Electronic device and method for editing face included in image by using artificial intelligence model in electronic device

Abstract

An electronic device according to an embodiment may comprise a communication circuit, a display, at least one processor, and a memory for storing instructions, wherein the instructions, when executed individually or collectively by the at least one processor, cause the electronic device to: when editing of a face included in a first image is identified, transmit editing information including first information about the face included in the first image to an artificial intelligence model, the first information being obtained by learning a feature of the face selected by the editing; when a second image obtained by editing the face included in the first image by using the editing information is received from the artificial intelligence model, obtain a score related to similarity between an edited face included in the second image and the face included in the first image; and when the obtained score is greater than or equal to a threshold value, store the second image. In addition, other embodiments may be included.

Description

A method for editing faces contained in images using artificial intelligence models in electronic devices and electronic devices.

[0001] The present disclosure relates to an electronic device and a method for editing a face included in an image using an artificial intelligence model in the electronic device.

[0002] Recently, technology to generate images using artificial intelligence models is being actively developed, and in particular, new images are being created by editing specific areas of the image.

[0003] When using AI models to edit faces in images, the edited faces can become completely different. However, using AI models to edit faces in images is not recommended, and is often prohibited, especially since it allows for the editing of other people's faces without their consent.

[0004] Using an artificial intelligence model, only authenticated faces can be edited, and images containing the edited face can be provided only if the edited face is similar to the authenticated face.

[0005] An electronic device according to an embodiment may include a communication circuit, a display, at least one processor, and a memory storing instructions. The instructions according to an embodiment may be configured to, when individually or collectively executed by the at least one processor, cause the electronic device to, when confirming editing of a face included in a first image, transmit edit information including first information about the face included in the first image to an artificial intelligence model, and acquire the first information by learning features of the face selected through the editing. The instructions according to an embodiment may be configured to, when individually or collectively executed by the at least one processor, cause the electronic device to, when receiving a second image obtained by editing a face included in the first image using the edit information from the artificial intelligence model, acquire a score related to similarity between an edited face included in the second image and the face included in the first image. The instructions according to one embodiment, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to store the second image if the acquired score is greater than or equal to a threshold value.

[0006] In one embodiment, a method for editing a face included in an image using an artificial intelligence model in an electronic device may include, when confirming editing of a face included in a first image, transmitting edit information including first information about the face included in the first image to an artificial intelligence model, and obtaining the first information by learning features of the face selected through the editing. In one embodiment, the method may include, when receiving a second image obtained by editing the face included in the first image using the edit information from the artificial intelligence model, obtaining a score related to similarity between the edited face included in the second image and the face included in the first image. In one embodiment, the method may include, when the obtained score is equal to or greater than a threshold value, storing the second image.

[0007] In one embodiment, a non-volatile storage medium storing commands is provided, wherein the commands are configured to cause the electronic device to perform at least one operation when executed by the electronic device, wherein the at least one operation may include: upon confirming editing of a face included in a first image, transmitting edit information including first information about the face included in the first image to an artificial intelligence model, wherein the first information is acquired by learning a feature of the face selected through the editing. In one embodiment, the at least one operation may include: upon receiving a second image obtained by editing the face included in the first image using the edit information from the artificial intelligence model, acquiring a score related to similarity between the edited face included in the second image and the face included in the first image. In one embodiment, the at least one operation may include: when the acquired score is equal to or greater than a threshold value, storing the second image.

[0008] The above and other aspects, features and advantages of specific embodiments of the present disclosure will become more apparent from the following description taken in conjunction with the accompanying drawings:

[0009] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment.

[0010] FIG. 2A is a block diagram of an electronic device according to one embodiment.

[0011] FIG. 2b is a block diagram illustrating the configuration of a processor and an artificial intelligence model according to one embodiment.

[0012] FIG. 3a, FIG. 3b, FIG. 3c, FIG. 3d, and FIG. 3e are drawings for explaining an operation of generating first information in an artificial intelligence model.

[0013] Figures 4a and 4b are drawings for explaining the operation of generating an image with an edited face in an artificial intelligence model.

[0014] FIG. 5 is a diagram illustrating an operation for checking similarity in an image in which a face has been edited in an electronic device according to one embodiment.

[0015] FIGS. 6A, 6B, 6C, and 6D are drawings for explaining an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0016] FIGS. 7A, 7B, and 7C are drawings for explaining an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0017] FIG. 8A is a diagram illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0018] FIG. 8b is a diagram illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0019] FIG. 9 is a flowchart illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0020] FIG. 10 is a flowchart illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0021] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to an embodiment. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the server (108) via a second network (199) (e.g., a long-range wireless communication network). According to an 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)).

[0022] 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 operation, the processor (120) may store a command or data received from another component (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the command or data stored in the volatile memory (132), and store the resulting 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.

[0023] The auxiliary processor (123) may control at least a part 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 device) 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.

[0024] 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).

[0025] 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).

[0026] 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).

[0027] 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. According to one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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)). According to 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.

[0032] 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).

[0033] A 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) may include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0034] 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.

[0035] 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).

[0036] 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.

[0037] 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).

[0038] 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) may 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) each, or 1 ms or less for round trip) for URLLC realization.

[0039] 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 selected at least one 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).

[0040] According to one embodiment, the antenna module (197) may form a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to 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 to 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.

[0041] 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)).

[0042] 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.

[0043] FIG. 2a is a block diagram of an electronic device according to one embodiment, and FIG. 2b is a block diagram for explaining the configuration of a processor and an artificial intelligence model according to one embodiment.

[0044] Referring to the above FIGS. 2A and 2B, the electronic device (201) may include a processor (220), a memory (230), a display (260), and a communication circuit (290). The electronic device (201) may correspond to the electronic device (101) (FIG. 1).

[0045] According to one embodiment, the processor (220) may perform overall control operations of the electronic device (201). The processor (220) according to one embodiment may execute software (e.g., the program (140) of FIG. 1) to control at least one other component (e.g., a hardware or software component) of the electronic device (201) connected to the processor (220), and may perform data processing or calculations based on instructions. Instructions according to one embodiment may include instructions configured in a machine language that can be processed by the electronic device (201) or the processor (220). For example, instructions may include instructions corresponding to operation instructions used in a program.

[0046] According to one embodiment, the processor (220) may generate editing information to be transmitted to an artificial intelligence model when it determines that a face included in a first image has been edited. In one or more examples, the editing of the face may be determined or determined based on the state of the electronic device (201). For example, when the electronic device (201) is executing an editing application that displays an image including a face, it may be determined that the face in the image is being edited. In one or more examples, the electronic device (201) may determine that the face in the image is being edited when one or more editing operations are being performed on the face.

[0047] According to one embodiment, the processor (220) can check whether a face is included in the first image when confirming the selection of the first image based on an input from a user of the electronic device.

[0048] According to one embodiment, the processor (220) can use a face filter to check whether a face is included in the first image.

[0049] According to one embodiment, the processor (220) can confirm editing of a face included in the first image based on the user's input.

[0050] According to one embodiment, the processor (220) can check an editing area for the first image based on the user's input, and check whether the editing area is a part or the entire area of ​​a face included in the first image.

[0051] According to one embodiment, the processor (220) can, when confirming editing of a face included in the first image, confirm whether the face selected for editing is an authenticated face that has been allowed to be edited using the artificial intelligence model.

[0052] According to one embodiment, the processor (220) may, if the face information selected for editing is included among the authenticated face information that has been allowed to be edited using an artificial intelligence model stored in the memory (230), confirm that the face selected for editing is an authenticated face that has been allowed to be edited using the artificial intelligence model, and obtain first information about the face selected for editing.

[0053] According to one embodiment, the processor (220) can obtain first information of a face selected through editing among first information learned from facial features stored in the memory (230).

[0054] According to one embodiment, if the processor (220) cannot confirm that the face selected for editing is an authenticated face that allows editing using the artificial intelligence model, it can display a message through the display (260) indicating that face editing for the first image is not possible.

[0055] According to one embodiment, the processor (220) can use the artificial intelligence model to identify at least one of the following: the face of the user of the electronic device, the face of the user of a contact selected by the user of the electronic device from among contacts stored in a contact list, the face of the user of a contact that meets a condition specified by the user from among contacts stored in a contact list, or a face including tag information of a face from among images including a face, as an authenticated face that allows editing.

[0056] According to one embodiment, the processor (220) may use the artificial intelligence model to pre-check an authenticated face that allows editing based on various conditions such as a user's selection, a user's specified condition, or conditions specified in an electronic device, and store the face in the memory (230).

[0057] According to one embodiment, the processor (220) may acquire first information obtained by learning facial features using an artificial intelligence learning unit (233) and store the information in the memory (230). In one or more examples, the artificial intelligence learning unit (233) may be an ASIC or processor configured to perform an artificial intelligence process. In one or more examples, the artificial intelligence learning unit (233) may be a set of one or more executable codes that, when executed by the processor (220), cause the processor (220) to execute an artificial intelligence process.

[0058] According to one embodiment, the processor (220) may use the artificial intelligence learning unit (233) to obtain the first information corresponding to the authenticated face that has been allowed to be edited using the artificial intelligence model and store the information in the memory (230).

[0059] According to one embodiment, the processor (220) may use the artificial intelligence learning unit (233) to learn (e.g., train) a plurality of images including the same face to generate first information including characteristics of the same face, and store the first information as first information about the same face included in the plurality of learned images in the memory (230).

[0060] According to one embodiment, the processor (220) may use the artificial intelligence learning unit (233) to divide a face into a plurality of regions (e.g., eye region, nose region, mouth region, and entire face region), check weights corresponding to the plurality of regions, and generate first information reflecting the checked weights.

[0061] An artificial intelligence learning unit (233) according to one embodiment may include an encoder stored in a memory (230).

[0062] An artificial intelligence learning unit (233) according to one embodiment may include a learned encoder transmitted from an artificial intelligence model (231).

[0063] According to one embodiment, the processor (220) may transmit editing information including at least one of the first image, information on an editing area for a face included in the first image, or a prompt describing editing, and first information on a face selected for editing to the artificial intelligence model (231).

[0064] According to one embodiment, a processor (220) can generate a second image by editing a face included in a first image based on editing information using an artificial intelligence model (231).

[0065] An artificial intelligence model (231) according to one embodiment may include an on-device artificial intelligence model stored in a memory (230), and the artificial intelligence model (231) may include a generative artificial intelligence model.

[0066] According to one embodiment, a processor (220) can perform an editing operation of an image including a face in the same manner as the artificial intelligence model (231) by using an external artificial intelligence model (251a) stored in an external server (251), and the external artificial intelligence model (251a) can include a generative artificial intelligence model.

[0067] According to one embodiment, the processor (220) may perform an editing operation of an image including a face using at least one of an artificial intelligence model (231) stored in a memory (230) and an external artificial intelligence model (251a) included in an external server (251). In one or more examples, the electronic device (201) may download the external artificial intelligence model (251a) and preload it with the artificial intelligence model (231). In one or more examples, when the external artificial intelligence model (251a) is updated, the updated external artificial intelligence model (251a) may be downloaded to the electronic device (201) to replace the artificial intelligence model (231). In one or more examples, one or more tasks may be distributed between the artificial intelligence model (231) and the external artificial intelligence model (251a). An artificial intelligence model (231) according to one embodiment may use as input values ​​at least one of the first image included in the editing information, information on an editing area for a face included in the first image, or a prompt explaining editing, and first information on a face selected for editing, and generate as output values ​​a second image in which a face included in the first image is edited.

[0068] An artificial intelligence model (231) according to one embodiment can check a weight for an editing area based on information about an editing area for a face included in the first image, and generate a second image in which a face included in the first image is edited by reflecting the checked weight.

[0069] According to one embodiment, the processor (220), when receiving a second image in which a face included in a first image is edited from an artificial intelligence model (231), can verify the similarity between the edited face included in the second image and the authenticated face, and provide (e.g., display, store) the second image.

[0070] In one embodiment, the processor (220) performs a process of dividing a face included in the second image into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and an entire face region), obtains scores for the plurality of regions, and if the scores for the plurality of regions are equal to or greater than a threshold value, confirms that the edited face included in the second image is the same face as the authenticated face, and displays the second image including the edited face through the display (260). In one embodiment, the authenticated face and the edited face can be authenticated as faces of the same person based on features of the authenticated face and the edited face (e.g., a plurality of regions dividing the face (e.g., an eye region, a nose region, a mouth region, or an entire face region)). According to one embodiment, the processor (220) may, if the score for the plurality of areas is less than or equal to the threshold value, confirm that the edited face included in the second image is not the same as the authenticated face, and display a message through the display (260) indicating that face editing for the first image is not possible.

[0071] According to an embodiment, the processor (220) divides the face included in the second image into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and the entire face region), obtains a score for a region corresponding to an edited region among the plurality of regions, and if the score for the region corresponding to the edited region is equal to or greater than a threshold value, confirms that the edited face included in the second image is the same face as the authenticated face, and displays the second image including the edited face through the display (260). According to an embodiment, the processor (220) determines that the edited face included in the second image is not the same face as the authenticated face, and displays a message indicating that face editing for the first image is not possible through the display (260), if the score for the region corresponding to the biased region is equal to or less than the threshold value.

[0072] In one embodiment, the processor (220) may obtain scores for the plurality of regions using Earth Mover Distance (EMD), perceptual Loss, or Mean Square Error (MSE), which are based on the minimum amount of work required to transform one distribution into another by moving the distributions between each other. In one or more examples, EMD may be a measure of the difference between two frequency distributions, densities, or measurements in space. In one or more examples, perceptual Loss may be determined by passing an image through a neural network and comparing feature maps in one or more layers.

[0073] According to one embodiment, the processor (220) may divide the authenticated face into a plurality of regions and set an average value of the scores of the plurality of regions as the threshold value.

[0074] According to one embodiment, the processor (220) may divide the authenticated face into a plurality of regions and set a threshold value for each of the plurality of regions.

[0075] According to one embodiment, the processor (220) may change the threshold value depending on the performance or purpose of the artificial intelligence model (231). In one or more examples, the artificial intelligence model (231) may be updated or retrained based on one or more images stored in the electronic device (201), and the threshold value may be updated during retraining.

[0076] According to one embodiment, the processor (220) may check the similarity between the edited face included in the second image and the face included in the first image, and if the similarity is greater than or equal to a threshold value, the processor (220) may display the second image through the display (260). According to one embodiment, if the similarity is less than or equal to the threshold value, the processor (220) may display a message indicating that face editing for the first image is not possible through the display (260).

[0077] According to one embodiment, the processor (220) can check the similarity between the edited face included in the second image and the face included in the first image using the mean squared error (MSE), peak signal-to-noise ratio (PSNR), or structural similarity index (SSIM).

[0078] According to one embodiment, an operation of editing a face included in an image using an artificial intelligence model is performed by a processor (220), or the processor (220) includes a face editing unit (280) for editing a face included in an image using an artificial intelligence model, or can control the face editing unit (280) separately configured in the electronic device.

[0079] According to one embodiment, the face editing unit (280) may include a face detection unit (281), an information unit (283), and a determination unit (285) to edit a face included in an image using an artificial intelligence model.

[0080] According to one embodiment, the face detection unit (281) can check whether a face is included in an image in the same manner as the processor (220).

[0081] According to one embodiment, the information unit (283) can generate editing information in the same manner as the processor (220).

[0082] According to one embodiment, the determination unit (285) can, like the processor (220), check whether a face included in a first image is an authenticated face, and can check the similarity between the edited face and the authenticated face in a second image including an edited face received from an artificial intelligence model.

[0083] According to one embodiment, the processor (220) may, when the electronic device is in pet mode, generate and provide a second image by editing the animal included in the first image using an artificial intelligence model.

[0084] According to one embodiment, the processor (220) may generate and provide a second image in which an animal included in a first image is edited using an artificial intelligence model when the electronic device is in pet mode, in the same manner as the method of generating a second image in which a face included in a first image is edited using an artificial intelligence model.

[0085] The memory (230) according to one embodiment may be implemented substantially identically or similarly to the memory (130) of FIG. 1.

[0086] According to one embodiment, the memory (230) may store an on-device artificial intelligence model (231).

[0087] The on-device artificial intelligence model (231) according to one embodiment is an artificial intelligence model installed in an electronic device (201) and can provide various functions without a network.

[0088] According to one embodiment, a plurality of artificial intelligence models may be stored in the memory (230).

[0089] According to an embodiment, each of the plurality of artificial intelligence models may be models learned based on a designated type of learning algorithm, and may be artificial intelligence models implemented to input various types of data (e.g., content), perform operations, and output (e.g., acquire) result data. According to an embodiment, the plurality of artificial intelligence models may include a generative artificial intelligence model. The generative artificial intelligence model may generate and output new content (e.g., text, images, and / or computer codes, etc.) based on what has been learned in response to an input prompt. For example, in an electronic device (201), learning may be performed based on a machine learning algorithm or a deep learning algorithm to input data of designated types of data and output a specific type of result data as output data, thereby generating a plurality of artificial intelligence models (e.g., machine learning models and deep learning models), and thus being stored in the electronic device (201), or artificial intelligence models learned from an external electronic device (e.g., an external server) may be transmitted to and stored in the electronic device (201). For example, in an electronic device (201), input data (input data) can be output as output data of a model learned through a specified type of artificial intelligence based on a machine learning algorithm or a deep learning algorithm.The machine learning algorithms include supervised learning algorithms such as linear regression and logistic regression, unsupervised learning algorithms such as clustering, visualization and dimensionality reduction, and association rule learning, and reinforcement learning algorithms, and the deep learning algorithms may include artificial neural networks (ANNs), deep neural networks (DNNs), and convolution neural networks (CNNs). As will be understood by those skilled in the art, the present disclosure is not limited to those described above and may further include various learning algorithms. The learned artificial intelligence model may include a plurality of computational operations (e.g., convolutional layers or pooling layers) for computing input data, and may be implemented to output result data by performing computations on the input data based on the plurality of computational operations.

[0090] According to one embodiment, the memory (230) may store a plurality of applications that can be connected to a plurality of external AI models.

[0091] According to one embodiment, the memory (230) may store authenticated facial information that allows editing using an artificial intelligence model and first information that learns facial features.

[0092] A display (260) according to one embodiment may be implemented substantially identically or similarly to the display module (160) of FIG. 1.

[0093] According to one embodiment, the display (260) may display a first image including a face before editing and / or a second image including an edited face.

[0094] A communication circuit (290) according to one embodiment can form a communication connection with an external electronic device (e.g., another electronic device or a server) through various types of communication methods, and transmit and / or receive data. As described above, the communication method may include a communication method that establishes a direct communication connection such as Bluetooth and Wi-Fi direct, a communication method using an access point (AP) (e.g., Wi-Fi communication), or a communication method using cellular communication using a base station (e.g., 3G, 4G / LTE, 5G). Since the communication circuit (290) can be implemented like the communication module (190) described above in FIG. 1, a redundant description will be omitted.

[0095] FIG. 3a, FIG. 3b, FIG. 3c, FIG. 3d, and FIG. 3e are drawings for explaining an operation of generating first information in an artificial intelligence model.

[0096] According to one embodiment, referring to FIG. 3A, when a plurality of images (311) including a first face (e.g., the same face) are input as input values ​​to an artificial intelligence learning unit (e.g., an encoder) (233a), the artificial intelligence learning unit (e.g., an encoder) (233a) may output first information (331a) about the first face having learned features of the first face. The artificial intelligence learning unit (e.g., an encoder) (233a) may analyze features of the first face included in each of the plurality of images (311) to generate a distribution map for the features of the first face and generate the first information (331a) having learned the distribution map for the features of the first face.

[0097] The artificial intelligence model (231) can output an edited image (351a) generated based on the edited information as an output value when edited information including the first information (331a) is input as an input value.

[0098] The first information (331a) above may be a value derived from the artificial intelligence learning unit (e.g., encoder) (233a), and may represent a value (e.g., latent vector value) that represents information and features of an image in a latent space. The first information (331a) may represent a collection of values ​​(e.g., distribution values) that can express features and information of an image.

[0099] According to one embodiment, the values ​​that determine conditions for the appearances (e.g., eye color, size, lighting, angle, etc.) of the image of a person, object, or situation used for learning (training) in the artificial intelligence learning unit are called latent variables, and information about the face, such as the gender, age, race, hairstyle, skin, and / or facial expression of the face included in the image or other appropriate facial expressions known to those skilled in the art, and values ​​for the background, face angle, distance, wind, and / or light around the person can be determined as latent variables. The artificial intelligence learning unit can learn and determine the data on its own.

[0100] According to one embodiment, referring to FIG. 3b, when a plurality of images (311) including a first face (e.g., the same face) are input as input values ​​to an artificial intelligence learning unit (e.g., an encoder) (233b), the artificial intelligence learning unit (e.g., an encoder) (233b) learns through fine-tuning, analyzes the features of the first face included in each of the plurality of images (311), generates a distribution map for the features of the first face, and generates the first information (331b) that has learned the distribution map for the features of the first face.

[0101] The artificial intelligence model (231) can output an edited image (351b) generated based on the edited information as an output value when the edited information including the first information (331b) is input as an input value. According to one embodiment, in the above-described Fig. 3b, T1 represents an area where the plurality of images (311) input as input values ​​are trained and fine-tuned in the artificial intelligence learning unit (e.g., encoder) (233b).

[0102] According to one embodiment, referring to FIG. 3c, when a plurality of images (311) including a first face (e.g., the same face) are input as input values ​​to an artificial intelligence learning unit (e.g., an encoder) (233c), the artificial intelligence learning unit (e.g., an encoder) (233c) may be trained using LoRA (Low Rank Adaptation) to analyze the features of the first face included in each of the plurality of images (311) to generate a distribution map for the features of the first face and generate the first information (331c) obtained by learning the distribution map for the features of the first face. When training a plurality of images using LoRA, the first information may also be efficiently generated if the memory usage time is less than when fine-tuning is used. In one or more examples, the LoRA is a model that can be used for fine tuning for fine tuning data when training the artificial intelligence learning unit. As understood by those skilled in the art, the above LoRA is described as an example, and the artificial intelligence learning unit can be trained in various ways other than the above LoRA.

[0103] The artificial intelligence model (231) can output an edited image (351c) generated based on the edited information as an output value when the edited information including the first information (331c) is input as an input value. According to one embodiment, in the above-described Fig. 3c, T2 represents an area where the plurality of images (311) input as input values ​​are trained and fine-tuned in the artificial intelligence learning unit (e.g., encoder) (233c).

[0104] According to one embodiment, referring to FIG. 3d, when a plurality of images (311) including a first face (e.g., the same face) are input as input values ​​to a first artificial intelligence learning unit (e.g., encoder) (233d), the first artificial intelligence learning unit (e.g., encoder) (233d) may analyze features of the first face included in each of the plurality of images (311) to generate a distribution map for the features of the first face, and transfer the distribution map for the features of the first face to a second artificial intelligence learning unit (e.g., distilled encoder) (233e). The second artificial intelligence learning unit (e.g., distilled encoder) (233e) may reduce the size of the features of the first face, which are large in size transferred from the first artificial intelligence learning unit (encoder) (233d), by distilling the distribution map, and generate the first information (331d) in which the distribution map is learned for the features of the first face, which are reduced in size. The electronic device receives a first artificial intelligence learning unit (e.g., encoder) (233d) having a large size from an artificial intelligence model, distills the first artificial intelligence learning unit (e.g., encoder) (233d) having a large size to generate a second artificial intelligence learning unit (e.g., distilled encoder) (233e) having a small size that can be used by the electronic device, and performs training on a plurality of face images (311) through the second artificial intelligence learning unit (e.g., distilled encoder) (233e).

[0105] The artificial intelligence model (231) can output an edited image (351d) generated based on the edited information as an output value when the edited information including the first information (331d) is input as an input value. According to one embodiment, T3 in the drawing 3d may represent an area where training and fine tuning are performed on the plurality of images (311) input as input values ​​in the second artificial intelligence learning unit (e.g., distilled encoder) (233e).

[0106] According to one embodiment, referring to FIG. 3e, when a plurality of images (311) including a first face (e.g., the same face) are input as input values ​​to an artificial intelligence learning unit (e.g., encoder) (233f), the artificial intelligence learning unit (e.g., encoder) (233f) can generate first information (331e) by combining a latent vector (a1) and a distribution (a2) generated by using a reparametrization trick of the latent vector.

[0107] When editing information including the first information (331e) is input as an input value, the artificial intelligence model (231) can output an edited image (351e) generated based on the editing information as an output value.

[0108] Figures 4a and 4b are drawings for explaining the operation of generating an image with an edited face in an artificial intelligence model.

[0109] In one embodiment, referring to FIG. 4A, an artificial intelligence model (231) (e.g., the artificial intelligence model (231) of FIG. 2B) may receive editing information including a first image, information on an editing area for a face included in the first image, and a prompt describing editing, and first information on a face included in the first image by learning features of the face, from a processor of the electronic device (e.g., the processor (220) of FIG. 2). If the artificial intelligence model (231) determines that the first information includes information on a distribution of facial features (e.g., variance, mean) and the word “face,” the artificial intelligence model (231) may detect information on a face (b1) from the information on the distribution, and may inject the detected information on a face (b1) into each step of the artificial intelligence model (231) to generate a second image in which the face included in the first image is edited.

[0110] According to one embodiment, when operating based on a generative artificial intelligence model (231) (e.g., a diffusion model), each attention (e.g., a call command) step can remove noise from an image through multiple steps. If the information (411) input at each step includes the word "person," noise can be removed at each step using the information input as an input value.

[0111] In one embodiment, referring to FIG. 4B, the artificial intelligence model (231) may receive, from a processor of the electronic device (e.g., the processor (220) of FIGS. 2A and 2B), edit information including at least one of a first image, information on an edit area for a face included in the first image, and a prompt describing editing, and first information on a face included in the first image by learning features of the face. The artificial intelligence model (231) may use the edit information as a condition of a controlnet to generate a second image in which the face included in the first image is edited using the controlnet. According to one embodiment, a generative artificial intelligence model (231) (e.g., a diffusion model) performs learning to express an image generated through a control network used in the artificial intelligence model (231) in a manner corresponding to an input value input to an artificial intelligence learning unit (e.g., an encoder) (233), and when the learned artificial intelligence learning unit (e.g., an encoder) (233) is transmitted to an electronic device, the electronic device can generate first information about a face having learned facial features using the artificial intelligence learning unit (e.g., an encoder) (233).

[0112] FIG. 5 is a diagram illustrating an operation for checking similarity in an image in which a face has been edited in an electronic device according to one embodiment.

[0113] According to one embodiment, referring to FIG. 5, an electronic device (e.g., the electronic device (101) of FIG. 1 and / or the electronic device (201) of FIG. 2) may generate a second image in which a face included in a first image is edited using an artificial intelligence model, and may divide the edited face included in the second image into a plurality of regions, for example, an eye region (511), a nose region (513), a mouth region (515), and a face region (517).

[0114] The electronic device may obtain scores of a plurality of regions that distinguish an edited face included in the second image or scores of regions corresponding to an edited region among the plurality of regions, and if the scores are equal to or greater than a threshold value, the electronic device may determine that the face is the same as a face before editing (e.g., not edited) or the same as an authenticated face, and display the second image through a display of the electronic device (e.g., a display (260) of FIG. 2A). If the scores are equal to or less than a threshold value, the electronic device may determine that the face is not the same as a face before editing (e.g., not edited) or the authenticated face, and display a message indicating that face editing is not possible for the first image through a display of the electronic device (e.g., a display (260) of FIG. 2A). In one or more examples, each region among the plurality of regions may receive an individual score that is averaged and used to compare with a threshold value. In one or more examples, the region having the highest score among the plurality of regions may be used to compare with the threshold value.

[0115] In one embodiment, the electronic device may, before requesting editing of a face included in a first image using an artificial intelligence model, check whether the face included in the first image is an authenticated face, and if the face included in the first image is not confirmed to be an authenticated face, limit editing of the first image.

[0116] According to one embodiment, the electronic device may divide a face included in the first image into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and an entire face region), obtain scores for the plurality of regions, and compare the obtained scores with a threshold value to determine whether the face included in the first image is an authenticated face.

[0117] For example, the electronic device may obtain scores for the plurality of sections using one of Earth Mover Distance (EMD), perceptual Loss, or Mean Square Error (MSE) based on the minimum amount of work required to transform one distribution into another by moving the distributions between each other.

[0118] The electronic device according to one embodiment may set a threshold value for determining whether a face is authenticated.

[0119] For example, the electronic device can divide the authenticated face into a plurality of areas and set a threshold value based on the size (range) of the editing area among the plurality of areas.

[0120] For example, the electronic device may divide an authenticated face into a plurality of regions, set a threshold value for each of the plurality of regions, and compare a score obtained from an editing region among the plurality of regions with the threshold value set for the editing region to determine whether a face included in the first image is an authenticated face.

[0121] FIGS. 6A, 6B, 6C, and 6D are drawings for explaining an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0122] According to one embodiment, as shown in FIG. 6A, an electronic device (e.g., the electronic device (101) of FIG. 1 and / or the electronic device (201) of FIG. 2) can check a first image (611) selected by a user.

[0123] According to one embodiment, as shown in FIG. 6b, when the electronic device determines that the eye area (613a) selected by the user among the faces (613) included in the first image (611) is an editing area, the electronic device may determine whether the face (613) included in the first image (611) is an authenticated face that allows editing using an artificial intelligence model. When the electronic device determines that the face (613) selected for editing in the first image (611) is an authenticated face that allows editing using the artificial intelligence model, the electronic device may obtain first information about the face (613), and generate editing information including at least one of the first image (611), information about the editing area (613a) for the face included in the first image, and a prompt explaining editing, and the first information about the face (613), and transmit the edit information to an artificial intelligence model (e.g., the artificial intelligence model (231) of FIG. 2b).

[0124] According to one embodiment, as shown in FIG. 6c, when the electronic device receives a second image (631) in which an eye area included in the first image is edited using the editing information from the artificial intelligence model, the electronic device divides the face (633) included in the second image (631) into a plurality of areas, and confirms that the score of the edited eye area (633a) among the plurality of areas is 87.562, which is greater than the threshold value of 75, the electronic device confirms that the face (633) included in the second image (631) is the same face as the face (613) included in the first image (611) before editing or an authenticated face, and displays the second image (631) through a display of the electronic device (e.g., the display (260) of FIG. 2a).

[0125] According to one embodiment, as shown in FIG. 6d, when the electronic device receives a second image (651) in which an eye area included in the first image is edited using the editing information from the artificial intelligence model, divides the face (653) included in the second image (651) into a plurality of areas, and confirms that the score of the edited eye area (653a) among the plurality of areas is 56.674, which is less than the threshold value of 75, the electronic device may not confirm that the face (653) included in the second image (651) is the same face as the face (613) included in the first image (611) before editing or the authenticated face, and may display a message indicating that face editing for the first image (611) is not possible through the display of the electronic device (e.g., the display (260) of FIG. 2).

[0126] FIGS. 7A, 7B, and 7C are drawings for explaining an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0127] According to one embodiment, as shown in FIG. 7A, an electronic device (201) (e.g., the electronic device (101) of FIG. 1 and / or the electronic device (201) of FIG. 2) may display a first image (711) selected by a user on a display (260) of the electronic device (e.g., the display (260) of FIG. 2A).

[0128] According to one embodiment, as shown in FIG. 7b, when the electronic device (201) determines that the left cheek area (713a) selected by the user among the faces (713) included in the first image (711) is an editing area, the electronic device (201) may determine whether the face (713) included in the first image (711) is an authenticated face that allows editing using an artificial intelligence model. When the electronic device (201) determines that the face (713) selected for editing in the first image (711) is an authenticated face that allows editing using the artificial intelligence model, the electronic device (201) may acquire first information about the face (713), and generate edit information including at least one of the first image (711), information about the editing area (713a) for the face included in the first image, and a prompt explaining editing (e.g., showing a heart on the left cheek), and the first information about the face (713), and transmit the edit information to an artificial intelligence model (e.g., the artificial intelligence model (231) of FIG. 2b).

[0129] According to one embodiment, as shown in FIG. 7c, when the electronic device (201) receives a second image (731) in which the left cheek area included in the first image is edited using the editing information from the artificial intelligence model, the electronic device (201) divides the face (733) included in the second image (731) into a plurality of areas, obtains a score of the entire face area among the plurality of areas, and, when the score is confirmed to be higher than a threshold value, confirms that the face (773) included in the second image (731) is the same face as the face (713) included in the first image (711) before editing or an authenticated face, and displays the second image (731) through the display (260).

[0130] FIG. 8A is a diagram illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0131] According to an embodiment, referring to FIG. 8A, when an electronic device (201) (e.g., the electronic device (101) of FIG. 1 and / or the electronic device (201) of FIG. 2) confirms a selection of editing for a face (813a) included in an image (813), the electronic device (201) may provide an option (815) that allows the user to select first information about the face (813a). The electronic device (201) may provide an option (815) including a plurality of pieces of first information so that the face included in the image can be edited into various faces based on the first information of various faces.

[0132] FIG. 8b is a diagram illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to one embodiment.

[0133] According to one embodiment, referring to FIG. 8B, an electronic device (e.g., a determination unit (285) of FIG. 2) may determine whether the mask area is a face in operation 831 when it confirms input of a first image (811) including a first face, a mask area (813) indicating an editing area, and a prompt (815) describing editing.

[0134] If the electronic device (e.g., the determination unit (285) of FIG. 2) determines that the mask area is a face, in operation 835, the artificial intelligence learning unit (e.g., 233) can check first information (853) about the first face by learning the features of the first face using a plurality of images (851) including the first face as input values, and can check the authenticated face information based on the first information (853) about the first face.

[0135] The electronic device (e.g., the determination unit (285) of FIG. 2) can, in operation 837, identify the face included in the first image as an authenticated face based on the first information (853) about the first face.

[0136] The electronic device (e.g., the determination unit (285) of FIG. 2) may, in operation 839, determine to edit the first image if it confirms that the face included in the first image is an authenticated face.

[0137] An artificial intelligence model (e.g., artificial intelligence model (231) of FIG. 2B) may receive, in operation 841, editing information including a first image (811) including a first face, a mask area (813) indicating an editing area, a prompt (815) describing the editing, and first information (853).

[0138] The above artificial intelligence model (e.g., the artificial intelligence model (231) of FIG. 2B) can generate and output a second image in which a face included in the first image is edited based on edit information including a first image (811) including a first face, a mask area (813) indicating an edit area, a prompt (815) explaining the edit, and first information (853), in operation 845.

[0139] An electronic device according to an embodiment (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may include a communication circuit (e.g., communication module (190) of FIG. 1 and / or communication circuit (257) of FIG. 2A), a display (e.g., display module (160) of FIG. 1 and / or display (260) of FIG. 2A), at least one processor (e.g., processor (120) of FIG. 1 and / or processor (220) of FIGS. 2A to 2B), and a memory (e.g., memory (130) of FIG. 1 and / or memory (230) of FIG. 2A) for storing instructions. In one embodiment, the instructions, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to, when confirming editing of a face included in a first image, transmit edit information including first information about the face included in the first face to an artificial intelligence model (e.g., the artificial intelligence model (231) of FIG. 2B), and the first information may be acquired by learning features of the face selected for the editing. In one embodiment, the instructions, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to, when receiving a second image obtained by editing a face included in the first image using the edit information from the artificial intelligence model, acquire a score related to similarity between the edited face included in the second image and the face included in the first image. In one embodiment, the instructions, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to, when the acquired score is equal to or greater than a threshold value, store the second image.

[0140] In one embodiment, the instructions, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to, when confirming editing of a face included in the first image, use the artificial intelligence model to determine whether a face included in the first image and selected for editing is an authenticated face that allows editing. In one embodiment, the instructions, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to, when confirming that a face included in the first image and selected for editing is an authenticated face, obtain first information about the face. In one embodiment, the instructions, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to, when confirming that a face included in the first image and selected for editing is not an authenticated face, display a message through the display indicating that face editing of the first image is not possible.

[0141] According to one embodiment, the authenticated face may be set to include at least one of the following: the face of a user of the electronic device, the face of a user of a contact selected by the user of the electronic device from among contacts stored in a contact list, or the face of a user of a contact that meets a condition specified by the user from among contacts stored in a contact list.

[0142] The instructions according to one embodiment, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to, using an artificial intelligence learning unit, learn a plurality of images including the same face and generate first information including characteristics of the same face. The instructions according to one embodiment, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to store the generated first information in the memory as first information about the same face included in the plurality of learned images.

[0143] In one embodiment, the commands may include at least one of: information about an editing area for the first image, information about a face included in the first image, or a prompt describing editing.

[0144] In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to divide the edited face included in the second image into a plurality of regions. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to obtain a score for the plurality of regions. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to display the second image through the display if the score is greater than or equal to a threshold value. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to display a message indicating that face editing for the first image is not possible through the display if the score is less than or equal to the threshold value.

[0145] In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to divide the edited face included in the second image into a plurality of regions. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to obtain a score for a region corresponding to the edit region included in the edit information among the plurality of regions. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to display the second image through the display if the score is greater than or equal to a threshold value. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to display a message indicating that face editing for the first image is not possible through the display if the score is less than or equal to the threshold value.

[0146] In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to check the similarity between the edited face included in the second image and the face included in the first image. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to display the second image through the display if the similarity is greater than or equal to a threshold value. In one embodiment, the commands, when individually or collectively executed by the at least one processor, may be configured to cause the electronic device to display a message indicating that face editing for the first image is not possible through the display if the similarity is less than or equal to the threshold value.

[0147] FIG. 9 is a flowchart illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to an embodiment. The operations of editing a face included in an image using the artificial intelligence model may include operations 901 to 915. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, at least two operations may be performed in parallel, or other operations may be added.

[0148] In operation 901, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may display a first image.

[0149] According to one embodiment, the electronic device can determine whether a face is included in the first image when confirming selection of a first image based on an input of a user of the electronic device.

[0150] According to one embodiment, the electronic device can determine whether a face is included in the first image using a face filter.

[0151] In operation 903, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) can confirm a selection of editing for a face included in a first image.

[0152] According to one embodiment, the electronic device can identify an editing area for the first image based on an input from a user of the electronic device, and can identify whether the editing area is a part or the entire area of ​​a face included in the first image.

[0153] In operation 905, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may generate editing information for a first image and transmit it to an artificial intelligence model.

[0154] According to one embodiment, the electronic device can obtain first information about a face selected for editing in the first image.

[0155] According to one embodiment, the electronic device can obtain first information of a face selected through editing from among first information of facial features learned from a memory of the electronic device (e.g., memory (230) of FIG. 2A).

[0156] According to one embodiment, the electronic device may generate first information by learning facial features using an artificial intelligence learning unit (e.g., the artificial intelligence learning unit (233) of FIG. 2b) and store the first information in the memory.

[0157] According to one embodiment, the electronic device may use the artificial intelligence learning unit to generate first information including characteristics of the same face by using an artificial intelligence learning process on a plurality of images including the same face, and store the first information as first information about the same face included in the plurality of learned images in the memory.

[0158] According to one embodiment, the electronic device may use the artificial intelligence learning unit to divide a face into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and an entire face region), identify weights corresponding to the plurality of regions, and generate first information reflecting the identified weights.

[0159] In one embodiment, the electronic device may generate edit information including at least one of the first image, information of an edit area for a face included in the first image, or a prompt describing the edit, and first information of a face selected for the edit, and transmit the edit information to the artificial intelligence model.

[0160] In operation 907, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may generate a second image by editing a face included in a first image using an artificial intelligence model.

[0161] The artificial intelligence model according to one embodiment (e.g., the artificial intelligence model (231) of FIG. 2B) may use as input values ​​at least one of the first image included in the editing information, information on an editing area for a face included in the first image, or a prompt explaining editing, and first information on a face selected for editing, and generate as output values ​​a second image in which a face included in the first image is edited.

[0162] According to one embodiment, the artificial intelligence model can determine a weight for an editing area based on information about an editing area for a face included in the first image, and generate a second image in which the face included in the first image is edited by reflecting the determined weight.

[0163] In operation 909, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) can verify the similarity between the edited face included in the second image and the authenticated face.

[0164] According to one embodiment, when the electronic device receives a second image in which a face included in a first image is edited from an artificial intelligence model (e.g., the artificial intelligence model (231) of FIG. 2B), the electronic device can verify the similarity between the edited face included in the second image and the authenticated face.

[0165] According to one embodiment, the electronic device may divide the face included in the second image into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and the entire face region) and obtain scores for the plurality of regions.

[0166] According to one embodiment, the electronic device may divide the face included in the second image into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and the entire face region), and obtain a score for a region corresponding to an editing region among the plurality of regions.

[0167] In one embodiment, the electronic device may obtain scores for the plurality of regions using Earth Mover Distance (EMD), perceptual loss, or mean square error (MSE) based on the minimum amount of work required to transform one distribution into another by moving the distributions between each other.

[0168] In operation 911, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may compare a score of a face area included in a second image with a threshold value.

[0169] In the above operation 911, the electronic device can display a second image in operation 913 if the score is greater than or equal to a threshold value.

[0170] In one embodiment, the electronic device may, if the score is greater than or equal to a threshold value, confirm that the edited face included in the second image is the same face as the authenticated face, and display the second image including the edited face through a display (e.g., 260 of FIG. 2A) of the electronic device.

[0171] In the above operation 911, if the score is below a threshold value, the electronic device may display a message indicating that editing of the first image is not possible in operation 915.

[0172] In one embodiment, the electronic device may, if the scores for the plurality of areas are less than or equal to the threshold value, determine that the edited face included in the second image is not the same as the authenticated face, and display a message indicating that face editing for the first image is not possible through a display of the electronic device (e.g., display (260) of FIG. 2b).

[0173] FIG. 10 is a flowchart illustrating an operation of editing a face included in an image using an artificial intelligence model in an electronic device according to an embodiment. The operations of editing a face included in an image using the artificial intelligence model may include operations 1001 to 1019. In the following embodiments, each operation may be performed sequentially, but is not necessarily performed sequentially. For example, the order of each operation may be changed, at least two operations may be performed in parallel, or other operations may be added.

[0174] In operation 1001, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may display a first image.

[0175] According to one embodiment, the electronic device can determine whether a face is included in the first image when confirming selection of a first image based on an input of a user of the electronic device.

[0176] According to one embodiment, the electronic device can determine whether a face is included in the first image using a face filter.

[0177] In operation 1003, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) can confirm a selection of editing for a face included in a first image.

[0178] According to one embodiment, the electronic device can identify an editing area for the first image based on an input from a user of the electronic device, and can identify whether the editing area is a part or the entire area of ​​a face included in the first image.

[0179] In operation 1005, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) can verify whether a face selected for editing in a first image is an authenticated face that allows editing using an artificial intelligence model.

[0180] According to one embodiment, the electronic device may, if the face information selected for editing is included among the authenticated face information that has been allowed to be edited using an artificial intelligence model stored in the memory of the electronic device (e.g., the memory (230) of FIG. 2A), the face selected for editing may be confirmed as the authenticated face that has been allowed to be edited using the artificial intelligence model.

[0181] In the above operation 1005, if the electronic device cannot confirm that the face selected for editing in the first image is an authenticated face that allows editing using an artificial intelligence model, the electronic device can display a message indicating that face editing for the first image is not possible in operation 1007.

[0182] In one embodiment, the electronic device may display a message indicating that face editing for the first image is not possible through a display of the electronic device (e.g., the display of FIG. 2b).

[0183] In the above operation 1005, if the electronic device verifies that the face selected for editing in the first image is an authenticated face that allows editing using an artificial intelligence model, in operation 1009, editing information for the first image can be generated and transmitted to the artificial intelligence model.

[0184] According to one embodiment, the electronic device can obtain first information about a face selected for editing in the first image.

[0185] According to one embodiment, the electronic device can obtain first information of a face selected through editing from among first information of facial features learned from a memory of the electronic device (e.g., memory (230) of FIG. 2A).

[0186] According to one embodiment, the electronic device may generate first information by learning facial features using an artificial intelligence learning unit (e.g., the artificial intelligence learning unit (233) of FIG. 2b) and store the first information in the memory.

[0187] According to one embodiment, the electronic device may use the artificial intelligence learning unit to learn a plurality of images including the same face, thereby generating first information including characteristics of the same face, and store the first information in the memory as first information about the same face included in the plurality of learned images.

[0188] According to one embodiment, the electronic device may use the artificial intelligence learning unit to divide a face into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and an entire face region), identify weights corresponding to the plurality of regions, and generate first information reflecting the identified weights.

[0189] In one embodiment, the electronic device may generate edit information including at least one of the first image, information of an edit area for a face included in the first image, or a prompt describing the edit, and first information of a face selected for the edit, and transmit the edit information to the artificial intelligence model.

[0190] In operation 1011, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may generate a second image by editing a face included in a first image using an artificial intelligence model.

[0191] The artificial intelligence model according to one embodiment (e.g., the artificial intelligence model (231) of FIG. 2B) may use as input values ​​at least one of the first image included in the editing information, information on an editing area for a face included in the first image, or a prompt explaining editing, and first information on a face selected for editing, and generate as output values ​​a second image in which a face included in the first image is edited.

[0192] According to one embodiment, the artificial intelligence model can determine a weight for an editing area based on information about an editing area for a face included in the first image, and generate a second image in which the face included in the first image is edited by reflecting the determined weight.

[0193] In operation 1013, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) can verify the similarity between an edited face included in a second image and an authenticated face.

[0194] According to one embodiment, when the electronic device receives a second image in which a face included in a first image is edited from an artificial intelligence model (e.g., the artificial intelligence model (231) of FIG. 2B), the electronic device can verify the similarity between the edited face included in the second image and the authenticated face.

[0195] According to one embodiment, the electronic device may divide the face included in the second image into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and the entire face region) and obtain scores for the plurality of regions.

[0196] According to one embodiment, the electronic device may divide the face included in the second image into a plurality of regions (e.g., an eye region, a nose region, a mouth region, and the entire face region), and obtain a score for a region corresponding to an editing region among the plurality of regions.

[0197] In one embodiment, the electronic device may obtain scores for the plurality of regions using Earth Mover Distance (EMD), perceptual loss, or mean square error (MSE) based on the minimum amount of work required to transform one distribution into another by moving the distributions between each other.

[0198] In operation 1015, an electronic device (e.g., electronic device (101) of FIG. 1 and / or electronic device (201) of FIGS. 2A to 2B) may compare a score of a face area included in a second image with a threshold value.

[0199] In the above operation 1015, if the score is greater than or equal to a threshold value, the electronic device can display a second image in operation 1017.

[0200] In one embodiment, the electronic device may, if the score is greater than or equal to a threshold value, identify the edited face included in the second image as the same face as the authenticated face, and display the second image including the edited face through a display of the electronic device (e.g., 260 of FIG. 2A).

[0201] In the above operation 1015, if the score is below a threshold value, the electronic device may display a message indicating that editing of the first image is not possible in operation 1019.

[0202] In one embodiment, the electronic device may, if the scores for the plurality of areas are less than or equal to the threshold value, determine that the edited face included in the second image is not the same as the authenticated face, and display a message indicating that face editing for the first image is not possible through a display of the electronic device (e.g., display (260) of FIG. 2b).

[0203] According to an embodiment, a method for editing a face included in an image using an artificial intelligence model in an electronic device (e.g., the electronic device (101) of FIG. 1 and / or the electronic device (201) of FIG. 2) may include an operation of, when confirming editing of a face included in a first image, transmitting edit information including first information about the face included in the first image to an artificial intelligence model (e.g., the artificial intelligence model (231) of FIG. 2B), and obtaining the first information by learning a feature of the face selected through the editing. According to an embodiment, the method may include an operation of, when receiving a second image obtained by editing a face included in the first image using the edit information from the artificial intelligence model, obtaining a score related to similarity between an edited face included in the second image and a face included in the first image. According to an embodiment, the method may include an operation of storing the second image if the obtained score is equal to or greater than a threshold value.

[0204] According to one embodiment, the method may include an operation of, when confirming editing of a face included in the first image, using the artificial intelligence model, confirming whether a face included in the first image and selected for editing is an authenticated face that allows editing. According to one embodiment, the method may include an operation of obtaining first information about the face when confirming that a face included in the first image and selected for editing is an authenticated face. According to one embodiment, the method may further include an operation of displaying a message through the display indicating that face editing of the first image is not possible when confirming that a face included in the first image and selected for editing is not an authenticated face.

[0205] In the method according to one embodiment, the authenticated face may include at least one of the following: the face of a user of the electronic device, the face of a user of a contact selected by the user of the electronic device from among contacts stored in a contact list, or the face of a user of a contact that meets a condition specified by the user from among contacts stored in a contact list.

[0206] The method according to one embodiment may include an operation of generating first information including characteristics of the same face by learning a plurality of images including the same face using an artificial intelligence learning unit. The method according to one embodiment may further include an operation of storing the generated first information as first information about the same face included in the plurality of learned images in a memory of the electronic device.

[0207] In one embodiment, the method may include at least one of: information on an editing area for the first image, information on a face included in the first image, or a prompt describing editing.

[0208] According to one embodiment, the method may include an operation of dividing an edited face included in the second image into a plurality of regions. According to one embodiment, the method may include an operation of obtaining a score for the plurality of regions. According to one embodiment, the method may include an operation of displaying the second image through the display if the score is greater than or equal to a threshold value. According to one embodiment, the method may further include an operation of displaying a message indicating that face editing of the first image is not possible through the display if the score is less than or equal to the threshold value.

[0209] The method according to one embodiment may include an operation of dividing an edited face included in the second image into a plurality of regions. The method according to one embodiment may include an operation of obtaining a score for a region corresponding to an edit region included in the edit information among the plurality of regions. The method according to one embodiment may include an operation of displaying the second image through the display if the score is greater than or equal to a threshold value. The method according to one embodiment may further include an operation of displaying a message indicating that face editing for the first image is not possible through the display if the score is less than or equal to the threshold value.

[0210] The method according to one embodiment may include an operation of checking the similarity between the edited face included in the second image and the face included in the first image. The method according to one embodiment may include an operation of displaying the second image through the display if the similarity is above a threshold value. The method according to one embodiment may further include an operation of displaying a message indicating that face editing for the first image is not possible through the display if the similarity is below the threshold value.

[0211] Electronic devices according to embodiments disclosed herein 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 embodiments disclosed herein are not limited to the aforementioned devices.

[0212] The embodiments of this document and the terminology used herein 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 one component from another, and do not limit the components in any other respect (e.g., importance or order). When a component (e.g., a first component) 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.

[0213] The term "module" used in one embodiment 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).

[0214] An embodiment 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) or an electronic device (301)). For example, a processor (e.g., a processor (520)) of the machine (e.g., an electronic device (301)) 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.

[0215] According to one embodiment, the method according to one embodiment disclosed in the present document may be provided as included in 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 available 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.

[0216] According to one embodiment, 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 one embodiment, 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 one embodiment, 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.

Claims

1. In an electronic device (101 in FIG. 1; 201 in FIG. 2a to FIG. 2b), Communication circuit (190 in Fig. 1; 290 in Figs. 2a to 2b); Display (160 in Fig. 1; 260 in Figs. 2a to 2b); At least one processor including a processing circuit (120 of FIG. 1; 220 of FIGS. 2A to 2B); and It includes a memory (130 in FIG. 1; 230 in FIGS. 2a to 2b) for storing commands, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: When an edit to a face included in a first image is confirmed, edit information including first information about the face included in the first image is transmitted to an artificial intelligence model (e.g., 231 in FIG. 2b), and the first information is obtained by learning the features of the face selected by the edit. When receiving a second image in which a face included in the first image is edited using the editing information from the artificial intelligence model, a score related to the similarity between the edited face included in the second image and the face included in the first image is obtained, An electronic device set to store the second image if the obtained score is greater than or equal to a threshold value.

2. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: When confirming the editing of the face included in the first image, the artificial intelligence model is used to confirm whether the face included in the first image and selected for editing is an authenticated face that allows editing. If the face selected through the above editing and included in the above first image is confirmed as the authenticated face, first information about the face is obtained, An electronic device set to display a message through the display indicating that face editing for the first image is not possible if the face selected for editing included in the first image is not confirmed as the authenticated face.

3. In paragraph 1 or 2, An electronic device wherein the authenticated face is set to include at least one of the following: a face of a user of the electronic device, a face of a user of a contact selected by the user of the electronic device from among contacts stored in a contact list, or a face of a user of a contact that meets conditions specified by the user from among contacts stored in a contact list.

4. In any one of paragraphs 1 to 3, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Using an artificial intelligence learning unit, multiple images containing the same face are learned to generate first information containing characteristics of the same face, An electronic device configured to store the first information generated above in the memory as first information about the same face included in the plurality of learned images.

5. In any one of paragraphs 1 to 4, An electronic device wherein the above editing information is set to include at least one of information about an editing area for the first image, a face included in the first image, or a prompt describing editing.

6. In any one of paragraphs 1 to 5, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Divide the edited face included in the second image into multiple regions, Obtain scores for the above multiple areas, If the score is greater than or equal to the threshold value, the second image is displayed through the display, An electronic device set to display a message through the display indicating that face editing for the first image is not possible if the score is below the threshold value.

7. In any one of paragraphs 1 to 6, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Divide the edited face included in the second image into multiple regions, Obtain a score for an area corresponding to an editing area included in the editing information among the above multiple areas, If the score is greater than or equal to the threshold value, the second image is displayed through the display, An electronic device set to display a message through the display indicating that face editing for the first image is not possible if the score is below the threshold value.

8. In any one of paragraphs 1 to 7, The above instructions, when individually or collectively executed by the at least one processor, cause the electronic device to: Check the similarity between the edited face included in the second image and the face included in the first image, If the similarity is greater than or equal to a threshold value, the second image is displayed through the display, An electronic device set to display a message through the display indicating that face editing for the first image is not possible if the similarity is below the threshold value.

9. A method for editing a face included in an image using an artificial intelligence model in an electronic device (101 of FIG. 1; 201 of FIG. 2a to FIG. 2b), An operation in which, upon confirming an edit to a face included in a first image, edit information including first information about the face included in the first image is transmitted to an artificial intelligence model (e.g., 231 in FIG. 2b), and the first information is acquired by learning the features of the face selected by the edit; An operation of receiving a second image in which a face included in the first image is edited using the editing information from the artificial intelligence model, and obtaining a score related to the similarity between the edited face included in the second image and the face included in the first image; and A method including an action of storing the second image if the obtained score is greater than or equal to a threshold value.

10. In paragraph 9, When confirming an edit to a face included in the first image, an operation of using the artificial intelligence model to confirm whether the face included in the first image and selected for the edit is an authenticated face that allows editing; An operation of obtaining first information about the face when the face selected through the editing included in the first image is confirmed as the authenticated face; and A method further comprising an action of displaying a message through the display indicating that face editing for the first image is not possible if the face selected for editing included in the first image is not confirmed as the authenticated face.

11. In paragraph 9 or 10, A method wherein the authenticated face comprises at least one of the following: a face of a user of the electronic device, a face of a user of a contact selected by the user of the electronic device from among contacts stored in a contact list, or a face of a user of a contact that meets a condition specified by the user from among contacts stored in a contact list.

12. In any one of paragraphs 9 to 11, An operation of generating first information including characteristics of the same face by learning a plurality of images including the same face using an artificial intelligence learning unit; and A method further comprising an action of storing the generated first information in the memory of the electronic device as first information for the same face included in the plurality of learned images.

13. In any one of paragraphs 9 to 12, A method wherein the above editing information includes at least one of information about an editing area for the first image, a face included in the first image, or a prompt describing editing.

14. In any one of paragraphs 9 to 13, An operation of dividing the edited face included in the second image into a plurality of regions; An action of obtaining scores for the above multiple areas; If the score is greater than or equal to the threshold value, an operation of displaying the second image through the display; and A method further comprising an action of displaying a message through the display indicating that face editing for the first image is not possible if the score is less than or equal to the threshold value.

15. In a non-volatile storage medium storing instructions, the instructions are configured to cause the electronic device to perform a method when executed by at least one processor of the electronic device, the method comprising: An operation in which, upon confirming an edit to a face included in a first image, edit information including first information about the face included in the first image is transmitted to an artificial intelligence model, and the first information is obtained by learning the features of the face selected by the edit; An operation of receiving a second image in which a face included in the first image is edited using the editing information from the artificial intelligence model, and obtaining a score related to the similarity between the edited face included in the second image and the faces included in the first image; and A storage medium including an operation of storing the second image if the obtained score is greater than or equal to a threshold value.

Images