a user uploads a photo taken at home, the emotion engine recognizes the feeling of happiness, changes the background to a beach, fixes makeup smudges, and sends the high-quality photo to the user's smartphone. The user can then share the photo on social media such as Instagram.

[0736] An example prompt is:

[0737] "Based on pre-entered user photos, use a generative AI model to recognize emotions, and then optimally modify the photo background and face based on the emotions. Use TensorFlow for emotion recognition."

[0738] In this way, by combining the emotion engine, it is possible to achieve more personalized photo editing according to the user's emotions, allowing users to easily create high-quality photos in a short amount of time, even without specialized skills or equipment.

[0739] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0740] Step 1:

[0741] Users take their own photos using a device such as a smartphone. After taking the photo, the photo is uploaded to a server via a dedicated application. The input here is the photo data taken by the user, and the output is the uploaded photo data.

[0742] Step 2:

[0743] The server receives uploaded photo data. The received data is stored for processing by the emotion engine. The input here is the uploaded photo data, and the output is the photo data stored on the server.

[0744] Step 3:

[0745] The server uses an emotion engine to analyze the user's facial expressions in the photo data and recognize emotions. The input is the photo data, and the output is the user's emotional information. Generative AI models such as TensorFlow are used for emotion analysis.

[0746] Step 4:

[0747] The server recognizes the background of the photo data and generates multiple background candidates based on the emotion information. It then selects the most suitable background from among them. The input here is the user's emotion information and the photo data, and the output is the most suitable background.

[0748] Step 5:

[0749] The server applies the optimal background to the photo data, creating a natural composite. The input is the selected background and the photo data, and the output is the new photo data with the background applied.

[0750] Step 6:

[0751] The server detects the user's face in the photo data and analyzes facial feature points (eyes, nose, mouth, etc.). It then corrects makeup smudges and wrinkles based on the emotion. The input here is the photo data and facial feature points, and the output is the corrected face. Image processing libraries such as OpenCV are used to analyze and correct facial feature points.

[0752] Step 7:

[0753] The server optimizes the modified photo data. The input is the modified photo data, and the output is optimized high-quality photo data. This optimization includes data compression and resolution adjustment.

[0754] Step 8:

[0755] The server sends the optimized photo data to the user's device, where the user can view the data through the application, download it, or share it on social media. The input here is the optimized photo data, and the output is the photo data sent to the device.

[0756] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0757] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0758] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0759] [Third embodiment]

[0760] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0761] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0762] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0763] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0764] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0765] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0766] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0767] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0768] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0769] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0770] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0771] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0772] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[0773] 1. User photo taking and uploading

[0774] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0775] 2. Automatic background generation

[0776] The server receives the uploaded photo data. After receiving it, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates. The server selects the best one from these background candidates and applies it to the photo data.

[0777] For example, if a user takes a photo indoors, the server can automatically change it to a beach or park background.

[0778] 3. Face detection and correction

[0779] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful photo.

[0780] Specifically, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[0781] 4. Optimize and save

[0782] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0783] 5. Photo distribution

[0784] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[0785] For example, a photo taken at home can be automatically changed to a beach background, and any smudged makeup on the face can be corrected, resulting in a high-quality photo sent to the user's smartphone. After this, the user can share the photo on Instagram or other platforms.

[0786] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[0787] The processing flow will be explained below.

[0788] Step 1:

[0789] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[0790] Step 2:

[0791] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[0792] Step 3:

[0793] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[0794] Step 4:

[0795] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[0796] Step 5:

[0797] The server generates multiple background candidates for the detected background portion, and then selects the best one from the generated background candidates.

[0798] Step 6:

[0799] The server applies the selected background to the photo data, and then performs the processing to replace the background.

[0800] Step 7:

[0801] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[0802] Step 8:

[0803] The server detects smudges and wrinkles on the face, and applies an automatic correction algorithm to the detected areas.

[0804] Step 9:

[0805] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[0806] Step 10:

[0807] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[0808] Step 11:

[0809] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[0810] Example 1

[0811] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0812] Conventional image editing systems require advanced skills and specialized software to perform complex processes on photos taken by users, such as changing the background, smoothing out makeup, or correcting wrinkles. This makes it difficult for average users to easily create professional-quality photos. Furthermore, there is no function to automatically select the optimal background from multiple background candidates, making manual selection a time-consuming process.

[0813] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0814] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for identifying a background portion of the image data and selecting an optimal background from a plurality of automatically generated background candidates and applying it to the image data, means for detecting the user's face in the image data and analyzing facial feature points to correct smudged makeup and wrinkles, means for optimizing and saving the image data after correction and background generation is complete, and means for transmitting the optimized image data to the terminal. This enables users to easily obtain high-quality photos with automatically selected backgrounds and corrected smudged makeup and wrinkles, even without special skills or equipment.

[0815] "User" means an individual or end user who uses the System.

[0816] "Device" refers to a computing device such as a smartphone, tablet, or PC.

[0817] "Image data" refers to digital image files that users take with their devices and upload to the server.

[0818] A "server" is a remote computer system that receives, processes, stores, and distributes image data.

[0819] "Background" refers to the area of ​​the image data other than the user's face or other people.

[0820] "Background candidates" are multiple background image options generated by the system.

[0821] "Facial area" refers to the area in the image data that is occupied by the user's face.

[0822] "Feature points" refer to notable points on the face, such as the eyes, nose, and mouth.

[0823] "Makeup breakdown" refers to the phenomenon of makeup becoming smudged, thinned, or messy.

[0824] "Wrinkles" refer to the fine folds and lines that form in the skin of the face.

[0825] "Optimization" refers to the process of adjusting the resolution and format of image data to reduce data size while maintaining maximum quality.

[0826] "Storage" refers to the act of recording processed image data in digital storage.

[0827] "Transmit" refers to the act of transferring stored image data to a user's device via digital communication.

[0828] The present invention relates to a photo studio system that automatically generates a background for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face.

[0829] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to a server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0830] The server receives the uploaded photo data. In particular, the server uses a server cluster with powerful computing power as its hardware, and frameworks such as Python and TensorFlow as its software for executing AI algorithms. For the received photo data, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates.

[0831] For example, if a user takes a photo indoors, the server can automatically change the background to a beach or park. This process uses a generative AI model such as GAN (generative adversarial network) to automatically generate the background.

[0832] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). Specifically, it utilizes OpenCV, an open-source computer vision library. This makes it possible to detect makeup smudges and wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful face photo.

[0833] For example, if a user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone. After correction and background generation are complete, the photo data is optimized by the server. This optimization process adjusts the resolution and format of the photo and saves it at the optimal quality. Adobe Photoshop's API and other image processing libraries can be used as image processing software.

[0834] Finally, the server sends the optimized, high-quality photo data to the user's device. The user receives this data and can view it through the application. The completed photo can then be downloaded or shared on social media. For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges corrected can be sent to the user's smartphone. The user can then share the photo on Instagram and other platforms.

[0835] Examples of prompts include:

[0836] User: Upload a photo from home and automatically generate a beautiful beach background. Also, smooth out facial wrinkles and send us your high-quality photo.

[0837] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[0838] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0839] Step 1:

[0840] A user takes a photo on a device such as a smartphone. The user opens the camera app, composes the image, and presses the shutter button. As a result of this operation, the photo data is saved on the device.

[0841] Input: A photo taken by the user

[0842] Output: Photo data stored on the device

[0843] Step 2:

[0844] The device uses a dedicated application to upload the captured photo data to the server. The user launches the dedicated application, selects the photo, and presses the "Upload" button. The application then sends the photo data to the server via the network.

[0845] Input: Photo data stored on the device

[0846] Output: Photo data sent to the server

[0847] Step 3:

[0848] The server receives the uploaded photo data. The server receives the HTTP request and saves the sent photo file in local storage.

[0849] Input: Photo data sent from the device

[0850] Output: Photo data saved in local storage

[0851] Step 4:

[0852] The server runs an AI algorithm to identify the background of the photo data. The AI ​​algorithm uses segmentation models such as DeepLab or U-Net to distinguish between the background and foreground in the image. Specifically, it uses Python and TensorFlow.

[0853] Input: Photo data stored in local storage

[0854] Output: Image data with background identified

[0855] Step 5:

[0856] The server automatically generates multiple background candidates based on the identified background areas. The server generates new backgrounds using a generative adversarial network (GAN) or retrieves suitable background images from an existing background library.

[0857] Input: Image data with background identified

[0858] Output: Multiple background candidate images

[0859] Step 6:

[0860] The server selects the best background from the generated background candidates and applies it to the photo data. It uses an AI algorithm to select the background that best suits the background color and context. It then uses an image processing library such as the Photoshop API to change the background.

[0861] Input: Multiple background candidate images, original photo data

[0862] Output: Photo data with new background applied

[0863] Step 7:

[0864] The server uses the OpenCV library to analyze facial feature points to detect the user's face in the photo data, thereby identifying the position of the face and important points (eyes, nose, mouth, etc.).

[0865] Input: Photo data with new background applied

[0866] Output: Image data with face detected

[0867] Step 8:

[0868] The server automatically corrects smudged makeup and wrinkles, and uses an AI model to correct the detected areas, resulting in a smooth, beautiful facial photo.

[0869] Input: Image data with face detected

[0870] Output: Image data with makeup smudges and wrinkles corrected

[0871] Step 9:

[0872] The server optimizes the photo data after correction and background generation is complete, adjusting the resolution and format to provide high-quality photos.

[0873] Input: Image data with makeup smudges and wrinkles corrected

[0874] Output: Optimized image data

[0875] Step 10:

[0876] The server sends the optimized photo data to the device, which then transfers the photo data to the user's device via email or a dedicated application.

[0877] Input: Optimized image data

[0878] Output: Photo data sent to the user's device

[0879] Step 11:

[0880] Users receive high-quality photos, review them, open them in a dedicated application, and download or share them on social media.

[0881] Input: Photo data sent to the user's device

[0882] Output: User confirmed photo data, and downloaded or shared photo data

[0883] (Application example 1)

[0884] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0885] Conventional photo data and user image processing systems only allowed limited changes to backgrounds and facial image corrections, making it difficult to easily and highly accurately provide users with the scenes and aesthetics they desired. Furthermore, particularly in online shopping, they lacked the realistic simulation functionality required when users try on products. This resulted in the time and inconvenience involved when users selected products through a virtual try-on experience.

[0886] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0887] In this invention, the server includes means for receiving photo data taken by a user on a terminal, means for automatically generating a background and applying it to the photo data, means for detecting a person's face and correcting makeup smudges and wrinkles, and means for overlaying a product image on the user's photo to simulate trying on the product. This not only enables the user to obtain a high-quality image of the desired background and corrected face, but also enables the user to check the product in a more realistic manner through a virtual try-on simulation of the desired product.

[0888] "Device" means an electronic device used by a user to take and process photographic data. Examples include smartphones and tablets.

[0889] "Photo data" refers to image files taken using a device, including the user's face image and background.

[0890] The "means for automatically generating background" is a technology that identifies elements behind photographic data and generates or selects and applies any new background image.

[0891] "Means for detecting a person's face" refers to an algorithm for identifying the facial area of ​​a person in the photograph data, which can then identify the location of smudged makeup or wrinkles on the face.

[0892] "Means for correcting smudged makeup and wrinkles" refers to image processing technology for correcting smudged makeup and wrinkles on detected facial areas, thereby improving the appearance of facial images in photographs.

[0893] "Optimization and storage means" refers to the technology that adjusts the resolution and format of processed photo data and stores it on a server or cloud storage, thereby enabling the provision of high-quality photos.

[0894] "Means for simulating trying on a product by overlaying a product image on a user's photograph" refers to a technology that overlays an image of a selected product on a user's photograph, visually simulating the user wearing the product.

[0895] The "means for generating background candidates and selecting the most appropriate background" refers to an algorithm that automatically generates multiple background images and selects the most appropriate background from among them.

[0896] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[0897] System configuration

[0898] This system consists of a device used by the user and a server that processes and stores data. Users take photos with their smartphones, tablets, or other devices and upload the photo data to the server using a dedicated application. The system has the following main functions:

[0899] User photo taking and uploading

[0900] The user takes a photo of themselves using their device. After taking the photo, they upload it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0901] Automatic background generation

[0902] When the server receives photo data, it uses a generative AI model to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates, selects the most suitable one from them, and applies it to the photo data. For example, a photo taken by a user indoors can be automatically changed to a beach or park background.

[0903] Facial detection and correction

[0904] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server then automatically corrects the detected areas, resulting in a smooth, beautiful photo. For example, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[0905] Product image try-on simulation

[0906] The image of the product selected by the user is overlaid on the photo to simulate trying on the item. This allows users to have a virtual try-on experience without visiting a store. The product image is naturally composited onto the user's photo, resulting in a more realistic try-on simulation.

[0907] Optimize and save

[0908] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0909] Photo distribution

[0910] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[0911] For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges fixed will be sent to the user's smartphone. After this, the user can share the photo on Instagram and other platforms.

[0912] Hardware and software used

[0913] The server is equipped with a high-performance processor (e.g., Intel Xeon processor) and a large amount of memory (e.g., 32GB or more) to process data quickly. Software such as Python, OpenCV, TensorFlow, or Pytorch is used to efficiently perform processes such as face detection, background identification, and makeup correction.

[0914] An example prompt is:

[0915] "Please add a park background to a photo I took at home and fix any wrinkles."

[0916] "Fix the makeup smudges in this photo and add a boutique as a new background."

[0917] The above is a specific embodiment of this photo studio system, which allows anyone to easily create professional-quality photographs without having special skills or equipment.

[0918] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0919] Step 1:

[0920] Users take photos and upload them to the server through a dedicated application.

[0921] Specific operation: The user takes a photo of themselves using the camera app on their smartphone. The photo is then sent to the server by opening a dedicated application and pressing the upload button.

[0922] Input: Photo data taken by the user.

[0923] Output: Photo data received by the server.

[0924] Step 2:

[0925] The server processes the received photo data and identifies the background portion.

[0926] How it works: The server inputs the received photo data into a deep learning model (e.g., TensorFlow or Pytorch) to identify the background. The AI ​​model identifies the background area of ​​the image.

[0927] Input: Photo data received by the server.

[0928] Output: Photo data with background areas identified.

[0929] Step 3:

[0930] The server generates multiple new background candidates based on the identified background portions.

[0931] Specific operation: The server generates or selects multiple background images and lists them as new background candidates. For example, background images such as beaches, parks, and cafes are generated.

[0932] Input: Identified background parts.

[0933] Output: Multiple generated background candidates.

[0934] Step 4:

[0935] The server selects the most suitable background and applies it to the photo data.

[0936] Specific operation: The server selects the most suitable background from the generated background candidates and combines it with the user's photo data. The background selection is performed using an algorithm to evaluate the suitability.

[0937] Input: Multiple generated background candidates.

[0938] Output: Photo data with background applied.

[0939] Step 5:

[0940] The server detects the user's face in the photo data and corrects smudged makeup and wrinkles.

[0941] Specific operation: The server uses a face detection algorithm (e.g., OpenCV) to detect facial features (eyes, nose, mouth, etc.) in the photo data, then corrects smudged makeup and wrinkles.

[0942] Input: Photo data with background applied.

[0943] Output: Photo data with makeup smudges and wrinkles corrected.

[0944] Step 6:

[0945] The server overlays product images onto the user's photo to simulate trying them on.

[0946] How it works: The server retrieves the product image selected by the user and naturally combines it with the user's photo, creating an image that looks as if the user is actually trying on the product.

[0947] Input: Photo data with makeup smudges and wrinkles corrected, and product images selected by the user.

[0948] Output: Photo data with product images overlaid.

[0949] Step 7:

[0950] The server optimizes and stores the photo data after correction, background generation, and product composition are completed.

[0951] Specific operation: The server adjusts the resolution and format of the photo data to optimize the data size, and stores high-quality photo data.

[0952] Input: Photo data with product images overlaid.

[0953] Output: Optimized, high-quality photo data.

[0954] Step 8:

[0955] The server sends optimized, high-quality photo data to the user's device.

[0956] How it works: The server sends the optimized photo data to the user's device via a dedicated application, and the user can open the application to view the edited, high-quality photo.

[0957] Input: Optimized, high-quality photo data.

[0958] Output: Photo data delivered to the user's device.

[0959] This allows users to easily create photos with high-quality backgrounds, photos with makeup smudges and wrinkles corrected, and even perform virtual try-on simulations.

[0960] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0961] The present invention combines an emotion engine with a photo studio system that automatically generates backgrounds for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention, with specific examples.

[0962] 1. User photo taking and uploading

[0963] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[0964] 2. Emotional Recognition

[0965] When the server receives the uploaded photo data, the emotion engine analyzes the user's face in the photo. The emotion engine recognizes the emotion based on the user's facial expression. This recognized emotion information is used in the subsequent background generation and correction process.

[0966] 3. Automatic background generation

[0967] The server detects the background of the photo data. The emotion engine generates multiple background candidates based on the analyzed emotion information. These background candidates vary depending on the user's recognized emotion. For example, if the user's emotion is "happy," a bright and open background is generated.

[0968] The server selects the best background from the generated candidates and applies it to the photo data. When applying the background, it performs adjustments to ensure a natural blend.

[0969] 4. Face detection and correction

[0970] The server detects the user's face in the photo data and uses an algorithm to analyze facial features (eyes, nose, mouth, etc.). Based on the analysis results of the emotion engine, smudged makeup and wrinkles on the face are corrected. For example, if the user's emotion is "tired," corrections are made, focusing on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0971] 5. Optimize and save

[0972] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[0973] 6. Photo distribution

[0974] Finally, the server sends the optimized, high-quality photo data to the user's device, where it can be viewed through the app, and the finished photo can be downloaded or shared on social media.

[0975] For example, the app recognizes happiness in photos taken at home, automatically changes the background to a beach, and fixes smudged makeup on the face, resulting in a high-quality photo sent to the user's smartphone. The user can then share the photo on Instagram or other platforms.

[0976] In this way, the combination of the emotion engine enables more personalized photo editing based on the user's emotions, allowing users to easily create professional-quality, individualized photos without the need for special skills or equipment.

[0977] The processing flow will be explained below.

[0978] Step 1:

[0979] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[0980] Step 2:

[0981] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[0982] Step 3:

[0983] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[0984] Step 4:

[0985] The server uses an emotion engine to analyze the user's face in the photo. The emotion engine recognizes the user's emotion based on their facial expression. For example, the emotion engine analyzes the user's face to detect emotions such as "happiness" or "sadness."

[0986] Step 5:

[0987] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[0988] Step 6:

[0989] The server generates multiple background candidates based on the emotion information obtained from the emotion engine. For example, if the user's emotion is "happy," a bright and open background will be suggested.

[0990] Step 7:

[0991] The server selects the most suitable background from the generated background candidates. The server applies the selected background to the photo data. When applying the background, adjustments are made to ensure a natural blend.

[0992] Step 8:

[0993] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[0994] Step 9:

[0995] The server detects smudged makeup and wrinkles on the face. Based on emotion information, it focuses on areas that require particular correction. For example, if the emotion "fatigue" is detected, it focuses on correcting the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[0996] Step 10:

[0997] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[0998] Step 11:

[0999] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[1000] Step 12:

[1001] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[1002] Example 2

[1003] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1004] Editing photos taken by users with professional quality requires advanced skills and specialized knowledge. It is particularly difficult for average users to change backgrounds, modify facial features, or perform personalized editing based on the user's emotions. The present invention aims to solve the above-mentioned problems by providing a system that allows users to easily perform high-quality photo editing.

[1005] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1006] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for analyzing the user's facial expression contained in the received image data and recognizing emotions, means for automatically generating a background based on the emotion information and applying it to the image data, means for detecting a person's face from the image data and analyzing facial features to correct makeup smudges and wrinkles, means for optimizing and saving the corrected image data, and means for transmitting the optimized image data to the terminal. This enables users to easily create photos that combine professional quality and individual response, even without special skills or equipment.

[1007] A "terminal" is an electronic device that a user uses to take pictures and receive processed image data.

[1008] A "server" is a central computer system that receives and processes image data sent by users.

[1009] "Image data" refers to photographic data taken by a user using a device.

[1010] An "emotion engine" is an algorithm and software that analyzes the user's facial expressions contained in image data and recognizes emotions.

[1011] The "automatic background generation means" is a means for automatically generating a background image based on the user's emotional information and applying it to image data.

[1012] The "face part detection means" refers to an algorithm and software for detecting and analyzing a person's face part from image data.

[1013] The "facial feature point analysis means" is a means for analyzing the position and shape of each part of the face (eyes, nose, mouth, etc.).

[1014] The "means for correcting makeup smudges and wrinkles" refers to algorithms and software for automatically correcting makeup smudges and wrinkles on detected facial areas.

[1015] The "optimization means" is a means for adjusting the resolution and format of the corrected image data and saving it with optimal quality.

[1016] "Emotional information" refers to the emotional data recognized by the emotion engine after analyzing the user's facial expressions.

[1017] System Overview

[1018] This system uses an emotion engine to automatically generate backgrounds for image data taken by a user on a device, and corrects makeup smudges and wrinkles on the face. This system provides high-quality photo editing personalized according to the user's emotions.

[1019] Hardware and Software Configuration

[1020] Terminal

[1021] Hardware: Smartphones, tablets, etc.

[1022] Software: Dedicated application

[1023] server

[1024] Hardware: high-performance computers, cloud servers

[1025] Software: Emotion engine, image processing algorithms, generative AI models

[1026] Specific processing explanation

[1027] User Actions

[1028] Users take a photo of their face using a device such as a smartphone. After taking the photo, they upload it to the server using a dedicated application. For example, when a user opens the app and presses the "upload photo" button, the device sends the photo data to the server.

[1029] Emotion recognition

[1030] When the server receives the photo data, the emotion engine analyzes the user's face in the photo. The emotion engine detects facial features (eyes, nose, mouth, eyebrows, etc.) and recognizes emotions from facial expressions. The recognized emotion information is generated as emotion labels such as "happiness," "sadness," and "surprise," and is used in the background generation and face correction processes.

[1031] Automatic background generation

[1032] The server generates multiple background candidates based on the emotion information from the emotion engine. Using a generative AI model, for example, in the case of "happiness," it generates a bright, open background image such as a beach or park. The server selects the most suitable background from the generated candidates and applies it to the photo data. When compositing the photo, color correction and border smoothing processes are performed.

[1033] Facial detection and correction

[1034] The server detects the user's face in the photo data and analyzes facial features. It then automatically corrects smudged makeup and wrinkles in the detected facial areas. In particular, if the "fatigue" emotion is recognized, corrections are made to make the area around the eyes clearer and the cheeks brighter.

[1035] Optimize and save

[1036] Once the photo data has been retouched, it is sent to a server where it is optimized for resolution and format, and then stored in high quality in cloud storage or a database.

[1037] Photo distribution

[1038] Finally, the server sends the optimized, high-quality photo data to the user's device, where the user can view the edited photo through a dedicated application. The finished photo can then be downloaded or shared on social media.

[1039] Examples and prompts

[1040] Examples:

[1041] For example, if you upload a photo taken at home, the system will recognize your sense of happiness, automatically change the background to a beach, fix any makeup smudges, and send the high-quality photo to your smartphone. Users can then share the photo on Instagram and other platforms.

[1042] Example prompt:

[1043] "A user takes a photo of themselves and uploads it to the server. The server automatically changes the background of the photo to a beach and fixes any makeup that has been smudged on the user's face."

[1044] In this way, the system can automatically perform high-level photo editing based on the user's emotions, making it possible for users without special skills or equipment to easily create photos that combine professional quality with individual responsiveness.

[1045] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1046] Step 1: User takes and uploads a photo

[1047] Input: Photo data taken by the user using the smartphone camera app

[1048] Specific operation: The user launches the camera app on their smartphone, takes a selfie, and then opens the dedicated application and presses the "Upload photo" button.

[1049] Output: The device sends the photo data to the server.

[1050] Step 2: The server receives the photo data

[1051] Input: Photo data sent from the device

[1052] Specific operation: The server receives the HTTP request and stores the photo data in an internal database.

[1053] Output: Photo data stored on the server

[1054] Step 3: The emotion engine analyzes the face and recognizes the emotion

[1055] Input: Photo data stored on the server

[1056] Specific operation: The server starts the emotion engine and analyzes the face in the photo. It detects facial features (eyes, nose, mouth, eyebrows, etc.) and infers emotions from facial expressions.

[1057] Output: Generate emotion information (e.g., emotion labels such as "happiness," "sadness," and "surprise").

[1058] Step 4: The server automatically generates the background

[1059] Input: Emotional information and photo data

[1060] How it works: Based on the emotion information from the emotion engine, the generative AI model is used to generate multiple background candidates. For example, for "happiness," background images of a beach or park are generated. Then, the most suitable background is selected.

[1061] Output: Optimal background image

[1062] Step 5: The server applies the background to the photo data

[1063] Input: Ideal background image and photo data

[1064] How it works: The server detects the background of the photo data and applies the generated background image. It also performs color correction and border smoothing to achieve a natural composite.

[1065] Output: Photo data with background applied

[1066] Step 6: The server detects the face and corrects any smudges or wrinkles.

[1067] Input: Photo data with background applied

[1068] What it does: The server uses a face detection algorithm to identify faces in the photo. It analyzes facial features and corrects smudged makeup and wrinkles. For example, if it detects a "tired" emotion, it brightens the area around the eyes and cheeks.

[1069] Output: Photo data with face correction

[1070] Step 7: The server optimizes and stores the photo data

[1071] Input: Photo data with face correction

[1072] What it does: The server optimizes the resolution and adjusts the format, then stores it in cloud storage or a database.

[1073] Output: Optimized photo data

[1074] Step 8: The server sends the optimized photo data to the device.

[1075] Input: Optimized photo data

[1076] Specific operation: Export the completed photo data in an appropriate format such as JSON and send it to the user's device.

[1077] Output: High-quality photo data sent to your device

[1078] Step 9: User reviews and shares optimized photo data

[1079] Input: High-quality photo data sent to the device

[1080] What it does: A user opens the app, taps on a photo preview to view it, and then uses the "Download" and "Share" buttons to post the photo to Instagram and Facebook.

[1081] Output: User's social media photos

[1082] (Application example 2)

[1083] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1084] Existing photo editing systems require users to manually change backgrounds and modify faces in photos they take, which requires a significant amount of time and expertise. Furthermore, they are unable to take user emotions into account when modifying images, resulting in often unsatisfactory results. Therefore, there is a need for a system that allows users to easily and quickly create professional-quality photos that match their emotions.

[1085] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photo data taken by a user with a terminal, means for automatically generating a background and applying it to the photo data, means for analyzing the user's facial expression using an emotion engine and recognizing the emotion, means for detecting the person's face and correcting makeup smudges and wrinkles based on the emotion, means for optimizing and saving the corrected photo, and means for transmitting the optimized photo data to the terminal. This enables users to easily create high-quality photos that reflect their emotions in a short amount of time, without having special skills or equipment.

[1086] A "terminal" is an electronic device with communication capabilities that a user owns, including smartphones and tablets.

[1087] "Photo data" refers to image information that a user takes with a device and stores in digital format.

[1088] "Means for automatically generating backgrounds" refers to technology that recognizes the background portion of photo data and generates a new background image using an algorithm.

[1089] An "emotion engine" is a software or hardware component that analyzes a user's facial expressions and recognizes their emotions.

[1090] "Methods for correcting smudged makeup and wrinkles" refers to technology that uses an algorithm to automatically correct smudged makeup and wrinkles on the face in a photo.

[1091] "Optimization means" refers to a technique that performs resolution and data compression on the edited photographs to appropriately adjust the data size while maintaining quality.

[1092] "Emotion-based correction method" refers to a technology that optimizes the correction pattern for facial makeup smudges and wrinkles based on the user's recognized emotional information.

[1093] "Background candidates" refer to multiple options for background images that can be applied to photo data.

[1094] "Facial feature points" refer to major points such as the eyes, nose, and mouth that are detected during facial analysis.

[1095] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[1096] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads the photo data to a server using a dedicated application. The device then sends the photo data to the server, which then moves on to the next processing step.

[1097] The server receives the uploaded photo data. The received photo data is analyzed using an emotion engine to recognize the user's facial expression and the emotion it conveys. The recognized emotion information is used in subsequent background generation and facial correction processes. Machine learning libraries such as TensorFlow are used to implement the emotion engine.

[1098] The server then detects the background of the photo data and generates multiple background candidates based on the emotional information analyzed by the emotion engine. These background candidates vary depending on the user's recognized emotion; for example, if the emotion is "happiness," multiple bright and open backgrounds are generated. The optimal background is selected from these and applied to the photo data to create a natural look.

[1099] Next, the server detects the user's face in the photo data and analyzes facial features (eyes, nose, mouth, etc.). Based on the emotion engine's analysis results, it corrects smudged makeup and wrinkles on the face. For example, if the user's emotion is "tired," corrections are made that focus particularly on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[1100] Once the photo data has been corrected and background generation is complete, it is optimized by the server. Optimization involves adjusting the photo resolution and data format to provide high-quality photos while keeping the data size appropriately low. This optimization process uses the image processing library OpenCV.

[1101] Finally, the server sends the optimized, high-quality photo data to the user's device, where they can view it and download it through the app or share it on social media.

[1102] In a real-world example, when a user uploads a photo taken at home, the emotion engine recognizes the feeling of happiness, changes the background to a beach, fixes makeup smudges, and sends the high-quality photo to the user's smartphone. The user can then share the photo on social media such as Instagram.

[1103] An example prompt is:

[1104] "Based on pre-entered user photos, use a generative AI model to recognize emotions, and then optimally modify the photo background and face based on the emotions. Use TensorFlow for emotion recognition."

[1105] In this way, by combining the emotion engine, it is possible to achieve more personalized photo editing according to the user's emotions, allowing users to easily create high-quality photos in a short amount of time, even without specialized skills or equipment.

[1106] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1107] Step 1:

[1108] Users take their own photos using a device such as a smartphone. After taking the photo, the photo is uploaded to a server via a dedicated application. The input here is the photo data taken by the user, and the output is the uploaded photo data.

[1109] Step 2:

[1110] The server receives uploaded photo data. The received data is stored for processing by the emotion engine. The input here is the uploaded photo data, and the output is the photo data stored on the server.

[1111] Step 3:

[1112] The server uses an emotion engine to analyze the user's facial expressions in the photo data and recognize emotions. The input is the photo data, and the output is the user's emotional information. Generative AI models such as TensorFlow are used for emotion analysis.

[1113] Step 4:

[1114] The server recognizes the background of the photo data and generates multiple background candidates based on the emotion information. It then selects the most suitable background from among them. The input here is the user's emotion information and the photo data, and the output is the most suitable background.

[1115] Step 5:

[1116] The server applies the optimal background to the photo data, creating a natural composite. The input is the selected background and the photo data, and the output is the new photo data with the background applied.

[1117] Step 6:

[1118] The server detects the user's face in the photo data and analyzes facial feature points (eyes, nose, mouth, etc.). It then corrects makeup smudges and wrinkles based on the emotion. The input here is the photo data and facial feature points, and the output is the corrected face. Image processing libraries such as OpenCV are used to analyze and correct facial feature points.

[1119] Step 7:

[1120] The server optimizes the modified photo data. The input is the modified photo data, and the output is optimized high-quality photo data. This optimization includes data compression and resolution adjustment.

[1121] Step 8:

[1122] The server sends the optimized photo data to the user's device, where the user can view the data through the application, download it, or share it on social media. The input here is the optimized photo data, and the output is the photo data sent to the device.

[1123] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1124] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1125] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1126] [Fourth embodiment]

[1127] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1128] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1129] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1130] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1131] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1133] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1134] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1135] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1136] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1138] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1139] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1140] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[1141] 1. User photo taking and uploading

[1142] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[1143] 2. Automatic background generation

[1144] The server receives the uploaded photo data. After receiving it, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates. The server selects the best one from these background candidates and applies it to the photo data.

[1145] For example, if a user takes a photo indoors, the server can automatically change it to a beach or park background.

[1146] 3. Face detection and correction

[1147] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful photo.

[1148] Specifically, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[1149] 4. Optimize and save

[1150] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[1151] 5. Photo distribution

[1152] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[1153] For example, a photo taken at home can be automatically changed to a beach background, and any smudged makeup on the face can be corrected, resulting in a high-quality photo sent to the user's smartphone. After this, the user can share the photo on Instagram or other platforms.

[1154] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[1155] The processing flow will be explained below.

[1156] Step 1:

[1157] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[1158] Step 2:

[1159] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[1160] Step 3:

[1161] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[1162] Step 4:

[1163] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[1164] Step 5:

[1165] The server generates multiple background candidates for the detected background portion, and then selects the best one from the generated background candidates.

[1166] Step 6:

[1167] The server applies the selected background to the photo data, and then performs the processing to replace the background.

[1168] Step 7:

[1169] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[1170] Step 8:

[1171] The server detects smudges and wrinkles on the face, and applies an automatic correction algorithm to the detected areas.

[1172] Step 9:

[1173] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[1174] Step 10:

[1175] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[1176] Step 11:

[1177] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[1178] Example 1

[1179] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1180] Conventional image editing systems require advanced skills and specialized software to perform complex processes on photos taken by users, such as changing the background, smoothing out makeup, or correcting wrinkles. This makes it difficult for average users to easily create professional-quality photos. Furthermore, there is no function to automatically select the optimal background from multiple background candidates, making manual selection a time-consuming process.

[1181] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1182] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for identifying a background portion of the image data and selecting an optimal background from a plurality of automatically generated background candidates and applying it to the image data, means for detecting the user's face in the image data and analyzing facial feature points to correct smudged makeup and wrinkles, means for optimizing and saving the image data after correction and background generation is complete, and means for transmitting the optimized image data to the terminal. This enables users to easily obtain high-quality photos with automatically selected backgrounds and corrected smudged makeup and wrinkles, even without special skills or equipment.

[1183] "User" means an individual or end user who uses the System.

[1184] "Device" refers to a computing device such as a smartphone, tablet, or PC.

[1185] "Image data" refers to digital image files that users take with their devices and upload to the server.

[1186] A "server" is a remote computer system that receives, processes, stores, and distributes image data.

[1187] "Background" refers to the area of ​​the image data other than the user's face or other people.

[1188] "Background candidates" are multiple background image options generated by the system.

[1189] "Facial area" refers to the area in the image data that is occupied by the user's face.

[1190] "Feature points" refer to notable points on the face, such as the eyes, nose, and mouth.

[1191] "Makeup breakdown" refers to the phenomenon of makeup becoming smudged, thinned, or messy.

[1192] "Wrinkles" refer to the fine folds and lines that form in the skin of the face.

[1193] "Optimization" refers to the process of adjusting the resolution and format of image data to reduce data size while maintaining maximum quality.

[1194] "Storage" refers to the act of recording processed image data in digital storage.

[1195] "Transmit" refers to the act of transferring stored image data to a user's device via digital communication.

[1196] The present invention relates to a photo studio system that automatically generates a background for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face.

[1197] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to a server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[1198] The server receives the uploaded photo data. In particular, the server uses a server cluster with powerful computing power as its hardware, and frameworks such as Python and TensorFlow as its software for executing AI algorithms. For the received photo data, the server uses an AI algorithm to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates.

[1199] For example, if a user takes a photo indoors, the server can automatically change the background to a beach or park. This process uses a generative AI model such as GAN (generative adversarial network) to automatically generate the background.

[1200] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). Specifically, it utilizes OpenCV, an open-source computer vision library. This makes it possible to detect makeup smudges and wrinkles. The server automatically corrects the detected areas, resulting in a smooth, beautiful face photo.

[1201] For example, if a user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone. After correction and background generation are complete, the photo data is optimized by the server. This optimization process adjusts the resolution and format of the photo and saves it at the optimal quality. Adobe Photoshop's API and other image processing libraries can be used as image processing software.

[1202] Finally, the server sends the optimized, high-quality photo data to the user's device. The user receives this data and can view it through the application. The completed photo can then be downloaded or shared on social media. For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges corrected can be sent to the user's smartphone. The user can then share the photo on Instagram and other platforms.

[1203] Examples of prompts include:

[1204] User: Upload a photo from home and automatically generate a beautiful beach background. Also, smooth out facial wrinkles and send us your high-quality photo.

[1205] In this way, the system of the present invention allows anyone to easily create professional quality photographs, even if the user does not have special skills or equipment.

[1206] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1207] Step 1:

[1208] A user takes a photo on a device such as a smartphone. The user opens the camera app, composes the image, and presses the shutter button. As a result of this operation, the photo data is saved on the device.

[1209] Input: A photo taken by the user

[1210] Output: Photo data stored on the device

[1211] Step 2:

[1212] The device uses a dedicated application to upload the captured photo data to the server. The user launches the dedicated application, selects the photo, and presses the "Upload" button. The application then sends the photo data to the server via the network.

[1213] Input: Photo data stored on the device

[1214] Output: Photo data sent to the server

[1215] Step 3:

[1216] The server receives the uploaded photo data. The server receives the HTTP request and saves the sent photo file in local storage.

[1217] Input: Photo data sent from the device

[1218] Output: Photo data saved in local storage

[1219] Step 4:

[1220] The server runs an AI algorithm to identify the background of the photo data. The AI ​​algorithm uses segmentation models such as DeepLab or U-Net to distinguish between the background and foreground in the image. Specifically, it uses Python and TensorFlow.

[1221] Input: Photo data stored in local storage

[1222] Output: Image data with background identified

[1223] Step 5:

[1224] The server automatically generates multiple background candidates based on the identified background areas. The server generates new backgrounds using a generative adversarial network (GAN) or retrieves suitable background images from an existing background library.

[1225] Input: Image data with background identified

[1226] Output: Multiple background candidate images

[1227] Step 6:

[1228] The server selects the best background from the generated background candidates and applies it to the photo data. It uses an AI algorithm to select the background that best suits the background color and context. It then uses an image processing library such as the Photoshop API to change the background.

[1229] Input: Multiple background candidate images, original photo data

[1230] Output: Photo data with new background applied

[1231] Step 7:

[1232] The server uses the OpenCV library to analyze facial feature points to detect the user's face in the photo data, thereby identifying the position of the face and important points (eyes, nose, mouth, etc.).

[1233] Input: Photo data with new background applied

[1234] Output: Image data with face detected

[1235] Step 8:

[1236] The server automatically corrects smudged makeup and wrinkles, and uses an AI model to correct the detected areas, resulting in a smooth, beautiful facial photo.

[1237] Input: Image data with face detected

[1238] Output: Image data with makeup smudges and wrinkles corrected

[1239] Step 9:

[1240] The server optimizes the photo data after correction and background generation is complete, adjusting the resolution and format to provide high-quality photos.

[1241] Input: Image data with makeup smudges and wrinkles corrected

[1242] Output: Optimized image data

[1243] Step 10:

[1244] The server sends the optimized photo data to the device, which then transfers the photo data to the user's device via email or a dedicated application.

[1245] Input: Optimized image data

[1246] Output: Photo data sent to the user's device

[1247] Step 11:

[1248] Users receive high-quality photos, review them, open them in a dedicated application, and download or share them on social media.

[1249] Input: Photo data sent to the user's device

[1250] Output: User confirmed photo data, and downloaded or shared photo data

[1251] (Application example 1)

[1252] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1253] Conventional photo data and user image processing systems only allowed limited changes to backgrounds and facial image corrections, making it difficult to easily and highly accurately provide users with the scenes and aesthetics they desired. Furthermore, particularly in online shopping, they lacked the realistic simulation functionality required when users try on products. This resulted in the time and inconvenience involved when users selected products through a virtual try-on experience.

[1254] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1255] In this invention, the server includes means for receiving photo data taken by a user on a terminal, means for automatically generating a background and applying it to the photo data, means for detecting a person's face and correcting makeup smudges and wrinkles, and means for overlaying a product image on the user's photo to simulate trying on the product. This not only enables the user to obtain a high-quality image of the desired background and corrected face, but also enables the user to check the product in a more realistic manner through a virtual try-on simulation of the desired product.

[1256] "Device" means an electronic device used by a user to take and process photographic data. Examples include smartphones and tablets.

[1257] "Photo data" refers to image files taken using a device, including the user's face image and background.

[1258] The "means for automatically generating background" is a technology that identifies elements behind photographic data and generates or selects and applies any new background image.

[1259] "Means for detecting a person's face" refers to an algorithm for identifying the facial area of ​​a person in the photograph data, which can then identify the location of smudged makeup or wrinkles on the face.

[1260] "Means for correcting smudged makeup and wrinkles" refers to image processing technology for correcting smudged makeup and wrinkles on detected facial areas, thereby improving the appearance of facial images in photographs.

[1261] "Optimization and storage means" refers to the technology that adjusts the resolution and format of processed photo data and stores it on a server or cloud storage, thereby enabling the provision of high-quality photos.

[1262] "Means for simulating trying on a product by overlaying a product image on a user's photograph" refers to a technology that overlays an image of a selected product on a user's photograph, visually simulating the user wearing the product.

[1263] The "means for generating background candidates and selecting the most appropriate background" refers to an algorithm that automatically generates multiple background images and selects the most appropriate background from among them.

[1264] The present invention relates to a photo studio system that automatically generates a background for photograph data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention with specific examples.

[1265] System configuration

[1266] This system consists of a device used by the user and a server that processes and stores data. Users take photos with their smartphones, tablets, or other devices and upload the photo data to the server using a dedicated application. The system has the following main functions:

[1267] User photo taking and uploading

[1268] The user takes a photo of themselves using their device. After taking the photo, they upload it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[1269] Automatic background generation

[1270] When the server receives photo data, it uses a generative AI model to identify the background of the photo. Based on this identified background, the server automatically generates multiple new background candidates, selects the most suitable one from them, and applies it to the photo data. For example, a photo taken by a user indoors can be automatically changed to a beach or park background.

[1271] Facial detection and correction

[1272] Next, the server detects the user's face in the photo data. To do this, it uses an algorithm that analyzes facial features (eyes, nose, mouth, etc.). This makes it possible to detect smudges of makeup or wrinkles. The server then automatically corrects the detected areas, resulting in a smooth, beautiful photo. For example, if the user has fine wrinkles on their face, the AI ​​will automatically smooth them out and even out their skin tone.

[1273] Product image try-on simulation

[1274] The image of the product selected by the user is overlaid on the photo to simulate trying on the item. This allows users to have a virtual try-on experience without visiting a store. The product image is naturally composited onto the user's photo, resulting in a more realistic try-on simulation.

[1275] Optimize and save

[1276] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[1277] Photo distribution

[1278] Finally, the server sends the optimized, high-quality photo data to the device, where the user can view it through the app and download the finished photo or share it on social media.

[1279] For example, a photo taken at home can be automatically changed to a beach background, and high-quality photos with makeup smudges fixed will be sent to the user's smartphone. After this, the user can share the photo on Instagram and other platforms.

[1280] Hardware and software used

[1281] The server is equipped with a high-performance processor (e.g., Intel Xeon processor) and a large amount of memory (e.g., 32GB or more) to process data quickly. Software such as Python, OpenCV, TensorFlow, or Pytorch is used to efficiently perform processes such as face detection, background identification, and makeup correction.

[1282] An example prompt is:

[1283] "Please add a park background to a photo I took at home and fix any wrinkles."

[1284] "Fix the makeup smudges in this photo and add a boutique as a new background."

[1285] The above is a specific embodiment of this photo studio system, which allows anyone to easily create professional-quality photographs without having special skills or equipment.

[1286] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1287] Step 1:

[1288] Users take photos and upload them to the server through a dedicated application.

[1289] Specific operation: The user takes a photo of themselves using the camera app on their smartphone. The photo is then sent to the server by opening a dedicated application and pressing the upload button.

[1290] Input: Photo data taken by the user.

[1291] Output: Photo data received by the server.

[1292] Step 2:

[1293] The server processes the received photo data and identifies the background portion.

[1294] How it works: The server inputs the received photo data into a deep learning model (e.g., TensorFlow or Pytorch) to identify the background. The AI ​​model identifies the background area of ​​the image.

[1295] Input: Photo data received by the server.

[1296] Output: Photo data with background areas identified.

[1297] Step 3:

[1298] The server generates multiple new background candidates based on the identified background portions.

[1299] Specific operation: The server generates or selects multiple background images and lists them as new background candidates. For example, background images such as beaches, parks, and cafes are generated.

[1300] Input: Identified background parts.

[1301] Output: Multiple generated background candidates.

[1302] Step 4:

[1303] The server selects the most suitable background and applies it to the photo data.

[1304] Specific operation: The server selects the most suitable background from the generated background candidates and combines it with the user's photo data. The background selection is performed using an algorithm to evaluate the suitability.

[1305] Input: Multiple generated background candidates.

[1306] Output: Photo data with background applied.

[1307] Step 5:

[1308] The server detects the user's face in the photo data and corrects smudged makeup and wrinkles.

[1309] Specific operation: The server uses a face detection algorithm (e.g., OpenCV) to detect facial features (eyes, nose, mouth, etc.) in the photo data, then corrects smudged makeup and wrinkles.

[1310] Input: Photo data with background applied.

[1311] Output: Photo data with makeup smudges and wrinkles corrected.

[1312] Step 6:

[1313] The server overlays product images onto the user's photo to simulate trying them on.

[1314] How it works: The server retrieves the product image selected by the user and naturally combines it with the user's photo, creating an image that looks as if the user is actually trying on the product.

[1315] Input: Photo data with makeup smudges and wrinkles corrected, and product images selected by the user.

[1316] Output: Photo data with product images overlaid.

[1317] Step 7:

[1318] The server optimizes and stores the photo data after correction, background generation, and product composition are completed.

[1319] Specific operation: The server adjusts the resolution and format of the photo data to optimize the data size, and stores high-quality photo data.

[1320] Input: Photo data with product images overlaid.

[1321] Output: Optimized, high-quality photo data.

[1322] Step 8:

[1323] The server sends optimized, high-quality photo data to the user's device.

[1324] How it works: The server sends the optimized photo data to the user's device via a dedicated application, and the user can open the application to view the edited, high-quality photo.

[1325] Input: Optimized, high-quality photo data.

[1326] Output: Photo data delivered to the user's device.

[1327] This allows users to easily create photos with high-quality backgrounds, photos with makeup smudges and wrinkles corrected, and even perform virtual try-on simulations.

[1328] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1329] The present invention combines an emotion engine with a photo studio system that automatically generates backgrounds for photo data taken by a user on a terminal and corrects makeup smudges and wrinkles on the face. The following describes an embodiment of the present invention, with specific examples.

[1330] 1. User photo taking and uploading

[1331] The user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads it to the server using a dedicated application. The device then sends the photo data to the server, which then proceeds to the next step.

[1332] 2. Emotional Recognition

[1333] When the server receives the uploaded photo data, the emotion engine analyzes the user's face in the photo. The emotion engine recognizes the emotion based on the user's facial expression. This recognized emotion information is used in the subsequent background generation and correction process.

[1334] 3. Automatic background generation

[1335] The server detects the background of the photo data. The emotion engine generates multiple background candidates based on the analyzed emotion information. These background candidates vary depending on the user's recognized emotion. For example, if the user's emotion is "happy," a bright and open background is generated.

[1336] The server selects the best background from the generated candidates and applies it to the photo data. When applying the background, it performs adjustments to ensure a natural blend.

[1337] 4. Face detection and correction

[1338] The server detects the user's face in the photo data and uses an algorithm to analyze facial features (eyes, nose, mouth, etc.). Based on the analysis results of the emotion engine, smudged makeup and wrinkles on the face are corrected. For example, if the user's emotion is "tired," corrections are made, focusing on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[1339] 5. Optimize and save

[1340] Once the photo data has been corrected and backgrounds generated, it is optimized by the server. The server adjusts the resolution and format of the photo and stores it at the optimal quality. This allows us to provide high-quality photos while keeping the data size small.

[1341] 6. Photo distribution

[1342] Finally, the server sends the optimized, high-quality photo data to the user's device, where it can be viewed through the app, and the finished photo can be downloaded or shared on social media.

[1343] For example, the app recognizes happiness in photos taken at home, automatically changes the background to a beach, and fixes smudged makeup on the face, resulting in a high-quality photo sent to the user's smartphone. The user can then share the photo on Instagram or other platforms.

[1344] In this way, the combination of the emotion engine enables more personalized photo editing based on the user's emotions, allowing users to easily create professional-quality, individualized photos without the need for special skills or equipment.

[1345] The processing flow will be explained below.

[1346] Step 1:

[1347] The user takes a photo on the device, then launches the dedicated application and selects the photo.

[1348] Step 2:

[1349] The user executes a command to upload a photo. The device sends the selected photo data to the server.

[1350] Step 3:

[1351] The server receives the uploaded photo data, performs an initial analysis of the photo data, and prepares it for processing.

[1352] Step 4:

[1353] The server uses an emotion engine to analyze the user's face in the photo. The emotion engine recognizes the user's emotion based on their facial expression. For example, the emotion engine analyzes the user's face to detect emotions such as "happiness" or "sadness."

[1354] Step 5:

[1355] The server uses an AI algorithm to detect the background of the photo data, and then performs background masking.

[1356] Step 6:

[1357] The server generates multiple background candidates based on the emotion information obtained from the emotion engine. For example, if the user's emotion is "happy," a bright and open background will be suggested.

[1358] Step 7:

[1359] The server selects the most suitable background from the generated background candidates. The server applies the selected background to the photo data. When applying the background, adjustments are made to ensure a natural blend.

[1360] Step 8:

[1361] The server uses an AI model to detect faces in the photo data, analyzing facial features (eyes, nose, mouth, etc.).

[1362] Step 9:

[1363] The server detects smudged makeup and wrinkles on the face. Based on emotion information, it focuses on areas that require particular correction. For example, if the emotion "fatigue" is detected, it focuses on correcting the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[1364] Step 10:

[1365] The server optimizes the corrected photo data, adjusting the resolution and compressing the data, and saving it in the optimal format.

[1366] Step 11:

[1367] The server then sends the resulting high-quality photo data to the user's device, where it is displayed in the application.

[1368] Step 12:

[1369] The user can view the completed photo, download it, or share it. The user can use the application's functions to save the photo or post it to social media.

[1370] Example 2

[1371] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1372] Editing photos taken by users with professional quality requires advanced skills and specialized knowledge. It is particularly difficult for average users to change backgrounds, modify facial features, or perform personalized editing based on the user's emotions. The present invention aims to solve the above-mentioned problems by providing a system that allows users to easily perform high-quality photo editing.

[1373] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1374] In this invention, the server includes means for receiving image data taken by a user on a terminal, means for analyzing the user's facial expression contained in the received image data and recognizing emotions, means for automatically generating a background based on the emotion information and applying it to the image data, means for detecting a person's face from the image data and analyzing facial features to correct makeup smudges and wrinkles, means for optimizing and saving the corrected image data, and means for transmitting the optimized image data to the terminal. This enables users to easily create photos that combine professional quality and individual response, even without special skills or equipment.

[1375] A "terminal" is an electronic device that a user uses to take pictures and receive processed image data.

[1376] A "server" is a central computer system that receives and processes image data sent by users.

[1377] "Image data" refers to photographic data taken by a user using a device.

[1378] An "emotion engine" is an algorithm and software that analyzes the user's facial expressions contained in image data and recognizes emotions.

[1379] The "automatic background generation means" is a means for automatically generating a background image based on the user's emotional information and applying it to image data.

[1380] The "face part detection means" refers to an algorithm and software for detecting and analyzing a person's face part from image data.

[1381] The "facial feature point analysis means" is a means for analyzing the position and shape of each part of the face (eyes, nose, mouth, etc.).

[1382] The "means for correcting makeup smudges and wrinkles" refers to algorithms and software for automatically correcting makeup smudges and wrinkles on detected facial areas.

[1383] The "optimization means" is a means for adjusting the resolution and format of the corrected image data and saving it with optimal quality.

[1384] "Emotional information" refers to the emotional data recognized by the emotion engine after analyzing the user's facial expressions.

[1385] System Overview

[1386] This system uses an emotion engine to automatically generate backgrounds for image data taken by a user on a device, and corrects makeup smudges and wrinkles on the face. This system provides high-quality photo editing personalized according to the user's emotions.

[1387] Hardware and Software Configuration

[1388] Terminal

[1389] Hardware: Smartphones, tablets, etc.

[1390] Software: Dedicated application

[1391] server

[1392] Hardware: high-performance computers, cloud servers

[1393] Software: Emotion engine, image processing algorithms, generative AI models

[1394] Specific processing explanation

[1395] User Actions

[1396] Users take a photo of their face using a device such as a smartphone. After taking the photo, they upload it to the server using a dedicated application. For example, when a user opens the app and presses the "upload photo" button, the device sends the photo data to the server.

[1397] Emotion recognition

[1398] When the server receives the photo data, the emotion engine analyzes the user's face in the photo. The emotion engine detects facial features (eyes, nose, mouth, eyebrows, etc.) and recognizes emotions from facial expressions. The recognized emotion information is generated as emotion labels such as "happiness," "sadness," and "surprise," and is used in the background generation and face correction processes.

[1399] Automatic background generation

[1400] The server generates multiple background candidates based on the emotion information from the emotion engine. Using a generative AI model, for example, in the case of "happiness," it generates a bright, open background image such as a beach or park. The server selects the most suitable background from the generated candidates and applies it to the photo data. When compositing the photo, color correction and border smoothing processes are performed.

[1401] Facial detection and correction

[1402] The server detects the user's face in the photo data and analyzes facial features. It then automatically corrects smudged makeup and wrinkles in the detected facial areas. In particular, if the "fatigue" emotion is recognized, corrections are made to make the area around the eyes clearer and the cheeks brighter.

[1403] Optimize and save

[1404] Once the photo data has been retouched, it is sent to a server where it is optimized for resolution and format, and then stored in high quality in cloud storage or a database.

[1405] Photo distribution

[1406] Finally, the server sends the optimized, high-quality photo data to the user's device, where the user can view the edited photo through a dedicated application. The finished photo can then be downloaded or shared on social media.

[1407] Examples and prompts

[1408] Examples:

[1409] For example, if you upload a photo taken at home, the system will recognize your sense of happiness, automatically change the background to a beach, fix any makeup smudges, and send the high-quality photo to your smartphone. Users can then share the photo on Instagram and other platforms.

[1410] Example prompt:

[1411] "A user takes a photo of themselves and uploads it to the server. The server automatically changes the background of the photo to a beach and fixes any makeup that has been smudged on the user's face."

[1412] In this way, the system can automatically perform high-level photo editing based on the user's emotions, making it possible for users without special skills or equipment to easily create photos that combine professional quality with individual responsiveness.

[1413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1414] Step 1: User takes and uploads a photo

[1415] Input: Photo data taken by the user using the smartphone camera app

[1416] Specific operation: The user launches the camera app on their smartphone, takes a selfie, and then opens the dedicated application and presses the "Upload photo" button.

[1417] Output: The device sends the photo data to the server.

[1418] Step 2: The server receives the photo data

[1419] Input: Photo data sent from the device

[1420] Specific operation: The server receives the HTTP request and stores the photo data in an internal database.

[1421] Output: Photo data stored on the server

[1422] Step 3: The emotion engine analyzes the face and recognizes the emotion

[1423] Input: Photo data stored on the server

[1424] Specific operation: The server starts the emotion engine and analyzes the face in the photo. It detects facial features (eyes, nose, mouth, eyebrows, etc.) and infers emotions from facial expressions.

[1425] Output: Generate emotion information (e.g., emotion labels such as "happiness," "sadness," and "surprise").

[1426] Step 4: The server automatically generates the background

[1427] Input: Emotional information and photo data

[1428] How it works: Based on the emotion information from the emotion engine, the generative AI model is used to generate multiple background candidates. For example, for "happiness," background images of a beach or park are generated. Then, the most suitable background is selected.

[1429] Output: Optimal background image

[1430] Step 5: The server applies the background to the photo data

[1431] Input: Ideal background image and photo data

[1432] How it works: The server detects the background of the photo data and applies the generated background image. It also performs color correction and border smoothing to achieve a natural composite.

[1433] Output: Photo data with background applied

[1434] Step 6: The server detects the face and corrects any smudges or wrinkles.

[1435] Input: Photo data with background applied

[1436] What it does: The server uses a face detection algorithm to identify faces in the photo. It analyzes facial features and corrects smudged makeup and wrinkles. For example, if it detects a "tired" emotion, it brightens the area around the eyes and cheeks.

[1437] Output: Photo data with face correction

[1438] Step 7: The server optimizes and stores the photo data

[1439] Input: Photo data with face correction

[1440] What it does: The server optimizes the resolution and adjusts the format, then stores it in cloud storage or a database.

[1441] Output: Optimized photo data

[1442] Step 8: The server sends the optimized photo data to the device.

[1443] Input: Optimized photo data

[1444] Specific operation: Export the completed photo data in an appropriate format such as JSON and send it to the user's device.

[1445] Output: High-quality photo data sent to your device

[1446] Step 9: User reviews and shares optimized photo data

[1447] Input: High-quality photo data sent to the device

[1448] What it does: A user opens the app, taps on a photo preview to view it, and then uses the "Download" and "Share" buttons to post the photo to Instagram and Facebook.

[1449] Output: User's social media photos

[1450] (Application example 2)

[1451] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1452] Existing photo editing systems require users to manually change backgrounds and modify faces in photos they take, which requires a significant amount of time and expertise. Furthermore, they are unable to take user emotions into account when modifying images, resulting in often unsatisfactory results. Therefore, there is a need for a system that allows users to easily and quickly create professional-quality photos that match their emotions.

[1453] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving photo data taken by a user with a terminal, means for automatically generating a background and applying it to the photo data, means for analyzing the user's facial expression using an emotion engine and recognizing the emotion, means for detecting the person's face and correcting makeup smudges and wrinkles based on the emotion, means for optimizing and saving the corrected photo, and means for transmitting the optimized photo data to the terminal. This enables users to easily create high-quality photos that reflect their emotions in a short amount of time, without having special skills or equipment.

[1454] A "terminal" is an electronic device with communication capabilities that a user owns, including smartphones and tablets.

[1455] "Photo data" refers to image information that a user takes with a device and stores in digital format.

[1456] "Means for automatically generating backgrounds" refers to technology that recognizes the background portion of photo data and generates a new background image using an algorithm.

[1457] An "emotion engine" is a software or hardware component that analyzes a user's facial expressions and recognizes their emotions.

[1458] "Methods for correcting smudged makeup and wrinkles" refers to technology that uses an algorithm to automatically correct smudged makeup and wrinkles on the face in a photo.

[1459] "Optimization means" refers to a technique that performs resolution and data compression on the edited photographs to appropriately adjust the data size while maintaining quality.

[1460] "Emotion-based correction method" refers to a technology that optimizes the correction pattern for facial makeup smudges and wrinkles based on the user's recognized emotional information.

[1461] "Background candidates" refer to multiple options for background images that can be applied to photo data.

[1462] "Facial feature points" refer to major points such as the eyes, nose, and mouth that are detected during facial analysis.

[1463] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following describes in detail the embodiments of the present invention.

[1464] First, the user takes a photo of themselves using a device such as a smartphone. After taking the photo, the user uploads the photo data to a server using a dedicated application. The device then sends the photo data to the server, which then moves on to the next processing step.

[1465] The server receives the uploaded photo data. The received photo data is analyzed using an emotion engine to recognize the user's facial expression and the emotion it conveys. The recognized emotion information is used in subsequent background generation and facial correction processes. Machine learning libraries such as TensorFlow are used to implement the emotion engine.

[1466] The server then detects the background of the photo data and generates multiple background candidates based on the emotional information analyzed by the emotion engine. These background candidates vary depending on the user's recognized emotion; for example, if the emotion is "happiness," multiple bright and open backgrounds are generated. The optimal background is selected from these and applied to the photo data to create a natural look.

[1467] Next, the server detects the user's face in the photo data and analyzes facial features (eyes, nose, mouth, etc.). Based on the emotion engine's analysis results, it corrects smudged makeup and wrinkles on the face. For example, if the user's emotion is "tired," corrections are made that focus particularly on the area around the eyes and cheeks, resulting in a lively and cheerful expression.

[1468] Once the photo data has been corrected and background generation is complete, it is optimized by the server. Optimization involves adjusting the photo resolution and data format to provide high-quality photos while keeping the data size appropriately low. This optimization process uses the image processing library OpenCV.

[1469] Finally, the server sends the optimized, high-quality photo data to the user's device, where they can view it and download it through the app or share it on social media.

[1470] In a real-world example, when a user uploads a photo taken at home, the emotion engine recognizes the feeling of happiness, changes the background to a beach, fixes makeup smudges, and sends the high-quality photo to the user's smartphone. The user can then share the photo on social media such as Instagram.

[1471] An example prompt is:

[1472] "Based on pre-entered user photos, use a generative AI model to recognize emotions, and then optimally modify the photo background and face based on the emotions. Use TensorFlow for emotion recognition."

[1473] In this way, by combining the emotion engine, it is possible to achieve more personalized photo editing according to the user's emotions, allowing users to easily create high-quality photos in a short amount of time, even without specialized skills or equipment.

[1474] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1475] Step 1:

[1476] Users take their own photos using a device such as a smartphone. After taking the photo, the photo is uploaded to a server via a dedicated application. The input here is the photo data taken by the user, and the output is the uploaded photo data.

[1477] Step 2:

[1478] The server receives uploaded photo data. The received data is stored for processing by the emotion engine. The input here is the uploaded photo data, and the output is the photo data stored on the server.

[1479] Step 3:

[1480] The server uses an emotion engine to analyze the user's facial expressions in the photo data and recognize emotions. The input is the photo data, and the output is the user's emotional information. Generative AI models such as TensorFlow are used for emotion analysis.

[1481] Step 4:

[1482] The server recognizes the background of the photo data and generates multiple background candidates based on the emotion information. It then selects the most suitable background from among them. The input here is the user's emotion information and the photo data, and the output is the most suitable background.

[1483] Step 5:

[1484] The server applies the optimal background to the photo data, creating a natural composite. The input is the selected background and the photo data, and the output is the new photo data with the background applied.

[1485] Step 6:

[1486] The server detects the user's face in the photo data and analyzes facial feature points (eyes, nose, mouth, etc.). It then corrects makeup smudges and wrinkles based on the emotion. The input here is the photo data and facial feature points, and the output is the corrected face. Image processing libraries such as OpenCV are used to analyze and correct facial feature points.

[1487] Step 7:

[1488] The server optimizes the modified photo data. The input is the modified photo data, and the output is optimized high-quality photo data. This optimization includes data compression and resolution adjustment.

[1489] Step 8:

[1490] The server sends the optimized photo data to the user's device, where the user can view the data through the application, download it, or share it on social media. The input here is the optimized photo data, and the output is the photo data sent to the device.

[1491] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1492] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1493] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1494] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1495] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1496] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1497] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1498] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1499] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1500] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1501] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1502] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1503] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1504] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1505] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1506] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1507] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1508] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1509] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1510] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1511] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1512] The following is further disclosed regarding the above embodiment.

[1513] (Claim 1)

[1514] A means for receiving photo data taken by a user on the terminal;

[1515] A means to automatically generate backgrounds and apply them to photo data;

[1516] A method for detecting a person's face and correcting makeup smudges and wrinkles,

[1517] a means for optimizing and storing the modified photograph;

[1518] means for transmitting the optimized photo data to the terminal;

[1519] A system including:

[1520] (Claim 2)

[1521] 2. The system according to claim 1, further comprising means for generating a plurality of background candidates when generating a background and selecting an optimum background from among them.

[1522] (Claim 3)

[1523] 2. The system according to claim 1, further comprising means for analyzing facial features when correcting smudged makeup or wrinkles on the face.

[1524] "Example 1"

[1525] (Claim 1)

[1526] A means for receiving image data captured by a user on a terminal;

[1527] a means for identifying a background portion of the image data, selecting an optimal background from a plurality of automatically generated background candidates, and applying the selected background to the image data;

[1528] A method for detecting the user's face in the image data and correcting makeup smudges and wrinkles by analyzing facial feature points;

[1529] means for optimizing and storing the image data after correction and background generation;

[1530] means for transmitting the optimized image data to a terminal;

[1531] A system including:

[1532] (Claim 2)

[1533] 2. The system according to claim 1, wherein when generating a background, a plurality of background candidates are generated and the most suitable background is selected from among them.

[1534] (Claim 3)

[1535] 2. The system according to claim 1, wherein facial feature points are analyzed when correcting smudged makeup or wrinkles on the face.

[1536] "Application Example 1"

[1537] (Claim 1)

[1538] A means for receiving photo data taken by a user on the terminal;

[1539] A means to automatically generate backgrounds and apply them to photo data;

[1540] A method for detecting a person's face and correcting makeup smudges and wrinkles,

[1541] a means for optimizing and storing the modified photograph;

[1542] means for transmitting the optimized photo data to the terminal;

[1543] A means to simulate trying on products by overlaying product images onto the user's photos,

[1544] A system including:

[1545] (Claim 2)

[1546] 2. The system according to claim 1, further comprising means for generating a plurality of background candidates when generating a background and selecting an optimum background from among them.

[1547] (Claim 3)

[1548] 2. The system according to claim 1, further comprising means for analyzing facial features when correcting smudged makeup or wrinkles on the face.

[1549] "Example 2: Combining Emotion Engines"

[1550] (Claim 1)

[1551] A means for receiving image data captured by a user on a terminal;

[1552] A means for analyzing a user's facial expression contained in the received image data and recognizing emotions;

[1553] a means for automatically generating a background based on emotion information and applying the background to image data;

[1554] A method for detecting a person's face from image data, analyzing facial features, and correcting makeup smudges and wrinkles.

[1555] means for optimizing and storing the modified image data;

[1556] means for transmitting the optimized image data to a terminal;

[1557] A system including:

[1558] (Claim 2)

[1559] 2. The system according to claim 1, further comprising means for generating a plurality of background candidates when generating a background and selecting an optimum background from among them.

[1560] (Claim 3)

[1561] 10. The system of claim 1, further comprising means for utilizing emotion information when correcting smudged makeup or wrinkles on the face.

[1562] "Application example 2 when combining emotion engines"

[1563] (Claim 1)

[1564] A means for receiving photo data taken by a user on the terminal;

[1565] A means to automatically generate backgrounds and apply them to photo data;

[1566] A means for analyzing the user's facial expressions and recognizing emotions using an emotion engine;

[1567] A method for detecting a person's face and correcting makeup smudges and wrinkles based on emotion.

[1568] a means for optimizing and storing the modified photograph;

[1569] means for transmitting the optimized photo data to the terminal;

[1570] A system including:

[1571] (Claim 2)

[1572] 2. The system according to claim 1, further comprising means for generating a plurality of background candidates when generating a background, and selecting the most suitable background from among them based on emotion.

[1573] (Claim 3)

[1574] 2. The system according to claim 1, further comprising means for analyzing facial features and making corrections based on emotions when correcting smudged makeup or wrinkles on the face. [Explanation of symbols]

[1575] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for receiving photo data taken by a user on the terminal; A means to automatically generate backgrounds and apply them to photo data; A method for detecting a person's face and correcting makeup smudges and wrinkles, a means for optimizing and storing the modified photograph; means for transmitting the optimized photo data to the terminal; A system including:

2. 2. The system according to claim 1, further comprising means for generating a plurality of background candidates when generating a background and selecting the most suitable background from among them.

3. 2. The system according to claim 1, further comprising means for analyzing facial features when correcting smudged makeup or wrinkles on the face.

Images