Patents
Literature
369results about "Modifying/creating image using manual input" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Information processing device, information processing method, and program
PCT designated stage expiredWO2025126712A1Processor architectures/configurationCommerceInformation processingEngineering
[Problem] To enable generation of more effective advertisements. [Solution] An information processing device comprising a control unit that edits a tag group obtained by converting advertisement content to text, extracts a derivable element from the advertisement content, and generates, by deriving the corresponding element according to the edited tag group, derived advertisement content based on the advertisement content.
Owner:SONY GROUP CORP
Information processing device, server, information processing method, and program
PendingJP2025120878ABiological modelsProgram/content distribution protectionInformation processingComputer graphics (images)
To improve convenience related to use of a diffusion model.SOLUTION: An information processing device capable of generating an adversarial image in a diffusion model includes a control unit configured to generate the adversarial image based on a first image and a watermark image including identification information. The adversarial image is an image in which identification information can be visually recognized in a second image when the second image is generated based on the diffusion model and the adversarial image.SELECTED DRAWING: Figure 1-1
Owner:LY CORP
Picture generation method and device, storage medium and computer equipment
PendingCN120451316AMachine learningModifying/creating image using manual inputGeneration processHuman–computer interaction
According to the picture generation method and device, the storage medium and the computer equipment provided by the invention, after the MCP server obtains the picture generation request sent by the client supporting the MCP protocol through the MCP protocol, the server can optimize the cue word according to the context information; according to the method, a prompt word is optimized, then picture data corresponding to the optimized prompt word is generated by utilizing a preset picture generation tool, so that the generated picture better meets the actual demand of a user, the accuracy and practicability of the picture are effectively improved, the limitation of a fixed template can be broken through in the process, the more flexible and innovative picture can be generated, and then the user experience is improved. According to the invention, the picture data can be preprocessed, and the preprocessed picture data can be returned to the client through the MCP protocol. Through the automatic generation process, the links of manual operation of the user are reduced, the picture generation efficiency is greatly improved, and the advantages are obvious especially when the pictures are generated in batches.
Owner:1DATA TECH SHANGHAI CO LTD
Methods and systems for preserving image features during image editing
Described embodiments generally relate to a computer-implemented method for editing an image. The method includes accessing an image; identifying at least a first area of the image and a second area of the image; configuring a model to generate an edited image based on the first area of the image and the second area of the image, wherein the edited image comprises a first area of the edited image and a second area of the edited image; wherein the model is configured to generate the edited image such that the first area of the edited image differs from the first area of the image less than the second area of the edited image differs from the second area of the image.
Owner:CANVA PTY LTD
Game graphic design automatic scene matching method and system based on deep learning
InactiveCN120107383ABiological modelsCharacter and pattern recognitionFeature vectorComputer graphics (images)
The invention discloses a game graphic design automatic scene matching method and system based on deep learning, and relates to the technical field of image matching, and the method comprises the steps: obtaining a background base map and a plurality of plane element image libraries of a game scene; performing image segmentation on the background base image, dividing the background base image into a plurality of to-be-matched areas, and extracting an image feature vector of each to-be-matched area; establishing a semantic tag generation model, and generating a scene semantic tag of each to-be-matched area; according to the scene semantic tag, screening a plane element matched with each to-be-matched area from a plane element image library, and calculating a matching degree score of the plane element and the to-be-matched area; and placing the plane element with the highest matching degree score in the corresponding to-be-matched area to generate a complete game scene design drawing. The complete and coordinated game scene design drawing can be automatically generated, selection and layout of game materials are optimized, and design efficiency and effect consistency are improved.
Owner:SHENZHEN AOKU TECH CO LTD
Apparel image generating system, method thereof, and program therefor
To realize a service for easily generating an apparel image.SOLUTION: According to an embodiment of the present invention, an apparel image generating system has: a display unit for displaying a selected screen for which a user can select at least one of a model image, an item image, a background image, a face image and a pose image; and an image generating unit for using an image generation model to generate an apparel image from the image selected by the user.SELECTED DRAWING: Figure 9
Owner:GENWORK CO LTD
Mouse track generation method and system for simulating user behavior, medium and equipment
The invention discloses a mouse track generation method and system for simulating user behaviors, a medium and equipment, and relates to the technical field of user simulation. The method comprises the steps that multiple pieces of real track data are collected, and a track library is constructed based on the track data; obtaining a starting point and an end point in a verification code image needing to be verified, and calculating a track direction and a track length based on the starting point and the end point; matching in the trajectory library based on the trajectory direction and the trajectory length to obtain a target trajectory; and preprocessing the target trajectory to obtain a simulated trajectory. By implementing the technical scheme provided by the invention, the authenticity of the mouse track can be improved.
Owner:SUZHOU CHUANGLUTIANXIA INFORMATION TECH CO LTD
Data processing device, data processing method and data processing program
ActiveJP2025165593ADigital data information retrievalSpecial data processing applicationsSoftware engineeringComputer engineering
To provide a data processing device, a data processing method and a program capable of reducing a work burden for creating a drawing.SOLUTION: A data processing device includes: a receiving unit 292 that accepts, from a user terminal operated by a user, a source drawing that is a source for drawing creation; a variable obtaining unit 294 that obtains, from an AI-OCR model, variable data by inputting the source drawing in the AI-OCR model that has learnt drawings created in past as learning data; and an obtaining unit 296 which accepts, from the user terminal, a prompt that instructs the creation of a new drawing, inputs, to a generative AI model 58A, the prompt together with the source drawing and the variable data, and obtains code information from the output by the generative AI model.SELECTED DRAWING: Figure 7
Owner:SOFTBANK GROUP CORP
Image expansion method and system based on artificial intelligence generation technology, and electronic equipment
PendingCN120765454AGeometric image transformationModifying/creating image using manual inputPattern recognitionImaging processing
The invention discloses an image expansion method and system based on an artificial intelligence generation technology and electronic equipment, and relates to the technical field of image processing, and the method comprises the steps: recognizing a target object and / or a key region in a to-be-expanded image, and determining the scaling of the to-be-expanded image according to the target object and / or the key region in the to-be-expanded image; scaling the to-be-expanded image according to a scaling ratio to obtain a scaled to-be-expanded image; according to the to-be-expanded image, the preset canvas and the picture canvas, generating an expanded image; and adding the zoomed to-be-expanded image into a target area in the expanded image to obtain an output image. According to the invention, the image expansion accuracy and efficiency can be improved.
Owner:QINGMUTEC
Interior space simulation device
To display a display image of an interior space including interior equipment that matches a user's image by a simple operation.SOLUTION: An interior space simulation device 1 comprises: an acquisition unit 12 for acquiring atmosphere information of an interior space input by a user terminal 200; an extraction unit 13 for extracting a plurality of images of interior spaces stored in association with the acquired atmosphere information of interior spaces from a storage unit 11; a selection unit 14 for selecting a prescribed number of images of interior spaces from among the plurality of extracted images of interior spaces; and a transmission unit 15 for transmitting at least one of the prescribed number of selected images of interior spaces to the user terminal 20. If an image similar to an image of any interior space constructed by an entity in the past can be retrieved from among the plurality of images of interior spaces through image recognition, the selection unit 14 selects the retrieved image of the interior space as the prescribed number of images of interior spaces.SELECTED DRAWING: Figure 1
Owner:SANGETSU CORP
Sketch-to-3d object creation
Text-to-image generation generally refers to the process of generating an image from one or more text prompts input by a user and in some cases also a user provided sample image. Existing text-to-image generation processes are configured to only generate content from text and usually non-original sample images (e.g. obtained from the Internet). This limits the customization options available to the user. The present disclosure provides a sketch-to-3D content generation process which allows users to generate 3D content from a given 3D human generated, or free-form, sketch, which enables greater customization of computer generated 3D content.
Owner:NVIDIA CORP
Image authentication
A system for managing the application of artwork to a substrate, the system comprising one or more processors configured to: receive an indication of a graphic; generate a set of candidate locations for markers visually differentiable from the graphic; transmit the candidate locations to a graphic applicator; receive from the applicator an image of a target substrate region having visually differentiable markers applied thereto; and compare the locations of the markers in the image with the candidate locations.
Owner:KELLER SERVICES FZCO
System
A system is provided.SOLUTION: Means for a user to select an image file from a terminal, means for the terminal to transmit the selected image file to a server, means for the server to receive the transmitted image file, means for the server to provide the received image file to a generation AI model and apply a customization element to generate an original stamp, means for the server to transmit the generated original stamp to the terminal, means for the terminal to display the transmitted original stamp to a user and receive a correction request, means for the server to transmit the correction request to the generation AI model again, A system, comprising: means for generating a modified original sticker; means for saving, by a server, a finally generated original sticker in an account of a user; and means for displaying, by a terminal, the finally saved original sticker for the user to use in a communication platform.SELECTED DRAWING: Figure 1
Owner:SOFTBANK GROUP CORP
Program, information processing method, information processing device, and image generation device
To improve convenience or the like about image generation.SOLUTION: A program to be executed by an information processing device makes the information processing device execute: acquiring a first image set for additional learning to an image generation device for generating an image on the basis of prompts; making the image generation device learn the first image set; setting a prompt set; and making the image generation device generate a second image set on the basis of the prompt set.SELECTED DRAWING: Figure 1-1
Owner:LY CORP
Information processing methods, information processing systems, and programs
This invention provides an information processing method, information processing system, and program that can improve the color reproducibility after color reduction compared to conventional methods. [Solution] According to one aspect of the present invention, an information processing method is provided, comprising an acquisition step, a color reduction step, and an output step, wherein in the acquisition step, a third image data which is colored image data is acquired; in the color reduction step, the colors contained in the third image data are clustered, and the third image data is color-reduced according to color-reduced information indicating the color corresponding to each cluster, the color corresponding to each cluster is determined using the mode of each cluster; and in the output step, a fourth image data which is color-reduced image data is output.
Owner:XENOTOON CO LTD
Generating user interface displaying augmented reality graphics
PendingCN120731415AInput/output for user-computer interactionCharacter and pattern recognitionGraphicsGraphic system
An augmented reality (AR) graphics system is provided. The AR graphics system may coordinate the display of augmented reality graphics created by a plurality of users located in an environment. The AR graphics system may determine an alignment object located in the environment, the alignment object being designated as a common origin of a real-world coordinate system for determining where to display the AR graphics within the environment. Further, a priority scheme is implemented to resolve conflicts between overlapping inputs provided by different users in order to generate a single version of the AR graph.
Owner:SNAP INC
Image style conversion device and image style conversion program
Owner:TAKENAKA CORP
Simulator, injection device or imaging system including the simulator, and simulation program
To achieve a prediction approximating a secular change of a pixel value in an actual tissue, with higher accuracy.SOLUTION: A simulator 20, which predicts a secular change of a pixel value in a tissue of a subject, includes: a subject information acquisition unit 11 to acquire information on the subject; a protocol acquisition unit 12 to acquire an injection protocol for a contrast medium; a tissue information acquisition unit 13 to acquire information on the tissue; and a prediction unit 16 to predict, based on the information on the subject, the injection protocol, and the information on the tissue, a secular change of a pixel value of each of a plurality of compartments obtained by dividing the tissue along a blood flow direction D.SELECTED DRAWING: Figure 1
Owner:HIROSHIMA UNIVERSITY +1
Electronic calligraphy style editing method based on action information, electronic equipment and storage medium
PendingCN120124599ANatural language data processingModifying/creating image using manual inputImaging processingData source
The invention discloses an electronic calligraphy style editing method based on action information, electronic equipment and a storage medium, the action information of the electronic calligraphy is defined, the sampled action information of the electronic calligraphy is obtained from hardware input equipment or a data source of the electronic calligraphy, a stroke model is input, a calligraphy character image is incrementally drawn, and the calligraphy character is edited. And modifying and adjusting the action information sequence for forming the calligraphy character image to form a new style calligraphy character image. According to the invention, the calligraphy character style is edited based on the writing action information, so that after the style is edited, the writing continuity is still kept, the traction belt between the strokes can be automatically adjusted, and the later image processing is not needed for the cursive script. The calligraphy character style is edited based on the writing action information, so that the writing dynamic state is still kept after the calligraphy character style is changed. By adjusting the style editing parameters, the effects of interpolation transition and dynamic adjustment between calligraphy styles can be achieved.
Owner:TAIZHOU KUDE TECHNOLOGY CO LTD
System
A system is provided.SOLUTION: A system comprising: a means for a user to take a photograph of his / her own face and upload the photograph; a means for analyzing the uploaded face photograph to identify the contour of the face, the hair type, and the length of hair; a means for fusing the analysis result and a hairstyle selected by the user to generate an optimal cutting method and a finished image; a means for displaying the generated finished image; a means for obtaining feedback by checking the displayed finished image; and a means for storing data of the final finished image and the cutting method and presenting the data to a hairdresser.SELECTED DRAWING: Figure 1
Owner:SOFTBANK GROUP CORP
system
Provide a system. A method for receiving an input message from a user; means for analyzing the received message and generating a response message based on the content of the message; means for generating images with different facial expressions and postures based on the response message; means for transmitting the generated response message and image to a user; A system including:
Owner:SOFTBANK GROUP CORP
Data acquisition device and data management system
PendingJP2025184038AModifying/creating image using manual inputInput/output processes for data processing
To allow a user to access data from a terminal device and perform processing or the like on the data on a display screen of the terminal device without using a dedicated application.SOLUTION: A data acquisition device 1 is assigned a unique identification ID and includes data acquisition means for acquiring data, storage control means for storing at least the data acquired by the data acquisition means in storage means in a prescribed format that can be expanded in a web browser, and wireless communication means. When the identification ID is read by a terminal device 3 equipped with ID reading means for reading the identification ID, the data acquisition device 1 is connected to the terminal device via the wireless communication means, and the data stored in the storage means becomes accessible from the terminal device via the web browser and can be processed and edited on a display screen 330 of the terminal device.SELECTED DRAWING: Figure 1
Owner:TOMY CO LTD
Computing system, computerized method, medium, and computer program for running a social media program with a face selection tool for masking recognized faces
A computing system is provided that includes one or more processors and associated memory storing instructions that cause the one or more processors to execute a social media program. The processor is configured to recognize one or more faces in a video via a face recognition module of the social media program. The processor is configured to display a graphical user interface (GUI). The GUI includes a face selection tool configured to allow a user to select at least one recognized face to be masked. The processor is configured to mask the selected at least one recognized face in the video to generate an edited video. After masking, the processor is configured to share the edited video to a social media platform for viewing by other users.
Owner:LEMON CO LTD
Display control system, display control method, and program
ActiveJP7844836B2Modifying/creating image using manual inputInput/output processes for data processingComputer hardwareControl system
To improve viewability of writing on an online basis.SOLUTION: A display control system 10 according to the present invention has a display control unit 101 and a writing reception unit 102. The display control unit 101, in a first terminal device and a second terminal device connected to each other through a communication network, displays an image captured by the first terminal device on the first terminal device and the second terminal device. The writing reception unit 102 receives writing by an operation on at least either of the first terminal device and the second terminal device. The display control unit 101 displays the writing so that it is superimposed on the image.SELECTED DRAWING: Figure 1
Owner:NEC CORP
Information processing device
To provide an information processing apparatus configured to generate effective content for a sales object, which draws the interest of a user.SOLUTION: An information processing apparatus 100 includes: a content generation unit 213 which applies a machine learning model to content for a specific sales object, to generate modified content by modifying a predetermined part other than the specific sales object in the content; and a content providing unit 214 which provides the generated modified content to a user. The content generation unit 213 applies the machine learning model to content for another sales object, and modifies a predetermined part other than the other sales object, according to an action of the user with respect to the modified content, in the content for the other sales object, to generate modified content for the other sales object.SELECTED DRAWING: Figure 2
Owner:NOMURA RESEARCH INSTITUTE
Drawing program, drawing device, control method, and recording medium
This drawing program causes a computer that draws line segments accompanied by textural expression to execute: an acquisition process for acquiring a plurality of textures that include a reference texture having a reference length, and that have mutually different lengths and exhibit a common textural expression; a selection process for selecting at least one of the plurality of textures acquired by the acquisition process, in accordance with the length of a line segment to be drawn; a drawing process for positioning the texture selected through the selection process and drawing the line segment; and a process for accepting a change in the length of the line segment, wherein the drawing program is characterized in that, when a change in the length of the line segment is accepted, a second texture corresponding to the length of the line segment after the change is selected, in lieu of a first texture that was selected in the selection process before the change, and when the length of the second texture is a prescribed integral multiple of the reference length, a prescribed integral number of pieces of the reference texture are selected in lieu of the second texture.
Owner:LIVE2D
Contour generation method and contour generation apparatus
ActiveJP7839686B2Modifying/creating image using manual inputPattern recognitionComputer graphics (images)
To reduce effort required to correct an outline of an object.SOLUTION: An outline generation method disclosed herein makes a computer perform processing of extracting an outline of an object in a captured image of the object, setting multiple outline points on the outline of the object, acknowledging designation of a region including a part of the outline, deleting outline points included in the region, and correcting the outline.SELECTED DRAWING: Figure 8
Owner:NIKON SYSTEMS INC
Handwriting display method and device, equipment and storage medium
PendingCN120610647AImage analysisModifying/creating image using manual inputHandwritingComputer graphics (images)
The invention provides a handwriting display method and device, equipment and a storage medium. The method comprises the steps that a first paper texture background image currently used by a display interface is determined; based on the first paper texture background image, determining a currently applicable target stroke style and a target handwriting color; and displaying the currently written target handwriting on the display interface based on the target stroke style and the target handwriting color. According to the method, the writing feeling of a simulation user can be enhanced while the convenience of handwriting adjustment is improved.
Owner:GUANGZHOU LANGO ELECTRONICS TECH CO LTD
Program, image generation support apparatus, image generation support system, and image generation support method
Owner:KONICA MINOLTA INC
Information Processing System and Program
To provide an information processing system, or the like, configured to identify a travel path in an imaging area more accurately.SOLUTION: An information processing system includes a processor which is configured to execute a program so that the following steps are to be performed. The program includes: an acquisition step of acquiring, by the processor, images captured by an imaging apparatus in imaging positions on a travel path on which the imaging apparatus moves in an imaging area with a predetermined marker provided there in; an estimation step of estimating the travel path and positional relationship between at least a part of the travel path and the marker, on the basis of the acquired captured images; a display output step of outputting, when an imaging position is designated, display data for displaying an image captured in the imaging position; and a drawing output step of outputting drawing data indicating a drawing of the imaging area and the estimated travel path superimposed on the drawing. In the drawing data, the position of the marker and the travel path in the drawing have the estimated positional relationship.SELECTED DRAWING: Figure 1
Owner:ZEN INTELLIGENCE INC