Image correction method based on atmosphere of image and electronic device thereof

Abstract

Various embodiments of the present invention may comprise: a display (160); a memory (130) storing instructions; and a processor (120). The instructions, when executed by the processor, may instruct the electronic device (101) to: identify a plurality of objects included in an image displayed on the display; extract metadata of the image; identify a subject of the image on the basis of the plurality of objects and the metadata; determine, from among the plurality of objects, a first object that does not correspond to the identified subject; if the first object is a person, perform face recognition on the person; search whether a person image matching the face-recognized person is stored in the memory or a server connected to the electronic device; identify, on the basis of the searched person image, a reference image having a facial expression corresponding to the identified subject; generate a prompt on the basis of the image, the identified subject, and the identified reference image; generate a second object for replacing the first object on the basis of the generated prompt; and display the generated second object. Various embodiments are possible.

Description

Image correction method based on the mood of the image and electronic device thereof

[0001] Various embodiments of the present disclosure relate to an image correction method based on the atmosphere of an image and an electronic device thereof.

[0002] With the advancement of digital technology, various types of electronic devices, such as mobile terminals, personal digital assistants (PDAs), electronic notebooks, smartphones, tablet PCs (personal computers), and wearable devices, are becoming widely used. These electronic devices are constantly undergoing improvements in their hardware and / or software to support and enhance their functionality.

[0003] Meanwhile, conventional image (or video) editing features (or applications) focus on enabling users to create engaging content and share it with others on social media. For example, image editing features may include offering a variety of stickers and filters, a user content sharing platform, and image or video editing technology.

[0004] In one embodiment, a method and device may be disclosed for identifying an image subject (or mood, situation, culture) based on an object (e.g., a person, an object, a background) of an image (or a video), metadata of the image, or user input information, and applying a facial expression (e.g., joy, sadness, surprise, anger) appropriate for the subject of the image to a person in the image through generative artificial intelligence (AI).

[0005] According to an embodiment of the present disclosure, an electronic device (101) includes a display (160), a memory (130) storing instructions; and a processor (120), wherein the instructions, when executed by the processor, cause the electronic device to identify a plurality of objects included in an image displayed on the display, extract metadata of the image, identify a subject of the image based on the plurality of objects and the metadata, determine a first object among the plurality of objects that does not correspond to the identified subject, perform facial recognition on the subject when the first object is a person, search whether a person image matching the recognized face is stored in the memory or a server connected to the electronic device, identify a reference image having a facial expression corresponding to the identified subject based on the searched person image, generate a prompt based on the image, the identified subject, and the identified reference image, generate a second object to replace the first object based on the generated prompt, and display the generated second object.

[0006] An operating method of an electronic device (101) according to an embodiment of the present disclosure may include an operation of identifying a plurality of objects included in an image displayed on a display of the electronic device, an operation of extracting metadata of the image, an operation of identifying a subject of the image based on the plurality of objects and the metadata, an operation of determining a first object among the plurality of objects that does not correspond to the identified subject, an operation of performing facial recognition on the subject when the first object is a person, an operation of searching whether a person image matching the recognized face of the person is stored in the memory or a server connected to the electronic device, an operation of identifying a reference image having a facial expression corresponding to the identified subject based on the searched person image, an operation of generating a prompt based on the image, the identified subject, and the identified reference image, an operation of generating a second object for replacing the first object based on the generated prompt, and an operation of displaying the generated second object.

[0007] In one embodiment, the subject of an image can be identified based on an object in the image (or video), metadata of the image, or user input information, and the subject of the image can be emphasized and enhanced by applying a facial expression that matches the subject of the image to a person in the image through generative AI.

[0008] According to one embodiment, the subject of an image can be automatically recognized without user intervention, and the facial expressions of people included in the image can be corrected to quickly and efficiently improve the image.

[0009] In one embodiment, by correcting an image with a facial expression generated to match the subject of the image, consistency of the image can be maintained and a more natural result can be provided.

[0010] In one embodiment, the person included in the image can be distinguished into a related person (e.g., a person whose photo is stored in memory or on a server) and an unrelated person, thereby helping the user to more easily select the desired image.

[0011] According to one embodiment, by creating a database of various facial expressions using photos stored in memory or on a server and using the databased images as reference images, AI (artificial intelligence) can generate and correct facial expressions of a person that match the subject of the image, thereby obtaining more accurate and high-quality results.

[0012] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0013] FIG. 2A is a diagram illustrating an example of analyzing an image in an electronic device according to one embodiment.

[0014] FIG. 2b is a diagram illustrating an example of correcting an image to fit an image subject in an electronic device according to one embodiment.

[0015] FIG. 3 is a flowchart illustrating an operating method of an electronic device according to one embodiment.

[0016] FIGS. 4A and 4B are diagrams illustrating an example of correcting a person in an image to match the subject of the image in an electronic device according to one embodiment.

[0017] FIGS. 5A and 5B are diagrams illustrating an example of correcting an object in an image to match the image subject in an electronic device according to one embodiment.

[0018] FIG. 6 is a flowchart illustrating a method for identifying an image subject of an electronic device according to one embodiment.

[0019] FIG. 7A is a diagram illustrating an example of identifying an object included in an image in an electronic device according to one embodiment.

[0020] FIG. 7b is a diagram illustrating an example of identifying metadata and user input information of an image in an electronic device according to one embodiment.

[0021] FIG. 8 is a flowchart illustrating an image correction method corresponding to an image subject in an electronic device according to one embodiment.

[0022] FIG. 9A and FIG. 9B are diagrams illustrating an example of databaseizing a person's facial expression in an electronic device according to one embodiment.

[0023] FIG. 9c is a diagram illustrating an example of searching for a stored human image in an electronic device according to one embodiment.

[0024] FIG. 9d is a diagram illustrating an example of generating an object that does not correspond to the subject of an image in an electronic device according to one embodiment.

[0025] FIG. 10 is a diagram illustrating an example of analyzing and database-izing a person who was not searched for in an electronic device according to one embodiment.

[0026] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments.

[0027] Referring to FIG. 1, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0028] The processor (120) may, for example, execute software (e.g., a program (140)) to control at least one other component (e.g., a hardware or software component) of the electronic device (101) connected to the processor (120) and perform various data processing or operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0029] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0030] The memory (130) can store various data used by at least one component (e.g., processor (120) or sensor module (176)) of the electronic device (101). The data can include, for example, software (e.g., program (140)) and input data or output data for commands related thereto. The memory (130) can include volatile memory (132) or non-volatile memory (134).

[0031] The program (140) may be stored as software in the memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0032] The input module (150) can receive commands or data to be used in a component of the electronic device (101) (e.g., a processor (120)) from an external source (e.g., a user) of the electronic device (101). The input module (150) can include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0033] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0034] The display module (160) can visually provide information to an external party (e.g., a user) of the electronic device (101). The display module (160) may include, for example, a display, a holographic device, or a projector and a control circuit for controlling the device. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

[0035] The audio module (170) can convert sound into an electrical signal, or vice versa, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150), output sound through the sound output module (155), or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphone) directly or wirelessly connected to the electronic device (101).

[0036] The sensor module (176) can detect the operating status (e.g., power or temperature) of the electronic device (101) or the external environmental status (e.g., user status) and generate an electrical signal or data value corresponding to the detected status. According to one embodiment, the sensor module (176) can include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biometric sensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0037] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0038] The connection terminal (178) may include a connector through which the electronic device (101) may be physically connected to an external electronic device (e.g., electronic device (102)). According to one embodiment, the connection terminal (178) may include, for example, an HDMI connector, a USB connector, an SD card connector, or an audio connector (e.g., a headphone connector).

[0039] The haptic module (179) can convert electrical signals into mechanical stimuli (e.g., vibration or movement) or electrical stimuli that a user can perceive through tactile or kinesthetic sensations. According to one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0040] The camera module (180) can capture still images and videos. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0041] The power management module (188) can manage power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented as, for example, at least a part of a power management integrated circuit (PMIC).

[0042] A battery (189) may power at least one component of the electronic device (101). In one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0043] The communication module (190) may support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between the electronic device (101) and an external electronic device (e.g., electronic device (102), electronic device (104), or server (108)), and the performance of communication through the established communication channel. The communication module (190) may operate independently from the processor (120) (e.g., application processor) and may include one or more communication processors that support direct (e.g., wired) communication or wireless communication. According to one embodiment, the communication module (190) may include a wireless communication module (192) (e.g., a cellular communication module, a short-range wireless communication module, or a global navigation satellite system (GNSS) communication module) or a wired communication module (194) (e.g., a local area network (LAN) communication module, or a power line communication module). Among these communication modules, the corresponding communication module can communicate with an external electronic device (104) via a first network (198) (e.g., a short-range communication network such as Bluetooth, wireless fidelity (WiFi) direct, or infrared data association (IrDA)) or a second network (199) (e.g., a long-range communication network such as a legacy cellular network, a 5G network, a next-generation communication network, the Internet, or a computer network (e.g., a LAN or WAN)). These various types of communication modules can be integrated into a single component (e.g., a single chip) or implemented as multiple separate components (e.g., multiple chips). The wireless communication module (192) can verify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) by using subscriber information (e.g., an international mobile subscriber identity (IMSI)) stored in the subscriber identification module (196).

[0044] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0045] The antenna module (197) can transmit or receive signals or power to or from an external device (e.g., an external electronic device). In one embodiment, the antenna module (197) may include an antenna including a radiator formed of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). In one embodiment, the antenna module (197) may include a plurality of antennas (e.g., an array antenna). In this case, at least one antenna suitable for a communication method used in a communication network, such as the first network (198) or the second network (199), may be selected from the plurality of antennas, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0046] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[0047] At least some of the above components can be interconnected and exchange signals (e.g., commands or data) with each other via a communication method between peripheral devices (e.g., a bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)).

[0048] According to one embodiment, commands or data may be transmitted or received between the electronic device (101) and an external electronic device (104) via a server (108) connected to a second network (199). Each of the external electronic devices (102 or 104) may be the same or a different type of device as the electronic device (101). According to one embodiment, all or part of the operations executed in the electronic device (101) may be executed in one or more of the external electronic devices (102, 104, or 108). For example, when the electronic device (101) is to perform a certain function or service automatically or in response to a request from a user or another device, the electronic device (101) may, instead of or in addition to executing the function or service itself, request one or more external electronic devices to perform the function or at least a part of the service. One or more external electronic devices that receive the request may execute at least a portion of the requested function or service, or an additional function or service related to the request, and transmit the result of the execution to the electronic device (101). The electronic device (101) may process the result as is or additionally and provide it as at least a portion of a response to the request. For this purpose, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used, for example. The electronic device (101) may provide an ultra-low latency service by using distributed computing or mobile edge computing, for example. In another embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server utilizing machine learning and / or a neural network. According to one embodiment, the external electronic device (104) or the server (108) may be included in the second network (199).The electronic device (101) can be applied to intelligent services (e.g., smart home, smart city, smart car, or healthcare) based on 5G communication technology and IoT-related technology.

[0049] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0050] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish the corresponding component from other corresponding components and do not limit the corresponding components in any other respect (e.g., importance or order). When a component (e.g., a first) is referred to as "coupled" or "connected" to another (e.g., a second) component, with or without the terms "functionally" or "communicatively," it means that the component can be connected to the other component directly (e.g., wired), wirelessly, or through a third component.

[0051] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0052] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0053] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0054] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0055] FIG. 2A is a diagram illustrating an example of analyzing an image in an electronic device according to one embodiment.

[0056] Referring to FIG. 2A, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may analyze a first image (210) (or a photo, a video) to generate a second image (230) of FIG. 2B. In the following description, images are used as examples, but the present invention may also be implemented by utilizing a scene of a video as an image. The first image (210) may be displayed on a display (e.g., the display module (160) of FIG. 1). For example, the first image (210) may be an image stored in a memory (e.g., the memory (130) of FIG. 1) or a cloud server (e.g., the server (108) of FIG. 1) connected to (or registered with) the electronic device (101), or a preview image acquired (or photographed) from a camera (e.g., the camera module (180) of FIG. 1).

[0057] The processor (120) can identify a plurality of objects included in the first image (210). The plurality of objects may include at least one of a person (or people), an animal, an object, or a background. The person may include a face. The object may include an animal. The object may be a clock, a desk, a tree, or a car. Alternatively, the object may include clothes worn by the person, the person's hair, or an item (e.g., an accessory, glasses) included in (or held by) the person. The background may be a mountain, an ocean, a sky, a sun, or a moon. For example, the processor (120) can identify eight people, clothes worn by each person, and items (e.g., a bouquet) held by each person as objects from the first image (210).

[0058] According to one embodiment, the processor (120) may identify the context of the first image (210) based on the identified object. If the identified object is a person, the processor (120) may perform facial recognition on the person and search whether a person image matching the recognized person is stored in the memory (130) or the server (108). The person image may be an acquaintance of the user of the electronic device (101), and may be matched with a contact, a photo, a video, or an image (or video) stored in the cloud. Alternatively, the processor (120) may search for a person image matching the recognized person in the SNS (social network service) of another user registered in the user's SNS account. If the person image is searched for in the memory (130) or the server (108), the processor (120) may classify the person of the object as a related person. If the person image is not retrieved from the memory (130) or server (108), the processor (120) can classify the person of the object as an irrelevant person.

[0059] According to one embodiment, when the processor (120) is classified as the relevant person, it can identify a reference image having a facial expression corresponding to the identified subject based on the retrieved person image. The reference image may serve as a basis when the generative AI generates a second object to replace the first object. The facial expression included in the first image (210) may be a neutral expression, while the facial expression in the reference image may be a smiling expression.

[0060] The processor (120) can acquire various facial expressions of the person image based on the person image matching the person stored in the memory (130) or the server (108), and identify a person image having a facial expression corresponding to the identified subject among the acquired facial expressions as the reference image. The various facial expressions are stored in a database, and may be templates that are created in advance, such as six facial expressions (e.g., joy, sadness, surprise, anger, disgust, fear), expressions having various emotions through the intensity of the expression (e.g., laughter, enjoyment, satisfaction, discouragement, depression, etc.), or combinations of similar facial expressions (e.g., fear + joy = desperate, fear + sadness = miserable).

[0061] When a person image matching the face-recognized person as the first object is not searched (e.g., classified as an irrelevant person), the processor (120) may analyze the first object to determine at least one of gender, age, or country, and generate and obtain various facial expressions of the first object based on the gender, age, or country. The processor (120) may generate and obtain various facial expressions of the first object by matching the first object to a virtual person having the same or similar gender, age, or country. The processor (120) may identify an image of the first object having a facial expression corresponding to the identified subject among the acquired facial expressions as the reference image.

[0062] The processor (120) can extract metadata of the first image (210). The metadata can include the date, time, or location when the first image (210) was created (or photographed). Alternatively, the metadata can further include attribute information such as file format, size (or capacity), resolution, pixels, camera manufacturer, model, exposure time, ISO sensitivity, or whether it is original. For example, the processor (120) can extract “July 2, 2024, 1:00 PM, Miami OO Street” as metadata of the first image (210). The processor (120) can identify the context of the first image (210) based on the metadata of the first image (210).

[0063] The processor (120) can identify the subject of the first image (210) based on the identified plurality of objects and the metadata. The subject represents the atmosphere of the first image (210) and may be replaced with terms such as situation, context, culture, religion, and color. The processor (120) can further utilize information stored in the memory (130) or the server (108) to identify the subject of the first image (210). For example, the stored information is information retrieved from the memory (130) or the server (108) based on the metadata, and may include schedule information stored on the shooting date of the first image (210), an image (or video) stored together with the shooting date or time (or time range (e.g., within 1 hour)) of the first image (210), and an image (or video) stored together with the location of the first image (210). The processor (120) can identify the subject of the first image (210) based on the object, the metadata, and the stored information. The processor (120) can identify the subject of the first image (210) based on the context of the first image (210), the metadata, and the stored information. For example, the processor (120) can identify an atmosphere such as a wedding, joy, or cheering as the subject of the first image (210).

[0064] The processor (120) can determine (or identify) a first object that does not correspond to the identified subject among the plurality of objects. The first object may be one or more. For example, the processor (120) can determine a first person (201), a second person (203), a first object (205) (e.g., clothing), and a second object (207) (e.g., a bouquet) included in the first image (210) as the first object.

[0065] The processor (120) may generate a prompt (or instruction) based on the identified subject and the first object. The prompt may be intended to inform the generative AI of what the user wants to generate, and may represent information (or instructions) necessary to generate the object desired by the user. The more specific and clear the prompt is, the better the generative AI can understand the user's intention and generate the desired object. When there are multiple first objects, the processor (120) may generate a prompt for each object. The generative AI may be included in the electronic device (101) or may be included in an intelligent server (e.g., the server (108) of FIG. 1). When the generative AI is included in the electronic device (101), it may be included as a module (or software) in the processor (120) or may be included as a component different from the processor (120). When the above-mentioned generative AI is included in the server (108), the processor (120) can transmit (or transfer) the generated prompt to the server (108) through a communication module (e.g., the communication module (190) of FIG. 1).

[0066] According to one embodiment, if the first object is a person, the processor (120) may perform facial recognition on the person, search whether a person image matching the recognized face is stored in the memory or a server connected to the electronic device, identify a reference image having a facial expression corresponding to the identified subject based on the searched person image, and generate a prompt based on the image, the identified subject, and the identified reference image. That is, the processor (120) may include the image itself in the prompt and transmit it to the generative AI, and may also include coordinate information of an image region including a first object to be changed (or replaced) in the prompt and transmit it to the generative AI. Alternatively, the processor (120) may include only coordinate information of an area including a first object to be changed in the image, not the image itself, in the prompt and transmit it to the generative AI.

[0067] According to one embodiment, when a person image matching a person whose face is recognized as the first object is not searched, the processor (120) may extract coordinate information of an image area of ​​the first object included in the first image (210) and generate the prompt based on the image, the coordinate information of the extracted image area, and the identified subject. When the first object is an object, the processor (120) may perform object recognition on the object, extract coordinate information of an image area of ​​the first object included in the first image (210), and generate the prompt based on the image, the coordinate information of the extracted image area, the identified subject, and object recognition information for the object.

[0068] According to one embodiment, the processor (120) may generate a prompt based on coordinate information of the extracted image region, the identified subject, and the identified reference image. That is, the processor (120) may include coordinate information of an image region including a first object to be changed in the image (e.g., information of a masking region) in the prompt and transmit it to the generative AI instead of the image itself. For example, if there are multiple first objects included in the image, the processor (120) may extract coordinate information of multiple image regions for the multiple first objects, and generate a prompt based on the coordinate information of the multiple extracted image regions, the identified subject, and the identified reference image. If there are multiple first objects to be changed in the image, the processor (120) may include coordinate information of regions including the first objects in the prompt and transmit it to the generative AI. The generative AI may generate a second object to replace each first object.

[0069] FIG. 2b is a diagram illustrating an example of correcting an image to fit an image subject in an electronic device according to one embodiment.

[0070] Referring to FIG. 2B, the processor (120) may generate a second object to replace the first object based on the generated prompt. The second object is generated based on the first object, and may not mean a new object that is completely different from the first object, but may mean something that is identical to the first object (e.g., the same person, the same thing), but has been modified (or changed, processed) to fit the theme. When there are multiple first objects, the processor (120) may generate multiple second objects corresponding to each of the first objects at once (or simultaneously). When the generative AI is included in the server (108), the processor (120) may receive (or obtain) the second object generated based on the prompt from the server (108).

[0071] For example, if the first object is a first person (201), the second object of the first person (201) may represent a smiling facial expression of the first person (201) with joy. On the other hand, the first object of the first person (201) may represent a sad facial expression or a blank facial expression, rather than a smiling facial expression. The processor (120) may generate one or more second objects to replace the first object. Alternatively, if the first object is a first thing (205), the second object of the first thing (205) may be a shape or color of the first thing (205) that has been changed to something different. For example, the first object of the first thing (205) may be a bouquet of colorful flowers, and the second object of the first thing (205) may be a bouquet of white flowers.

[0072] The processor (120) can display the generated second object. When there are multiple first objects, if one first object is designated (or selected) by the user, the processor (120) can display multiple second objects corresponding to the designated first object. The processor (120) can display multiple objects and select any one second object from the multiple objects based on a user input. The processor (120) can select any one second object from the multiple objects for each first object. The processor (120) can generate a second image (230) reflecting the selected second object. The second image (230) can be an image in which the 2-1 object (231), the 2-2 object (233), the 2-3 object (235), and the 2-4 object (237) are changed (or activated).

[0073] The 2-1 object (231) may be the 1-1 object, which is the first person (201) of the 1st image (210), whose facial expression has been changed to fit the theme of the image (e.g., blank expression → smiling expression). The 2-2 object (233) may be the 1-2 object, which is the second person (203) of the 1st image (210), whose facial expression has been changed to fit the theme of the image (e.g., frowning expression → smiling expression). The 2-3 object (235) may be the 1-3 object, which is the first thing (205) of the 1st image (210), whose clothing color has been changed to fit the theme of the image (e.g., black → purple). The 2-4 object (237) may be the 1-4 object, which is the second thing (207) of the 1st image (210), whose bouquet color has been changed to fit the theme of the image (e.g., red → white).

[0074] The processor (120) can share the second image (230) based on a user's input. The user can share the second image (230) with people included in the second image (230). When a request for sharing is received from the user, the processor (120) can recognize the face of the person included in the second image (230), identify the contact information (e.g., phone number, messenger, email, etc.) of another user whose face has been recognized, and provide the identified contact information. The processor (120) can transmit the second image (230) to a contact selected by the user from among the provided contact information.

[0075] According to the present disclosure, the subject matter of an image can be emphasized and enhanced by changing objects in the image to suit the subject matter of the image.

[0076] According to an embodiment of the present disclosure, an electronic device (101) includes a display (160), a memory (130) storing instructions; and a processor (120), wherein the instructions, when executed by the processor, cause the electronic device to identify a plurality of objects included in an image displayed on the display, extract metadata of the image, identify a subject of the image based on the plurality of objects and the metadata, determine a first object among the plurality of objects that does not correspond to the identified subject, perform facial recognition on the subject when the first object is a person, search whether a person image matching the recognized face is stored in the memory or a server connected to the electronic device, identify a reference image having a facial expression corresponding to the identified subject based on the searched person image, generate a prompt based on the image, the identified subject, and the identified reference image, generate a second object to replace the first object based on the generated prompt, and display the generated second object.

[0077] The identified plurality of objects may include at least one of a person, an object, or a background, and the metadata of the image may include at least one of a creation date, a time, or a location of the image. The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to identify a context of the image based on the identified plurality of objects, identify stored information associated with the image in the memory based on the metadata of the image, and identify a subject of the image based on the context of the image, the metadata, or the stored information.

[0078] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to extract coordinate information of an image area of ​​a first object included in the image, and generate the prompt based on the image, the coordinate information of the extracted image area, the identified subject, and the identified reference image.

[0079] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to acquire various facial expressions of a person image based on a person image matching the person stored in the memory or the server, and to identify a person image having a facial expression corresponding to the identified subject among the acquired facial expressions as the reference image.

[0080] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to extract coordinate information of an image area of ​​the first object included in the image, if a person image matching the face-recognized person is not retrieved, and generate the prompt based on the image, the coordinate information of the extracted image area, and the identified subject.

[0081] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to analyze the first object to determine at least one of a gender, an age, or a country, if a person image matching the recognized face is not retrieved, obtain various facial expressions of the first object based on the gender, age, or country, and identify an image of the first object having a facial expression corresponding to the identified subject among the obtained facial expressions as the reference image.

[0082] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to perform object recognition on the object, if the first object is an object, extract coordinate information of an image area of ​​the first object included in the image, and generate the prompt based on the image, the coordinate information of the extracted image area, the identified subject, and the object recognition information for the object.

[0083] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to extract a coordinate area of ​​an image area of ​​a first object included in the image, and generate the prompt based on coordinate information of the extracted image area, the identified subject, and the identified reference image.

[0084] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to extract coordinate information of a plurality of image regions for a plurality of first objects included in the image, if there are a plurality of first objects included in the image, generate a prompt based on the extracted coordinate information of the plurality of image regions, the identified subject, and the identified reference image, and generate a plurality of second objects to replace each of the plurality of first objects based on the generated prompt.

[0085] The instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display a plurality of objects corresponding to a subject of the image, select a second object from among the displayed plurality of objects based on a user input, and reflect the selected second object in the image.

[0086] The above instructions, when individually or collectively executed by the at least one processor, may cause the electronic device to display a new image reflecting the selected second object and share the new image based on a user input.

[0087] Figure 3 is a flowchart (300) illustrating an operating method of an electronic device according to one embodiment.

[0088] Referring to FIG. 3, in operation 301, a processor (e.g., the processor 120 of FIG. 1) of an electronic device (e.g., the electronic device 101 of FIG. 1) according to an embodiment may identify an image subject from a displayed image. In the following description, the displayed image is used as an example, but the present invention may also be implemented for a video by utilizing a scene of the video as an image. The processor (120) may display an image on a display (e.g., the display module (160) of FIG. 1) and identify a subject of the displayed image. The displayed image may be an image stored in a memory (e.g., the memory (130) of FIG. 1) or a cloud server (e.g., the server (108) of FIG. 1) connected to (or registered with) the electronic device (101), or a preview image acquired (or captured) from a camera (e.g., the camera module (180) of FIG. 1).

[0089] The processor (120) can identify an object included in the displayed image, extract metadata of the displayed image, and identify a subject of the displayed image based on the object and the metadata. The object may include at least one of a person (or people), an animal, an object, or a background. The person may include a face. The object may include an animal. The object may be a clock, a desk, a tree, or a car. Alternatively, the object may include clothes worn by the person, the person's hair, or an item (e.g., an accessory, glasses) included in (or held by) the person. The background may be a mountain, an ocean, a sky, a sun, or a moon.

[0090] The metadata may include the date, time, or location at which the displayed image was created (or captured). Alternatively, the metadata may further include attribute information such as file format, size (or capacity), resolution, pixels, camera manufacturer, model, exposure time, ISO sensitivity, or whether the image is original. The processor (120) may identify the context of the first image (210) based on the metadata of the displayed image.

[0091] The subject indicates the mood of the displayed image and may be replaced with terms such as situation, context, culture, religion, and color. The processor (120) may further utilize information stored in the memory (130) or the server (108) to identify the subject of the displayed image. For example, the stored information may include information retrieved from the memory (130) or the server (108) based on the metadata, such as schedule information stored on the shooting date of the displayed image, an image (or video) stored together with the shooting date or time (or time range) of the displayed image, and an image (or video) stored together with the location of the displayed image. The processor (120) may identify the subject of the displayed image based on the object, the metadata, and the stored information. The processor (120) may identify the subject of the first image (210) based on the context of the displayed image, the metadata, and the stored information. For example, the subject of the image above may represent subjective elements from the user's perspective, such as a wedding, a happy day, a picnic, a gloomy day, or a sunny day.

[0092] In operation 303, the processor (120) may determine (or identify) a first object that does not correspond to the subject of the image. The first object may be one or more. For example, the processor (120) may determine one person and one animal as the first object from the displayed image. Alternatively, the processor (120) may determine one person and two objects as the first object from the displayed image.

[0093] In operation 305, the processor (120) may perform facial recognition on the person if the first object is a person. The processor (120) may perform facial recognition on the person if the object is a person through object recognition.

[0094] In operation 307, the processor (120) may search for a person image matching the face-recognized person. The person image may be matched with a contact, a photo, a video, or an image (or video) stored in the cloud as an acquaintance of the user of the electronic device (101). Alternatively, the processor (120) may search for a person image matching the face-recognized person in an SNS of another user registered to the user's SNS account. If the person image is searched for in the memory (130) or the server (108), the processor (120) may classify the person of the object as a relevant person. If the person image is not searched for in the memory (130) or the server (108), the processor (120) may classify the person of the object as an irrelevant person.

[0095] In operation 309, the processor (120) may identify a reference image having a facial expression corresponding to the identified subject based on the retrieved human image. According to one embodiment, the processor (120) may identify a reference image having a facial expression corresponding to the identified subject based on the retrieved human image. The reference image may be a basis when the generative AI generates a second object to replace the first object. For example, the facial expression included in the displayed image may be a neutral expression, while the facial expression of the reference image may be a smiling expression. The processor (120) may acquire (e.g., generate and acquire) various facial expressions of the human image based on a human image matching the human stored in the memory (130) or the server (108), and may identify a human image having a facial expression corresponding to the identified subject among the acquired facial expressions as the reference image. Acquiring the above-mentioned various facial expressions can be done by pre-creating templates of six facial expressions (e.g., joy, sadness, surprise, anger, disgust, fear), facial expressions with various emotions through the intensity of the expression (e.g., laughter, enjoyment, satisfaction, disappointment, depression, etc.), or combinations of similar facial expressions (e.g., fear + joy = desperate, fear + sadness = miserable).

[0096] When a person image matching the face-recognized person as the first object is not searched, the processor (120) can analyze the first object to determine at least one of gender, age, or country, and obtain various facial expressions of the first object based on the gender, age, or country. The processor (120) can obtain various facial expressions of the first object by matching the first object to a virtual person of the same or similar gender, age, or country. The processor (120) can identify an image of the first object having a facial expression corresponding to the identified subject among the obtained facial expressions as the reference image.

[0097] In operation 311, the processor (120) may generate a prompt based on the image, the identified subject, and the identified reference image. The prompt may be for informing the generative AI of what the user wants to generate, and may indicate information (or instructions) necessary for the user to generate the desired object. The processor (120) may include the image itself in the prompt and transmit it to the generative AI, and may also include coordinate information of an image region containing a first object to be changed in the image and transmit it to the generative AI. Alternatively, the processor (120) may include coordinate information of an image region containing a first object to be changed in the image (e.g., information on a masking region) in the prompt and transmit it to the generative AI instead of the image itself.

[0098] According to one embodiment, when a person image matching a person whose face is recognized as the first object is not searched, the processor (120) may extract coordinate information of an image area of ​​the first object included in the displayed image, and generate the prompt based on the image, the identified subject, and the coordinate information of the extracted image area. When the first object is an object, the processor (120) may perform object recognition on the object, extract coordinate information of an image area of ​​the first object included in the displayed image, and generate the prompt based on the identified subject, the object recognition information, and the coordinate information of the extracted image area.

[0099] According to one embodiment, if there are multiple first objects, the processor (120) may generate a prompt for each object. If there are multiple first objects included in the image, the processor (120) may extract coordinate information of multiple image areas for the multiple first objects, and generate a prompt based on the extracted coordinate information of the multiple image areas, the identified subject, and the identified reference image.

[0100] In operation 313, the processor (120) may generate a second object to replace the first object based on the generated prompt. The second object is generated based on the first object, and may not mean a new object that is completely different from the first object, but may mean something that is identical to the first object (e.g., the same person, the same object), but has been modified (or changed, processed) to fit the subject matter. When there are multiple first objects, the processor (120) may generate multiple second objects corresponding to each of the first objects at once (or simultaneously).

[0101] According to one embodiment, the generative AI may be included in the electronic device (101) or may be included in an intelligent server (e.g., the server (108) of FIG. 1). When the generative AI is included in the electronic device (101), it may be included in the processor (120) as a module (or software) or may be included as a component different from the processor (120). When the generative AI is included in the server (108), the processor (120) may transmit (or forward) the generated prompt to the server (108) via a communication module (e.g., the communication module (190) of FIG. 1).

[0102] In operation 315, the processor (120) may display the generated second object. If there are multiple first objects, when one first object is designated (or selected) by the user, the processor (120) may display multiple second objects corresponding to the designated first object. The processor (120) may display multiple objects and select any second object from the multiple objects based on a user input. The processor (120) may select any second object from the multiple objects to replace each first object based on the user input. The processor (120) may generate a new image reflecting the selected second object. If the subject of the image is a wedding, the second object may be a person whose facial expression is changed (e.g., from a blank expression to a smiling expression) to match the subject of the image.

[0103] The processor (120) can share the new image based on a user's input. The user can share the new image with the people included in the new image. When a sharing request is received from the user, the processor (120) can recognize the face of the person included in the new image, identify the contact information (e.g., phone number, messenger, email, etc.) of the other user whose face has been recognized, and provide the identified contact information. The processor (120) can transmit the new image to a contact selected by the user from among the provided contact information.

[0104] FIGS. 4A and 4B are diagrams illustrating an example of correcting a person in an image to match the subject of the image in an electronic device according to one embodiment.

[0105] Referring to FIG. 4A, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may display a first user interface (410) on a display (e.g., a display module (160) of FIG. 1). The first user interface (410) includes an image (401). The image (401) may be an image stored in a memory (e.g., a memory (130) of FIG. 1) or a cloud server (e.g., a server (108) of FIG. 1) connected to (or registered with) the electronic device (101), or a preview image acquired (or captured) from a camera (e.g., a camera module (180) of FIG. 1). The image (401) may include four people, two women wearing dresses with bouquets, and two men wearing suits.

[0106] The second user interface (420) may illustrate an example in which a user activates the generative AI function (421). The generative AI function (421) may analyze an image (401) and cause the generative AI to change (or transform, process) objects that do not fit the subject of the image. The subject represents the mood of the displayed image and may be replaced with terms such as situation, context, culture, religion, and color. The object may include at least one of a person (or person), an animal, an object, or a background. When the generative AI function (421) is activated, the processor (120) may analyze the image (401).

[0107] The processor (120) can identify a plurality of objects included in the image (401), extract metadata of the image (401), and identify a subject of the image (401) based on the plurality of objects and the metadata. If the identified plurality of objects are people, the processor (120) can perform facial recognition on the person, and search whether a person image matching the recognized person is stored in the memory (130) or the server (108). The metadata can include the date, time, or location when the image (401) was created (or photographed). The processor (120) can further utilize information stored in the memory (130) or the server (108) to identify the subject of the image (401). For example, the stored information may include information retrieved from the memory (130) or server (108) based on the metadata, such as schedule information stored on the shooting date of the displayed image, an image (or video) stored together with the shooting date or time (or time range) of the displayed image, and an image (or video) stored together at the same location as the location of the image (401). The processor (120) may identify the subject of the image (401) based on the plurality of objects, the metadata, and the stored information.

[0108] The third user interface (430) may indicate a first object that does not correspond to the identified subject. The processor (120) may determine (or identify) the first object that does not correspond to the identified subject. The first object may be one or more. For example, the third user interface (430) may include a first object area (e.g., a square area) and a guidance message (435) when the first object is a 'person' (437) (e.g., a face). The first object may include a first-first object (431) and a first-second object (433). The guidance message (435) may request a user confirmation to change the first object through a generative AI. When the first object area is touched by the user, the processor (120) may deactivate the display of the first object.

[0109] Referring to FIG. 4B, the fourth user interface (440) may include a second-second object (445) to replace the first-second object (443). The processor (120) may generate a prompt based on the image (401), the identified subject, and the identified reference image. That is, the processor (120) may include coordinate information of the image (401) itself and an image region including a first object to be changed within the image (401) in the prompt and transmit the prompt to the generative AI. Alternatively, the processor (120) may include only coordinate information of an image region including a first object to be changed (or replaced) within the image (401) (e.g., coordinate information of a masking region), but not the image (401) itself, in the prompt and transmit the prompt to the generative AI.

[0110] According to one embodiment, the processor (120) may identify a person image having a facial expression corresponding to the identified subject from among the databased facial expressions as a reference image. The databased facial expression may be a template created in advance of six facial expressions (e.g., joy, sadness, surprise, anger, disgust, fear), facial expressions having various emotions through the intensity of the expression (e.g., laughter, enjoyment, satisfaction, discouragement, depression, etc.), or combinations of similar facial expressions (e.g., fear + joy = desperate, fear + sadness = miserable). The reference image may be a basis when the generative AI generates the 2-2 object (445) corresponding to the 1-2 object (443). For example, the facial expression included in the image (401) may be a blank expression, while the facial expression of the reference image may be a smiling expression.

[0111] The processor (120) may generate a 2-2 object (445) corresponding to the 1-2 object (443) based on the generated prompt. The processor (120) may extract coordinate information of an image area of ​​the 1-2 object (443) included in the image (401), generate a prompt based on the image (401), the identified subject, and the identified reference image, and generate a 2-2 object (445) to replace the 1-2 object (443) based on the generated prompt. One or more 2-2 objects (445) may be generated.

[0112] If the subject of the image (401) is a wedding, the second-second object (445) may be a person whose facial expression has been changed to match the subject of the image (e.g., from a frowning expression to a smiling expression). If there are multiple second-second objects (445), they may be displayed in a list format, or additional second-second objects that are not displayed may be displayed based on user input (e.g., scrolling). The fourth user interface (440) may include a message (or pop-up) (447) requesting selection of any one second object among the plurality of second-second objects. The user may select any one second object through the message (447). When the user selects (e.g., focuses on) the second object and then selects an application menu (or button, item) of the message (447), the processor (120) may generate a new image reflecting the selected second object. When the new image is generated, the processor (120) may store the new image in the memory (130).

[0113] The fifth user interface (450) may include a new image (451) and a sharing guidance message (453). The processor (120) may store the new image (451) in the memory (130) based on a user input (e.g., a save request). The user may check the new image (451) and share the new image (451) with a person included in the new image (451). For example, when the processor (120) receives a user selection of a sharing menu (or button, item) in the sharing guidance message (453), the processor (120) may recognize the face of the person included in the new image (451), identify the contact information (e.g., phone number, messenger, email, etc.) of another user whose face has been recognized, and provide the identified contact information. The processor (120) may transmit the new image (451) to a contact selected by the user from among the provided contact information.

[0114] The sixth user interface (460) may include a second-first object (463) for replacing the first-first object (461) according to a user's request for additional editing. The processor (120) may generate a prompt based on the image (401), the identified subject matter, and the reference image identified in correspondence with the first-first object (461). The processor (120) may generate the second-first object (463) for replacing the first-first object (461) based on the generated prompt. The processor (120) may extract coordinate information of an image area of ​​the first-first object (461) included in the image (401), generate a prompt based on the image (401), the identified subject matter, and the identified reference image, and generate the second-first object (463) for replacing the first-first object (461) based on the generated prompt. There may be one or more second-first objects (463). When a user selects a second object (e.g., focuses on it) and then selects an application menu, the processor (120) can generate a new image reflecting the selected second object.

[0115] When there are multiple first objects, the processor (120) can create multiple objects for each first object and select one second object from among the multiple objects created based on user input.

[0116] FIGS. 5A and 5B are diagrams illustrating an example of correcting an object in an image to match the image subject in an electronic device according to one embodiment.

[0117] Referring to FIG. 5A, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may display a first user interface (510) on a display (e.g., a display module (160) of FIG. 1). The first user interface (510) illustrates an example of activating a generative AI function (421) when an object is a 'thing' (e.g., an item). The first user interface (510) may include an image (501) and a generative AI activation guidance message (513). The image (501) may include four people, two women wearing dresses with bouquets, and two men wearing suits.

[0118] When the generative AI function (421) is activated, the processor (120) can analyze the image (501). The processor (120) can identify a plurality of objects included in the image (501), extract metadata of the image (501), and identify a subject of the image (501) based on the plurality of objects and the metadata. The second user interface (520) may indicate a first object that does not match the identified subject. The processor (120) may determine (or identify) the first object that does not correspond to the identified subject. The first object may be one or multiple. For example, the second user interface (520) may include a first object area and a guidance message (525) when the first object is an 'object' (511) (e.g., an item). The first object may include a first-first object (521) and a first-second object (523). The first object (521) may be a bouquet, and the first object (523) may be clothing (e.g., a dress). The guidance message (525) may request the user to confirm whether to change the first object through the generative AI.

[0119] The third user interface (530) may include a second object and a storage guidance message (535). The second object may include a second-first object (531) generated to replace the first-first object (521) and a second-second object (533) generated to replace the first-second object (523). When the first object is an object, the processor (120) may perform object recognition on the object, extract coordinate information of an image area of ​​the first object included in the image (501), and generate a prompt based on the image (501), the identified subject, the object recognition information, and the extracted coordinate information of the image area. The processor (120) may include the image (501) itself in the prompt and transmit it to the generative AI, and may also include coordinate information of an image area of ​​the first-first object (521) to be changed in the image (501) in the prompt. Alternatively, the processor (120) may include coordinate information of an image area of ​​the first-1 object (521) to be changed within the image (501) in the prompt (e.g., information of a masking area) instead of the image (501) itself.

[0120] The processor (120) can extract coordinate information of an image area of ​​a 1-1 object (521) included in an image (501), generate a prompt based on the image (501), the identified subject, the object recognition information, and the coordinate information of the image area of ​​the 1-1 object (521), and generate a 2-1 object (531) to replace the 1-1 object (521) based on the generated prompt. The processor (120) can extract coordinate information of an image area of ​​a 1-2 object (523) included in an image (501), generate a prompt based on the image (501), the identified subject, the object recognition information, and the coordinate information of the image area of ​​the 1-2 object (523), and generate a 2-2 object (533) to replace the 1-2 object (523) based on the generated prompt. When the processor (120) selects the save menu through the save guidance message (535), it can save a new image in which the 2-1 object (531) and the 2-2 object (533) are reflected in the image (501).

[0121] Referring to FIG. 5B, the processor (120) may receive from the user a selection of a portion to be further modified. The fourth user interface (540) may be an example of additional editing for the 2-1 object (541). When the 2-1 object (541) is selected by the user, the 4th user interface (540) may include another object (545) corresponding to the 2-1 object (541) and an application guidance message (543). The other object (545) may be a bouquet having a different shape or color than the 2-1 object (541). The user may select one of the other objects (545) and select (e.g., touch) an application menu. When the application menu is selected, the processor (120) may generate a new image (553) reflecting the selected other object (545).

[0122] The fifth user interface (550) may include a new image (553) and a sharing guide message (551). The user may check the new image (553) and share the new image (553) with a person included in the new image (553). For example, when the processor (120) receives a user's selection of a sharing menu (or button, item) in the sharing guide message (551), the processor (120) may recognize the face of the person included in the new image (553), identify the contact information (e.g., phone number, messenger, email, etc.) of another user whose face has been recognized, and provide the identified contact information. The processor (120) may transmit the new image (553) to a contact selected by the user from among the provided contact information.

[0123] FIG. 6 is a flowchart (600) illustrating a method for identifying an image subject of an electronic device according to one embodiment. FIG. 6 may be a specific embodiment of operation 301 of FIG. 3.

[0124] Referring to FIG. 6, in operation 601, a processor (e.g., the processor 120 of FIG. 1) of an electronic device (e.g., the electronic device 101 of FIG. 1) according to an embodiment may identify a context of an object-based image. The processor (120) may identify an object included in the image. The identified object may be one or more. The object may include at least one of a person (or people), an animal, an object, or a background. The person may include a face. The object may include an animal. The object may be a clock, a desk, a tree, or a car. Alternatively, the object may include clothes worn by the person, the person's hair, or an item (e.g., an accessory, glasses) included in (or held by) the person. The background may be a mountain, an ocean, a sky, a sun, or a moon.

[0125] If the identified object is a person, the processor (120) may perform facial recognition on the person and search whether a person image matching the recognized person is stored in a memory (e.g., memory (130) of FIG. 1) or a cloud server (e.g., server (108) of FIG. 1) connected to (or registered with) the electronic device (101). If the person image is searched for in the memory (130) or server (108), the processor (120) may classify the person of the object as a relevant person. If the person image is not searched for in the memory (130) or server (108), the processor (120) may classify the person of the object as an irrelevant person.

[0126] In operation 603, the processor (120) may identify the context of the background-based image. If the background is included in the object, operation 603 may be omitted. The processor (120) may identify the context of the image by identifying whether the background of the image is daytime or nighttime. Alternatively, the processor (120) may identify the context of the image by identifying whether the background of the image is a tree or a building.

[0127] In operation 605, the processor (120) may extract metadata from the image. The metadata may include the date, time, or location at which the displayed image was created (or photographed). Alternatively, the metadata may further include attribute information such as file format, size (or capacity), resolution, pixels, camera manufacturer, model, exposure time, ISO sensitivity, or whether the image is original. The processor (120) may identify the context of the image based on the metadata of the image.

[0128] In operation 607, the processor (120) may identify the context of the image based on the stored information. For example, the stored information may include information retrieved from the memory (130) or the server (108) based on the metadata, such as schedule information stored on the shooting date of the image, an image (or video) stored together with the shooting date or time (or time range) of the image, or an image (or video) stored together with the location of the image.

[0129] In operation 609, the processor (120) may determine an image theme based on the context and metadata. The image theme represents the mood of the image and may be replaced with terms such as situation, context, culture, religion, and color. For example, the image theme may represent subjective elements from a user's perspective, such as a wedding, a happy day, a picnic, a gloomy day, or a sunny day.

[0130] FIG. 7A is a diagram illustrating an example of identifying an object included in an image in an electronic device according to one embodiment.

[0131] Referring to FIG. 7A, a processor (e.g., processor (120) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1) according to an embodiment can identify an object from an image (710). The identified object may be one or more. The image (710) may be displayed on a display (e.g., display module (160) of FIG. 1). For example, the image (710) may be an image stored in a memory (e.g., memory (130) of FIG. 1) or a cloud server (e.g., server (108) of FIG. 1) connected to (or registered with) the electronic device (101), or a preview image acquired (or captured) from a camera (e.g., camera module (180) of FIG. 1).

[0132] The object may include at least one of a person (or a person), an animal, an object, or a background. The person may include a face. The object may include an animal. The object may be a clock, a desk, a tree, or a car. Alternatively, the object may include clothes worn by the person, hair of the person, or items included (or held) by the person (e.g., accessories, glasses). The background may be a mountain, an ocean, a sky, a sun, or a moon. For example, the processor (120) may identify eight people (701) (e.g., circles), clothes worn by each person (711) (e.g., squares), and items held by each person (721) (e.g., triangles) as objects from the image (710).

[0133] For example, the processor (120) can determine that a total of eight people, four men and four women, are recognized as faces in the image (710), all of the women are smiling with their eyes, and three women except one are smiling with their mouth corners raised and their teeth visible. In addition, the processor (120) can determine that three men are smiling with their eyes and teeth visible, and one man is smiling with his eyes and teeth not visible (e.g., crying). The processor (120) can determine that the subject of the photo is primarily expressing joy because seven out of eight people are smiling.

[0134] The processor (120) can identify four male figures in the image (710) as wearing four identical suits, three female figures as wearing identical dresses, one central female figure as wearing a white dress, three female figures holding three identical flowers (e.g., a bouquet), and one female figure holding a different flower. In addition, the processor (120) can identify trees behind the figures in the image (710) and can identify that the image (710) was taken during the day through the white color visible as the sky between the trees. In American culture, a white dress is identified as a bride getting married on the same day, so the processor (120) can recognize one central female figure as the main character. The processor (120) can confirm that the shooting date of the image (710) is registered as a wedding in the schedule information registered in the calendar application, determine that the image (710) is a wedding photo, and determine weather information based on the time and location of the shooting date. The processor (120) can determine the secondary image theme as a daytime wedding photo, as it shows four pairs of men and women wearing the same suit and dress, each of the women holding a flower, and the central female figure wearing a white dress.

[0135] FIG. 7b is a diagram illustrating an example of identifying metadata and user input information of an image in an electronic device according to one embodiment.

[0136] Referring to FIG. 7B, the processor (120) may extract metadata (750) from the image (710). The metadata may include the date and time information (751) when the image (710) was created (or photographed) and location information (753). Alternatively, the metadata may further include attribute information such as file format, size (or capacity), resolution, pixels, camera manufacturer, model, exposure time, ISO sensitivity, or whether it is original. The processor (120) may extract storage information associated with the image (710) based on the metadata (750). The storage information may be information stored in the memory (130) or the server (108), and may be, for example, schedule information (760). The schedule information (760) may be a user's schedule (e.g., Emma's wedding (Paju)) registered on the same date or time as the date and time information (751) in a calendar application.

[0137] In this way, the processor (120) can identify the subject of the image (710) based on the objects (e.g., person (701), clothing (711), item (721)), metadata (750), and schedule information (760). The processor (120) can identify the tertiary image subject that the image (710) was taken at a wedding by identifying that the shooting time of the image (710) matches the schedule information (760) identified in the calendar application. The processor (120) can determine the subject of the image (710) as “joy” celebrating a wedding.

[0138] FIG. 8 is a flowchart (800) illustrating an image correction method corresponding to an image subject in an electronic device according to one embodiment.

[0139] Referring to FIG. 8, in operation 801, a processor (e.g., the processor (120) of FIG. 1) of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may determine whether an object (e.g., a first object (e.g., a first person (201), a second person (203), a first thing (205), or a second thing (207) of FIG. 2A)) is a person. The processor (120) may identify an object from an image displayed on a display (e.g., a display module (160) of FIG. 1), extract metadata of the displayed image, and identify a subject of the displayed image based on the object and the metadata. The object may be one or more. The object may include at least one of a person (or a person), an animal, an object, or a background. The metadata may include a date, time, or location at which the displayed image was generated (or photographed). The subject represents the mood of the displayed image, and may include a situation, a context, a culture, It may be replaced with terms such as religion and color. The processor (120) may determine whether an object (e.g., the first object) among multiple objects included in the image that does not correspond to the identified subject is a person.

[0140] The processor (120) can determine whether the object is a person. If the object is a person, the processor (120) can perform operation 803, and if the object is not a person, the processor (120) can perform operation 802. In the drawing, the operation of determining whether the object is a person is performed first, but if the object is not an object (e.g., if it is a person), operation 803 can also be performed depending on whether the object is an object or not.

[0141] If the object is not a person (e.g., an object), in operation 802, the processor (120) may extract an item (or object) reference image from the image. If the object is an object, the processor (120) may perform object recognition on the object to determine what the object is. The processor (120) may extract an area including the object recognized as the object reference image from the image. After extracting the item reference image, the processor (120) may perform operation 807.

[0142] If the object is a person, in operation 803, the processor (120) can determine whether the object is a person related to the user. If the object is a person, the processor (120) can perform facial recognition on the person and search whether a person image matching the recognized person is stored in a memory (e.g., memory (130) of FIG. 1) or a cloud server (e.g., server (108) of FIG. 1) connected to (or registered with) the electronic device (101). The person image may be an acquaintance of the user of the electronic device (101), and may be matched with a contact, a photo, a video, or an image (or video) stored in the cloud. If the person image is searched for in the memory (130) or the server (108), the processor (120) can classify the person of the object as a person related to the user of the electronic device (101). If the person image is not retrieved from the memory (130) or server (108), the processor (120) may classify the person of the object as an unrelated person. If the person is a user-related person, the processor (120) may perform operation 805, and if the person is not a user-related person (e.g., an unrelated person), the processor (120) may perform operation 804.

[0143] If the person is not a user-related person, in operation 804, the processor (120) may extract a person reference image from the image. The processor (120) may extract an area including the recognized person from the image as a person reference image. Alternatively, the processor (120) may analyze the person to determine at least one of gender, age, or country, and generate or obtain various facial expressions of the first object based on the gender, age, or country. The processor (120) may match the first object to a virtual person having the same or similar gender, age, or country to generate or obtain various facial expressions of the first object. The processor (120) may identify an image of the first object having a facial expression corresponding to the identified subject among the acquired facial expressions as the reference image. After extracting the person reference image, the processor (120) may perform operation 807.

[0144] In the case of a user-related person, in operation 805, the processor (120) may determine a person reference image from an expression database. The expression database may store person images having various facial expressions of the person images based on person images matching the person stored in the memory (130) or the server (108). The processor (120) may identify a person image having a facial expression corresponding to the identified subject among the facial expressions stored in the expression database as the person reference image. The expression database may store person images corresponding to six facial expressions (e.g., joy, sadness, surprise, anger, disgust, fear). Alternatively, the expression database may store person images corresponding to facial expressions having various emotions through the intensity of the expression (e.g., laughter, enjoyment, satisfaction, dejection, depression, etc.). Alternatively, the expression database may include a template that pre-creates combinations of similar facial expressions (e.g., fear + joy = desperate, fear + sadness = miserable).

[0145] In operation 807, the processor (120) may designate a masking area including an object. The masking area may be an area that includes only the object to be changed within the image. If the reference image is extracted from the image (e.g., operation 802), operation 807 may be omitted.

[0146] In operation 809, the processor (120) may generate a prompt corresponding to the image subject. The processor (120) may generate the prompt based on the image, the image subject, the masking area, and the reference image. The processor (120) may include coordinate information of an image area of ​​an object to be changed within the image (e.g., information of a masking area) rather than the image itself in the prompt. If there are multiple objects, the processor (120) may generate a prompt for each object. If the first object is an object, the processor (120) may generate the prompt based on the image subject, the object recognition information, the masking area, and the extracted item reference image.

[0147] In operation 811, the processor (120) may generate an object (e.g., a second object) corresponding to a subject (e.g., an image subject) based on a reference image, a masking area, and a prompt. The processor (120) may generate an object (hereinafter, referred to as a “second object”) corresponding to the image subject through generative AI. The second object is generated based on the object (e.g., the first object), and does not mean generating a new object that is completely different from the first object, but may mean that the second object is the same as the first object (e.g., the same person, the same object), but is modified (or changed, processed) to fit the subject. When there are multiple first objects, the processor (120) may generate each second object at once (or simultaneously) to replace each first object.

[0148] In operation 813, the processor (120) may display the generated object (e.g., the second object). If there are multiple first objects, and one first object is designated (or selected) by the user, the processor (120) may display multiple second objects to replace the designated first object.

[0149] In operation 815, the processor (120) may reflect an object generated based on a user input in an image. The processor (120) may display a plurality of objects and select a second object from among the plurality of objects based on a user input. The processor (120) may select a second object from among the plurality of objects for each first object based on the user input. For example, the processor (120) may generate a second-first object, a second-second object, and a second-third object as objects to replace the first-first object, and may generate a second-fourth object, a second-fifth object, a second-sixth object, and a second-seventh object as objects to replace the first-second object. The processor (120) may generate a new image reflecting the selected second object. The processor (120) may store the new image in the memory (130) based on the user input or share the new image with other users.

[0150] FIG. 9A and FIG. 9B are diagrams illustrating an example of databaseizing a person's facial expression in an electronic device according to one embodiment.

[0151] Referring to FIG. 9A, an example of a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment of the present invention stores (or acquires) various facial expressions of a first person (e.g., a woman) as a user-related person in a database. For example, a first facial expression database (910) related to the first person may store person images related to various facial expressions such as good (901), surprise (903), anger (903), or annoyance (904). The processor (120) may generate various facial expressions of the first person and store the generated facial expressions in the first facial expression database (910).

[0152] Referring to FIG. 9B, the processor (120) illustrates an example of database-building (or acquiring) various facial expressions of a second person (e.g., a male) as a user-related person. For example, the second facial expression database (920) related to the second person may store images of the person associated with various facial expressions, such as joy (921), ecstasy (922), sadness (923), or sorrow (924). The processor (120) may generate various facial expressions of the second person and store the generated facial expressions in the second facial expression database (910).

[0153] FIG. 9c is a diagram illustrating an example of searching for a stored human image in an electronic device according to one embodiment.

[0154] Referring to FIG. 9c, if an object that does not match the image subject is a relevant person (930), the processor (120) may search for a person image stored in a memory (e.g., memory (130) of FIG. 1) or a cloud server (e.g., server (108) of FIG. 1) connected to (or registered with) the electronic device (101). Alternatively, if an object that does not match the image subject is an unrelated person (940), the processor (120) may match the person to a virtual person of the same or similar gender, age, or country.

[0155] FIG. 9d is a diagram illustrating an example of generating an object that does not correspond to the subject of an image in an electronic device according to one embodiment.

[0156] Referring to FIG. 9D , the processor (120) may generate a new image (980) based on a prompt (950), a reference image (960), and a second object (970) corresponding to an image theme (e.g., joy). The reference image (960) may be for generating a second object (970) for a person. The first reference image (961) may be a reference image for a first person included in the image, and the second reference image (963) may be a reference image for a second person (e.g., different from the first person) included in the image. When there are multiple first objects that do not match the image theme, the processor (120) may identify reference images for each object. The processor (120) may generate a second-first object (971) based on the prompt (950) and the first reference image (961). The processor (120) can generate a second-second object (973) based on the prompt (950) and the second reference image (963). The processor (120) can generate a first new image (981) reflecting the second-first object (971) based on the user input. The processor (120) can generate a second new image (983) reflecting the second-second object (973) based on the user input.

[0157] FIG. 10 is a diagram illustrating an example of analyzing and database-izing a person who was not searched for in an electronic device according to one embodiment.

[0158] Referring to FIG. 10, a processor (e.g., a processor (120) of FIG. 1) of an electronic device (e.g., an electronic device (101) of FIG. 1) according to an embodiment may provide a first user interface (1010) when a person that does not match the image subject is an irrelevant person. When the identified object is a person, the processor (120) may perform facial recognition on the person and search whether a person image matching the recognized person is stored in the memory (130) or the server (108). When the person image is not searched in the memory (130) or the server (108), the processor (120) may classify the person of the object as an irrelevant person.

[0159] The first user interface (1010) may be an example for receiving input from a user for the name, gender, age, or country of an unrelated person. The second user interface (1030) may be an example for receiving input for the gender of an unrelated person. The third user interface (1050) may be an example for receiving additional input for information about an unrelated person.

[0160] According to an embodiment of the present disclosure, an operating method of an electronic device (101) may include an operation of identifying a plurality of objects included in an image displayed on a display of the electronic device, an operation of extracting metadata of the image, an operation of identifying a subject of the image based on the plurality of objects and the metadata, an operation of determining a first object that does not correspond to the identified subject among the plurality of objects, an operation of performing facial recognition on the subject when the first object is a person, an operation of searching whether a person image matching the recognized face of the person is stored in the memory or a server connected to the electronic device, an operation of identifying a reference image having a facial expression corresponding to the identified subject based on the searched person image, an operation of generating a prompt based on the image, the identified subject, and the identified reference image, an operation of generating a second object for replacing the first object based on the generated prompt, and an operation of displaying the generated second object.

[0161] The identified object may include at least one of a person, an object, or a background, and the metadata of the image may include at least one of a creation date, a time, or a location of the image, and the act of identifying the subject may include an act of identifying a context of the image based on the plurality of identified objects, an act of identifying stored information associated with the image in the memory based on the metadata of the image, and an act of identifying a subject of the image based on the context of the image, the metadata, or the stored information.

[0162] The operation of generating the prompt may include extracting coordinate information of an image area of ​​a first object included in the image, and generating the prompt based on the image, the coordinate information of the extracted image area, the identified subject, and the identified reference image.

[0163] The operation of identifying the reference image may include an operation of obtaining various facial expressions of the person image based on a person image matching the person stored in the memory or the server, and an operation of identifying a person image having a facial expression corresponding to the identified subject among the obtained facial expressions as the reference image.

[0164] The operation of generating the above prompt may further include an operation of extracting coordinate information of an image area of ​​the first object included in the image when a person image matching the face-recognized person is not searched, and an operation of generating the prompt based on the image, the coordinate information of the extracted image area, and the identified subject.

[0165] The operation of identifying the reference image may include, when a person image matching the face-recognized person is not searched, an operation of analyzing the first object to determine at least one of gender, age, or country, an operation of obtaining various facial expressions of the first object based on the gender, age, or country, and an operation of identifying an image of the first object having a facial expression corresponding to the identified subject among the obtained facial expressions as the reference image.

[0166] The action of generating the prompt may include, if the first object is an object, performing object recognition on the object, extracting coordinate information of an image area of ​​the first object included in the image, and generating the prompt based on the image, corresponding coordinate information of the extracted image area, the identified subject, and object recognition information on the object.

[0167] The operation of generating the above prompt may include, when there are multiple first objects included in the image, an operation of extracting coordinate information of multiple image areas for the multiple first objects, and an operation of generating a prompt based on the extracted coordinate information of the multiple image areas, the identified subject, and the identified reference image.

[0168] The method may further include an action of displaying a plurality of objects corresponding to the identified subject, an action of selecting a second object from among the displayed plurality of objects based on a user input, an action of displaying a new image reflecting the selected second object in the image, and an action of sharing the new image based on the user input.

[0169] The various embodiments of the present invention disclosed in this specification and drawings are merely specific examples presented to facilitate easy explanation of the technical content of the present invention and aid understanding thereof, and are not intended to limit the scope of the present invention. Therefore, the scope of the present invention should be interpreted to include all modifications or variations derived based on the technical concept of the present invention, in addition to the embodiments disclosed herein.

Claims

1. In an electronic device (101), Display (160), Memory (130) for storing instructions; and An electronic device comprising at least one processor (120), wherein the instructions, when individually or collectively executed by the processor, Identifying multiple objects included in the image displayed on the above display, Extract the metadata of the above image, Identifying the subject of the image based on the plurality of objects and the metadata, Determine a first object among the plurality of objects that does not correspond to the identified subject, If the first object above is a person, face recognition is performed on the person, Searching for a person image matching the above-mentioned recognized person stored in the memory or a server connected to the electronic device, Identifying a reference image having a facial expression corresponding to the identified subject based on the retrieved human image, Generate a prompt based on the image, the identified subject, and the identified reference image; Create a second object to replace the first object based on the generated prompt, An electronic device that displays the second object generated above.

2. In paragraph 1, The above identified plurality of objects include at least one of a person, an object, or a background, The metadata of the image includes at least one of the creation date, time, or location of the image, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Identifying the context of the image based on the identified plurality of objects, Identifying storage information associated with the image in the memory based on metadata of the image; An electronic device that identifies a subject of an image based on the context of the image, the metadata or the stored information.

3. In the first paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, Extract coordinate information of the image area of ​​the first object included in the above image, An electronic device that generates a prompt based on the image, coordinate information of the extracted image area, the identified subject, and the identified reference image.

4. In the first paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, Obtaining various facial expressions of the person image based on a person image matching the person stored in the memory or the server, An electronic device that identifies a person image having a facial expression corresponding to the identified subject among the acquired facial expressions as the reference image.

5. In the first paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, If a person image matching the above-mentioned face-recognized person is not found, the coordinate information of the image area of ​​the first object included in the image is extracted, An electronic device that generates the prompt based on the image, coordinate information of the extracted image area, and the identified subject.

6. In the fifth paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, If a person image matching the above-mentioned facially recognized person is not found, the first object is analyzed to determine at least one of gender, age, or country, Obtaining various facial expressions of the first object based on the gender, age or country, An electronic device that identifies an image of the first object having a facial expression corresponding to the identified image subject among the acquired facial expressions as the reference image.

7. In the first paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, If the first object is an object, object recognition is performed on the object, Extracting coordinate information of the image area of ​​the first object included in the image, An electronic device that generates the prompt based on the image, coordinate information of the extracted image area, the identified subject, and object recognition information for the object.

8. In the first paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, Extract coordinate information of the image area of ​​the first object included in the above image, An electronic device that generates a prompt based on coordinate information of the extracted image area, the identified subject, and the identified reference image.

9. In the first paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, If there are multiple first objects included in the image, extract coordinate information of multiple image areas for the multiple first objects, Generate a prompt based on coordinate information of the extracted plurality of image areas, the identified subject, and the identified reference image, An electronic device that generates each of the plurality of second objects to replace each of the plurality of first objects based on the generated prompt.

10. In the first paragraph, when the instructions are individually or collectively executed by the at least one processor, the electronic device, Display multiple objects corresponding to the subject of the above image, Selecting the second object based on user input from among the plurality of objects displayed above, An electronic device that reflects the selected second object in the image.

11. In the 10th paragraph, when the instructions are individually and collectively executed by the at least one processor, the electronic device, Display a new image reflecting the second object selected above, An electronic device that enables sharing of said new image based on user input.

12. In the operating method of the electronic device (101), An operation of identifying a plurality of objects included in an image displayed on a display of the electronic device; An action to extract metadata of the above image; An operation of identifying a subject of the image based on the plurality of objects and the metadata; An operation of determining a first object among the plurality of objects that does not correspond to the identified image subject; If the first object is a person, an action of performing facial recognition on the person; An action of searching whether a person image matching the above-mentioned recognized person is stored in the memory or a server connected to the electronic device; An action of identifying a reference image having a facial expression corresponding to the identified subject based on the retrieved human image; An action to generate a prompt based on the image, the identified subject, and the identified reference image; An operation of generating a second object to replace the first object based on the generated prompt; and A method comprising an action of displaying the second object generated above.

13. In paragraph 12, The identified object includes at least one of a person, an object, or a background, The metadata of the image includes at least one of the creation date, time, or location of the image, The action of identifying the above subject is, An operation of identifying the context of the image based on the identified plurality of objects; An operation of identifying storage information associated with the image in the memory based on metadata of the image; and A method comprising an action of identifying a subject of the image based on the context of the image, the metadata or the stored information.

14. In paragraph 12, the action of generating the prompt is: An operation of extracting coordinate information of an image area of ​​a first object included in the image; and A method comprising generating a prompt based on the image, coordinate information of the extracted image area, the identified subject, and the identified reference image.

15. In paragraph 14, the operation of identifying the reference image comprises: An operation of acquiring various facial expressions of the person image based on a person image matching the person stored in the memory or the server; and A method including an action of identifying a person image having a facial expression corresponding to the identified subject among the acquired facial expressions as the reference image.

Images