Electronic device and image processing method using electronic device

Abstract

An electronic device according to various embodiments of the present invention includes: a display; at least one processor; and a memory including one or more storage media storing instructions. The instructions may cause, when individually or integrally executed by the at least one processor, the electronic device to: display a first image including an object image area and a background image area through a user interface; receive an input for selecting the object image area included in a first image while the first image is displayed; identify an outline of the selected object image area on the basis of the input; generate a mask area related to the identified outline of the object image area; transform the generated mask area into another shape; and generate, through generative artificial intelligence (200), a second image obtained by changing the selected object image area to a background image area, on the basis of information related to the first image including the transformed mask area.

Description

Electronic device and image processing method using the electronic device

[0001] Various embodiments of the present invention disclose an electronic device and a method of processing an image using the electronic device.

[0002] The use of electronic devices such as bar type, foldable type, rollable type or sliding type is increasing, and various functions are being provided to electronic devices.

[0003] The electronic device can capture images or videos using one or more cameras.

[0004] The above electronic device can display images or videos captured using a camera through a display module.

[0005] The above information may be provided as background art to aid in understanding the present disclosure. No claim or determination is made as to whether any of the above is applicable as prior art in connection with the present disclosure.

[0006] Electronic devices can install at least one application and perform various functions. For example, an electronic device may provide the ability to edit images captured by a camera using a specific application.

[0007] The electronic device can use generative artificial intelligence to provide variously edited images from the original image. For example, if a user of the electronic device deletes an object image area (e.g., a specific object) from an image, the generative artificial intelligence can generate a new object in place of the deleted object image area (e.g., the specific object).

[0008] For example, if a user of the electronic device only wants to delete an object image area (e.g., a specific object) from an image, the generative artificial intelligence may generate another unnecessary object of a similar shape to the object image area (e.g., the specific object) in the area where the object image area (e.g., the specific object) is deleted. If the electronic device provides an image including an unnecessary object using the generative artificial intelligence, the user may not be able to obtain the image he or she wants.

[0009] Various embodiments of the present invention can provide an electronic device and an image processing method using the electronic device that can prevent a generative artificial intelligence from generating another image in an area where an object image area (e.g., a specific object) is deleted from an image.

[0010] Various embodiments of the present invention may provide an electronic device and an image processing method using the electronic device, which, when a user desires to delete an object image area (e.g., a specific object) within an image, deforms a mask area related to the object image area to be deleted so that a generative artificial intelligence cannot estimate or predict the shape (e.g., an outline or boundary) of the object image area to be deleted.

[0011] The technical problems to be achieved in the present disclosure are not limited to the technical problems mentioned above, and other technical problems not mentioned can be clearly understood by a person having ordinary skill in the technical field to which the present invention belongs from the description below.

[0012] An electronic device according to one embodiment of the present invention may include a display, at least one processor, and a memory including one or more storage media storing instructions. According to one embodiment, the instructions, when individually or integrally executed by the at least one processor, may cause the electronic device to display a first image including an object image area and a background image area through a user interface, receive an input for selecting the object image area included in the first image while the first image is displayed, identify an outline of the selected object image area based on the input, generate a mask area related to the outline of the identified object image area, transform the generated mask area to have a different outline, and generate a second image in which the selected object image area is changed to the background image area based on information related to the first image including the transformed mask area, through generative artificial intelligence.

[0013] A method for processing an image using an electronic device according to one embodiment of the present invention may include an operation of displaying a first image including an object image area and a background image area through a user interface. According to one embodiment, the method may include an operation of receiving an input for selecting the object image area included in the first image while the first image is displayed. According to one embodiment, the method may include an operation of identifying an outline of the selected object image area based on the input. According to one embodiment, the method may include an operation of generating a mask area related to the outline of the identified object image area. According to one embodiment, the method may include an operation of modifying the generated mask area to have a different outline. According to one embodiment, the method may include an operation of generating a second image in which the selected object image area is changed to the background image area through generative artificial intelligence based on information related to the first image including the modified mask area.

[0014] According to one embodiment, a method of processing an image using the electronic device may be performed using a non-transitory computer-readable storage medium storing one or more programs. According to one embodiment, the one or more programs may include instructions and / or commands that are executed when executed by a processor of the electronic device.

[0015] According to various embodiments of the present invention, when a user deletes an object image area (e.g., a specific object) within an image, the generative artificial intelligence can obtain a desired image by preventing the user from generating a new image in the area where the object image area was deleted.

[0016] According to various embodiments of the present invention, when a user deletes an object image area (e.g., a specific object) within an image, a mask area associated with the object image area to be deleted can be deformed so that the generative artificial intelligence cannot estimate or predict the shape of the object image area to be deleted.

[0017] In addition, various effects may be provided, either directly or indirectly, through this document.

[0018] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0019] FIG. 1A is a block diagram of an electronic device within a network environment according to various embodiments of the present invention.

[0020] FIG. 1b is a block diagram of a display module according to various embodiments of the present invention.

[0021] FIG. 2 is a block diagram schematically showing the configuration of an electronic device according to one embodiment of the present invention.

[0022] FIG. 3A is a diagram schematically illustrating a first image displayed through a display of an electronic device according to one embodiment of the present invention.

[0023] FIG. 3b is a diagram schematically illustrating a mask area generated in relation to an object image area in a first image of an electronic device according to one embodiment of the present invention.

[0024] FIG. 3c is a schematic diagram illustrating a second image in which an object image area is deleted and a background image area is filled in a first image of an electronic device according to one embodiment of the present invention.

[0025] FIG. 4 is a schematic diagram illustrating an example in which an electronic device according to one embodiment of the present invention generates a mask area for an object image area.

[0026] FIGS. 5A to 5C are schematic diagrams illustrating embodiments in which an electronic device according to one embodiment of the present invention transforms an object image area into a polygonal shape.

[0027] FIG. 6 is a schematic diagram illustrating an example in which an electronic device according to one embodiment of the present invention creates holes of irregular size around a mask area.

[0028] FIG. 7A is a diagram schematically illustrating a first image including an object image area and a shadow image area displayed through a display of an electronic device according to one embodiment of the present invention.

[0029] FIG. 7b is a diagram schematically illustrating a generated mask area including an object image area and a shadow image area in a first image of an electronic device according to one embodiment of the present invention.

[0030] FIG. 7c is a schematic diagram illustrating a second image in which an object image area and a shadow image area are deleted and a background image area is filled in a first image of an electronic device according to one embodiment of the present invention.

[0031] FIG. 8A is a diagram schematically illustrating a first image including an object image area and a background image area displayed through a display of an electronic device according to one embodiment of the present invention.

[0032] FIG. 8b is a diagram schematically illustrating a mask area and anchor points generated for an object image area in a first image of an electronic device according to one embodiment of the present invention.

[0033] FIG. 8C is a diagram schematically illustrating a second image including a background image area and an object image area in a first image of an electronic device according to one embodiment of the present invention.

[0034] FIG. 9A is a diagram schematically illustrating a first image displayed through a display of an electronic device according to one embodiment of the present invention.

[0035] FIG. 9b is a diagram schematically illustrating an embodiment of moving an object image area in a first image of an electronic device according to one embodiment of the present invention.

[0036] FIG. 9c is a diagram schematically illustrating a mask area generated for an object image area in a first image of an electronic device according to one embodiment of the present invention.

[0037] FIG. 9d is a schematic diagram illustrating an embodiment in which a mask area generated in relation to an object image area in a first image of an electronic device according to one embodiment of the present invention is transformed into a polygonal shape.

[0038] FIG. 9e is a diagram schematically illustrating an embodiment in which an object image area is deleted and an object image area is moved in a first image of an electronic device according to one embodiment of the present invention.

[0039] FIG. 10 is a flowchart schematically illustrating a method of processing an image using an electronic device according to one embodiment of the present invention.

[0040] FIG. 1A is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments of the present invention.

[0041] Referring to FIG. 1A, in a network environment (100), an electronic device (101) may communicate with an electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of an electronic device (104) or a server (108) via a second network (199) (e.g., a long-range wireless communication network). In one embodiment, the electronic device (101) may communicate with the electronic device (104) via the server (108). According to one embodiment, the electronic device (101) may include a processor (120), a memory (130), an input module (150), an audio output module (155), a display module (160), an audio module (170), a sensor module (176), an interface (177), a connection terminal (178), a haptic module (179), a camera module (180), a power management module (188), a battery (189), a communication module (190), a subscriber identification module (196), or an antenna module (197). In some embodiments, the electronic device (101) may omit at least one of these components (e.g., the connection terminal (178)), or may have one or more other components added. In some embodiments, some of these components (e.g., the sensor module (176), the camera module (180), or the antenna module (197)) may be integrated into one component (e.g., the display module (160)).

[0042] 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 calculations. According to one embodiment, as at least a part of the data processing or calculations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or a secondary 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 therewith. For example, if the electronic device (101) includes a main processor (121) and a secondary processor (123), the secondary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a specified function. The secondary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[0043] The auxiliary processor (123) may control at least a portion of functions or states associated with at least one component (e.g., a display module (160), a sensor module (176), or a communication module (190)) of the electronic device (101), for example, on behalf of the main processor (121) while the main processor (121) is in an inactive (e.g., sleep) state, or together with the main processor (121) while the main processor (121) is in an active (e.g., application execution) state. In one embodiment, the auxiliary processor (123) (e.g., an image signal processor or a communication processor) may be implemented as a part of another functionally related component (e.g., a camera module (180) or a communication module (190)). In one embodiment, the auxiliary processor (123) (e.g., a neural network processing unit) may include a hardware structure specialized for processing artificial intelligence models. The artificial intelligence models may be generated through machine learning. This learning can be performed, for example, on the electronic device (101) itself where the artificial intelligence model is executed, or can be performed through a separate server (e.g., server (108)). The learning algorithm can include, for example, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning, but is not limited to the examples described above. The artificial intelligence model can include multiple artificial neural network layers.The artificial neural network may be one of a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a bidirectional recurrent deep neural network (BRDNN), a deep Q-network, or a combination of two or more of the above, but is not limited to the examples described above. In addition to, or alternatively to, a hardware structure, an artificial intelligence model may include a software structure.

[0044] 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).

[0045] 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).

[0046] 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).

[0047] The audio output module (155) can output audio signals to the outside of the electronic device (101). The audio output module (155) can include, for example, a speaker or a receiver. The speaker can be used for general purposes, such as multimedia playback or recording playback. The receiver can be used to receive incoming calls. In one embodiment, the receiver can be implemented separately from the speaker or as part of the speaker.

[0048] 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. In 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.

[0049] 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).

[0050] 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.

[0051] The interface (177) may support one or more designated protocols that may be used to directly or wirelessly connect the electronic device (101) with an external electronic device (e.g., the electronic device (102)). In one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0052] 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).

[0053] 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. In one embodiment, the haptic module (179) can include, for example, a motor, a piezoelectric element, or an electrical stimulation device.

[0054] 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.

[0055] 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, for example, as at least a part of a power management integrated circuit (PMIC).

[0056] 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.

[0057] 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).

[0058] The wireless communication module (192) can support 5G networks and next-generation communication technologies following the 4G network, such as NR access technology (new radio access technology). The NR access technology can support high-speed transmission of high-capacity data (eMBB (enhanced mobile broadband)), minimization of terminal power and connection of multiple terminals (mMTC (massive machine type communications)), or high reliability and low latency (URLLC (ultra-reliable and low-latency communications)). The wireless communication module (192) can support, for example, a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate. The wireless communication module (192) can support various technologies for securing performance in a high-frequency band, such as beamforming, massive multiple-input and multiple-output (MIMO), full dimensional MIMO (FD-MIMO), array antenna, analog beam-forming, or large scale antenna. The wireless communication module (192) can support various requirements specified in the electronic device (101), an external electronic device (e.g., the electronic device (104)), or a network system (e.g., the second network (199)). According to one embodiment, the wireless communication module (192) can support a peak data rate (e.g., 20 Gbps or more) for eMBB realization, a loss coverage (e.g., 164 dB or less) for mMTC realization, or a U-plane latency (e.g., 0.5 ms or less for downlink (DL) and uplink (UL), or 1 ms or less for round trip) for URLLC realization.

[0059] 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 by, for example, the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through 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).

[0060] According to various embodiments, 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 a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high frequency band.

[0061] 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)).

[0062] 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.

[0063] FIG. 1b is a block diagram (105) of a display module (160) according to various embodiments of the present invention.

[0064] Referring to FIG. 1B, the display module (160) may include a display (161) and a display driver IC (DDI) (165) for controlling the display (161). The DDI (165) may include an interface module (165a), a memory (165b) (e.g., a buffer memory), an image processing module (165c), or a mapping module (165d). The DDI (165) may receive, for example, image information including image data or an image control signal corresponding to a command for controlling the image data, from another component of the electronic device (101) through the interface module (165a). According to one embodiment, the image information may be received from a processor (120) (e.g., a main processor (121) (e.g., an application processor) or a secondary processor (123) (e.g., a graphics processing unit)) that operates independently of the function of the main processor (121). The DDI (165) can communicate with the touch circuit (168) or the sensor module (176) through the interface module (165a). In addition, the DDI (165) can store at least a portion of the received image information in the memory (165b), for example, on a frame basis. The image processing module (165c) can, for example, perform preprocessing or postprocessing (e.g., resolution, brightness, or size adjustment) on at least a portion of the image data based on at least the characteristics of the image data or the characteristics of the display (161). The mapping module (165d) can generate a voltage value or a current value corresponding to the image data preprocessed or postprocessed through the image processing module (165c). According to one embodiment, the generation of the voltage value or the current value can be performed based at least in part on, for example, the properties of the pixels of the display (161) (e.g., the arrangement of the pixels (RGB stripe or pentile structure), or the size of each subpixel).At least some pixels of the display (161) may be driven based at least in part on, for example, the voltage value or current value, so that visual information (e.g., text, an image, or an icon) corresponding to the image data may be displayed through the display (161).

[0065] According to one embodiment, the display module (160) may further include a touch circuit (168). The touch circuit (168) may include a touch sensor (168a) and a touch sensor IC (168b) for controlling the touch sensor (168a). The touch sensor IC (168b) may control the touch sensor (168a) to detect, for example, a touch input or a hovering input for a specific location of the display (161). For example, the touch sensor IC (168b) may detect the touch input or the hovering input by measuring a change in a signal (e.g., voltage, light quantity, resistance, or charge quantity) for a specific location of the display (161). The touch sensor IC (168b) may provide information (e.g., location, area, pressure, or time) regarding the detected touch input or hovering input to the processor (120). According to one embodiment, at least a portion of the touch circuit (168) (e.g., touch sensor IC (168b)) may be included as part of the display driver IC (165), or as part of the display (161), or as part of another component (e.g., auxiliary processor (123)) disposed external to the display module (160).

[0066] According to one embodiment, the display module (160) may further include at least one sensor (e.g., a fingerprint sensor, an iris sensor, a pressure sensor, or an illuminance sensor) of the sensor module (176), or a control circuit therefor. In this case, the at least one sensor or the control circuit therefor may be embedded in a part of the display module (160) (e.g., the display (161) or the DDI (165)) or a part of the touch circuit (168). For example, when the sensor module (176) embedded in the display module (160) includes a biometric sensor (e.g., a fingerprint sensor), the biometric sensor may obtain biometric information (e.g., a fingerprint image) associated with a touch input through a part of the display (161). For example, when the sensor module (176) embedded in the display module (160) includes a pressure sensor, the pressure sensor may obtain pressure information associated with a touch input through a part or the entire area of ​​the display (161). According to one embodiment, the touch sensor (168a) or sensor module (176) may be positioned between pixels of a pixel layer of the display (161), or above or below the pixel layer.

[0067] Electronic devices according to the various embodiments disclosed in this document may take various forms. Electronic devices may include, for example, portable communication devices (e.g., smartphones), computer devices, portable multimedia devices, portable medical devices, cameras, wearable devices, or home appliances. Electronic devices according to the embodiments of this document are not limited to the aforementioned devices.

[0068] The various embodiments of this document and the terminology used therein are not intended to limit the technical features described in this document to specific embodiments, but should be understood to include various modifications, equivalents, or substitutes of the embodiments. In connection with the description of the drawings, similar reference numerals may be used for similar or related components. The singular form of a noun corresponding to an item may include one or more of the items, unless the context clearly indicates otherwise. In this document, each of the phrases "A or B", "at least one of A and B", "at least one of A or B", "A, B, or C", "at least one of A, B, and C", and "at least one of A, B, or C" can include any one of the items listed together in the corresponding phrase among those phrases, or all possible combinations thereof. Terms such as "first," "second," or "first" or "second" may be used merely to distinguish 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.

[0069] The term "module" used in various embodiments of this document may include a unit implemented in hardware, software, or firmware, and may be used interchangeably with terms such as logic, logic block, component, or circuit. A module may be an integral component, or a minimum unit or part of such a component that performs one or more functions. For example, according to one embodiment, a module may be implemented in the form of an application-specific integrated circuit (ASIC).

[0070] Various embodiments of the present document may be implemented as software (e.g., a program (140)) including one or more instructions stored in a storage medium (e.g., an internal memory (136) or an external memory (138)) readable by a machine (e.g., an electronic device (101)). For example, a processor (e.g., a processor (120)) of the machine (e.g., an electronic device (101)) may call at least one instruction among the one or more instructions stored from the storage medium and execute it. This enables the machine to operate to perform at least one function according to the at least one called instruction. The one or more instructions may include code generated by a compiler or code executable by an interpreter. The machine-readable storage medium may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' simply means that the storage medium is a tangible device and does not contain signals (e.g., electromagnetic waves), and the term does not distinguish between cases where data is stored semi-permanently or temporarily on the storage medium.

[0071] According to one embodiment, the method according to various embodiments disclosed in this document may be provided as a computer program product. The computer program product may be traded between sellers and buyers as a product. The computer program product may be distributed in the form of a device-readable storage medium (e.g., compact disc read-only memory (CD-ROM)) or may be provided through an application store (e.g., Play Store). TM ) or directly between two user devices (e.g., smart phones), online distribution (e.g., downloading or uploading). In the case of online distribution, at least a portion of the computer program product may be at least temporarily stored or temporarily created in a machine-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or an intermediary server.

[0072] According to various embodiments, each component (e.g., a module or a program) of the above-described components may include one or more entities, and some of the entities may be separated and placed in other components. According to various embodiments, one or more components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Alternatively or additionally, a plurality of components (e.g., a module or a program) may be integrated into a single component. In such a case, the integrated component may perform one or more functions of each of the plurality of components identically or similarly to those performed by the corresponding component among the plurality of components prior to the integration. According to various embodiments, the operations performed by a module, program, or other component may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

[0073] FIG. 2 is a block diagram schematically showing the configuration of an electronic device according to one embodiment of the present invention.

[0074] According to various embodiments, the electronic device (101) disclosed below may include at least some of the embodiments described in FIGS. 1A and 1B. In the description of the electronic device (101) according to the embodiments of the present invention disclosed below, the same reference numerals are given to components that are substantially the same as those of the embodiments disclosed in FIGS. 1A and 1B described above, and redundant descriptions of their functions may be omitted.

[0075] Referring to FIG. 2, an electronic device (101) according to one embodiment of the present invention may include a camera (280), a display (260), a memory (130), and / or a processor (120).

[0076] According to one embodiment, the electronic device (101) may include a generative artificial intelligence (200). According to various embodiments, the generative artificial intelligence (200) may be included in the server (108) disclosed in FIG. 1A. According to various embodiments, the generative artificial intelligence (200) may be included in the electronic device (101) and / or the server (108) disclosed in FIG. 1A.

[0077] According to various embodiments, the camera (280) may include the camera module (180) disclosed in FIG. 1A. For example, the camera (280) may be at least one camera used in the electronic device (101). The display (260) may include the display module (160) disclosed in FIGS. 1A and 1B.

[0078] According to various embodiments, the memory (130) may include one or more storage media for storing instructions. For example, the instructions, when individually or collectively executed by at least one processor (120), may be configured to perform or control at least a portion of a function of the electronic device.

[0079] According to various embodiments, at least one processor (120) may be included in the electronic device (101). For example, the processor (120) may include an application processor, a microprocessor unit (MPU), and / or a data processing unit (DPU).

[0080] According to one embodiment, the camera (280) (e.g., the camera module (180) of FIG. 1A) can capture at least one of still images and videos. Images and / or videos captured by the camera (280) can be stored in the memory (130). For example, the camera (280) can include one or more image sensors (e.g., a front sensor or a rear sensor), at least one lens, an Image Signal Processor (ISP), or a flash (e.g., an LED or a xenon lamp).

[0081] According to one embodiment, the display (260) (e.g., the display module (160) of FIGS. 1A and 1B) may display images and / or videos stored in the memory (130). The display (260) may display an execution screen of a specific application. For example, the specific application may include an application such as a gallery or a photo editor capable of editing images. The specific application is not limited to the examples described above and may include various other applications capable of editing images.

[0082] According to various embodiments, the display (260) may include a touch circuit (e.g., a touch circuit (168) of FIG. 1B). The touch circuit (168) may include a touch sensor (168a) and a touch sensor IC (168b) as disclosed in FIG. 1B. The touch circuit (168) may detect or receive a user's touch, press (e.g., a long press), drag, and / or stylus pen input to a designated location of the display (260). For example, the display (260) may receive a user input (e.g., a touch, press, or drag) to an object image area (e.g., a specific object) within an image. For example, the display (260) may receive a user input for selecting an object image area (e.g., the first image (310) of FIG. 3A) within an image including an object image area (e.g., the object image area (301) of FIG. 3A) and / or a background image area (e.g., the background image area (302) of FIG. 3A). For example, the display (260) may provide a screen for setting functions and operations of an image or a specific application (e.g., a gallery or a photo editor) capable of editing the image, based on an input signal of a user of the electronic device (101). For example, the display (260) may operate or be performed based on a user interface (UI) that may provide various services to the user.

[0083] According to various embodiments, the display (260) may display the initial screen, setting screen, and / or execution screens of various applications of the electronic device (101). The display (260) may display a user interface (UI) that may provide various services to a user of the electronic device (101). The display (260) may perform a display function and an input function. The display (260) may include a display (e.g., the display (161) of FIG. 1B) and a touch circuit (e.g., the touch circuit (168) of FIG. 1B) to perform the display function and the input function. The display (161) may visually provide a menu, input data, function setting information, and various information of the electronic device (101) to the user. The display (161) may include at least one of a liquid crystal display (LCD), an organic light emitting diode (OLED), and an active matrix organic light emitting diode (AMOLED). The touch circuit (168) may include a touch sensor (e.g., touch sensor (168a) of FIG. 1B) or a pressure sensor, such as a capacitive overlay, a resistive overlay, or an infrared beam.

[0084] According to one embodiment, the memory (130) can store images captured by the camera (280). The memory (130) can store images provided through an external electronic device (e.g., the external electronic device (102, 104) of FIG. 1A) and / or a server (e.g., the server (108) of FIG. 1A). The memory (130) can store at least one application (e.g., a gallery or a photo editor) capable of editing images. The memory (130) can store executable instructions. For example, the memory (130) can include one or more storage media that store instructions. For example, the memory (130) can store at least one instruction that, when individually or collectively executed by at least one processor (120), causes the electronic device (101) to perform at least one operation. For example, at least one instruction may be stored on a computer-readable recording medium. The recording medium may be tangible and non-transitory. The memory (130) and / or the recording medium may store one or more programs including at least one instruction.

[0085] According to various embodiments, the memory (130) may store the initial screen, setting screen, and / or various applications of the electronic device (101) provided through the display (260). The memory (130) may store a user interface (UI) that may provide various services to the user of the electronic device (101). The memory (130) may perform a function of storing a program for processing and controlling the processor (120) (e.g., the program (140) of FIG. 1A), an operating system (e.g., the operating system (142) of FIG. 1A), various applications, and input / output data. The memory (130) may store a program that controls the overall operation of the electronic device (101). The memory (130) may store various setting information required when processing functions in the electronic device (101).

[0086] According to one embodiment, the processor (120) may be operatively connected to a camera (280), a display (260), a memory (130), and / or a generative artificial intelligence (200). The processor (120) may control functions and operations of the camera (280), the display (260), the memory (130), and / or the generative artificial intelligence (200). The processor (120) may be configured to access the memory (130) and execute at least one instruction. The electronic device (101) may include at least one processor (120). For example, the processor (120) may include an application processor, a microprocessor unit (MPU), and / or a data processing unit (DPU).

[0087] According to one embodiment, the processor (120) may display a first image (e.g., the first image (310) of FIG. 3A) stored in the memory (130) through the display (260) based on an input signal of a user of the electronic device (101). The first image (e.g., the first image (310) of FIG. 3A) may include an object image area (e.g., the object image area (301) disclosed in FIG. 3A) and / or a background image area (e.g., the background image area (302) of FIG. 3A). The processor (120) may display an execution screen of a specific application (e.g., a gallery or a photo editor) capable of editing the first image (e.g., the first image (310) of FIG. 3A) through the display (260) based on an input signal of a user of the electronic device (101). The processor (120) can receive (e.g., detect) a user input (e.g., a touch or press) related to selection of an object image area (e.g., a specific object (301) disclosed in FIG. 3A) included in a first image (e.g., a first image (310) of FIG. 3A).

[0088] According to one embodiment, the processor (120) may include a segmentation unit (201), a mask area setting unit (203), and / or a deformation unit (205).

[0089] According to one embodiment, the processor (120) may use the segmentation unit (201) to identify an outline (e.g., a shape) of an object image area (e.g., an object image area (301) of FIG. 3A) selected by a user of the electronic device (101). For example, the segmentation unit (201) may identify an external shape (e.g., an outline or a boundary) of an object image area (e.g., a specific object such as a person) selected by a user of the electronic device (101).

[0090] According to various embodiments, the segmentation unit (201) may perform segmentation on an object image area (e.g., the object image area (301) of FIG. 3A) within a first image (e.g., the first image (310) of FIG. 3A) selected by a user. For example, information segmented through the segmentation unit (201) may be displayed after, for example, resolution, brightness, shape, or size is processed through the image processing module (165c) of the display (260). The segmentation unit (201) may perform image segmentation (e.g., object segmentation, skin segmentation, body segmentation, or background segmentation). For example, image segmentation may include an operation of dividing or subdividing an area corresponding to an object image area (e.g., the object image area (301) of FIG. 3A) selected by a user so that the user can recognize it. For example, image segmentation may include an operation of classifying or identifying an object image area (e.g., an object image area (301) of FIG. 3A) within a first image (e.g., a first image (310) of FIG. 3A) by dividing the area into pixel units or area units.

[0091] According to one embodiment, the processor (120) may use the mask area setting unit (203) to generate a mask area (e.g., a mask area (305) of FIG. 3b) related to an object image area (e.g., an object image area (301) of FIG. 3a) identified through the segmentation unit (201). For example, the mask area (e.g., a mask area (305) of FIG. 3b) may include a mask map. For example, the processor (120) may use the mask area setting unit (203) to set a mask area (e.g., a mask area (305) of FIG. 3b) related to an object image area (e.g., an object image area (301) of FIG. 3a) identified through the segmentation unit (201).

[0092] According to various embodiments, the mask area setting unit (203) can recognize or identify the identified object image area and form a mask map. For example, the mask area setting unit (203) can classify the object image area (e.g., the object image area (301) of FIG. 3A) identified through the segmentation unit (201) and the background image area (e.g., the background image area (302) of FIG. 3B) based on features (e.g., attributes) such as edges or blobs of the object image area (e.g., the object image area (301) of FIG. 3A) identified through the segmentation unit (201).

[0093] According to one embodiment, the processor (120) may use the deformation unit (205) to deform the mask area (e.g., the mask area (305) of FIG. 3B) generated through the mask area setting unit (203) into a different shape. According to various embodiments, the processor (120) may use the deformation unit (205) to deform the mask area (e.g., the mask area (305) of FIG. 3B) generated through the mask area setting unit (203) into a different outline (e.g., shape) or boundary.

[0094] According to one embodiment, the processor (120) may generate a second image (e.g., the second image (320) of FIG. 3c) that changes a selected object image area (e.g., a specific object (301) of FIG. 3a) into a background image area (e.g., the background image area (302) of FIG. 3a) through generative artificial intelligence (200) based on information related to a first image (e.g., the first image (310) of FIG. 3a) that includes a transformed mask area.

[0095] According to one embodiment, the processor (120) may transmit information related to a first image (e.g., the first image (310) of FIG. 3b and / or the first image (310) of FIG. 8b) including a mask area deformed through the deformable portion (205) to the generative artificial intelligence (200).

[0096] For example, the deformed mask region may include the deformed mask region (315) disclosed in FIG. 5c, FIG. 6, FIG. 7b, FIG. 8b, and / or FIG. 9d.

[0097] According to various embodiments, the processor (120) may match the deformed mask area through the deformer (205) to a first image (e.g., the first image (310) of FIG. 3b and / or the first image (310) of FIG. 8b) and transmit information related to the matched first image (301) and the deformed mask area to the generative artificial intelligence (200).

[0098] According to various embodiments, information related to a mask area deformed through a deformation unit (205) (e.g., a deformed mask area (315) disclosed in FIGS. 5C, 6, 7B, 8B, and / or 9D) may include information that the mask area generated through the mask area setting unit (203) has been deformed so that the generative artificial intelligence (200) cannot estimate or predict it.

[0099] According to one embodiment, the mask area deformed through the deformation unit (205) (e.g., the deformed mask area (315) disclosed in FIGS. 5C, 6, 7B, 8B, and / or 9D) may include an area that is expanded or deformed to be larger or wider than the object image area selected in the first image (e.g., the first image (310) of FIG. 3A) (e.g., the object image area (301) of FIG. 3A). For example, a mask area deformed through a deformation unit (205) (e.g., a deformed mask area (315) disclosed in FIGS. 5C, 6, 7B, 8B, and / or 9D) may include an area in which a mask area generated through a mask area setting unit (203) (e.g., a mask area (305) of FIG. 3B) is larger or wider than an object image area selected in a first image (e.g., a first image (310) of FIG. 3A) (e.g., an object image area (301) of FIG. 3A). For example, the generated mask area (e.g., the mask area (305) of FIG. 3b) and / or the deformed mask area (e.g., the deformed mask area (315) disclosed in FIGS. 5c, 6, 7b, 8b, and / or 9d) may include an area or a deformed area that is expanded by about 5 to 10% of the size and / or width of the object image area (e.g., the object image area (301) of FIG. 3a) selected in the first image (e.g., the first image (310) of FIG. 3a).

[0100] According to one embodiment, a mask area deformed through a deformation unit (205) (e.g., a deformed mask area (315) disclosed in FIGS. 5C, 6, 7B, 8B, and / or 9D) may include an area in which a mask area generated through a mask area setting unit (203) is deformed into a polygonal shape (e.g., a polygonal shape (530) of FIG. 5C). For example, the area deformed into a polygonal shape (e.g., a polygonal shape (530) of FIG. 5C) may include a shape without an interior angle of about 180° or more. For example, the polygon may include a plurality of vertices. For example, the area deformed into a polygonal shape (e.g., a polygonal shape (530) of FIG. 5C) may include an outline or boundary of the polygon.

[0101] According to one embodiment, the mask area deformed through the deformation unit (205) (e.g., the deformed mask area (315) disclosed in FIGS. 5c, 6, 7b, 8b, and / or 9d) may include holes of irregular size (e.g., the holes (610) of FIG. 6) created around the mask area created through the mask area setting unit (203). For example, the mask area deformed through the deformation unit (205) (e.g., the deformed mask area (315) disclosed in FIGS. 5c, 6, 7b, 8b, and / or 9d) may include at least one hole randomly formed at a periphery of the mask area created through the mask area setting unit (203). For example, at least one hole (e.g., hole (610) of FIG. 6) may be formed at a location such that the generative artificial intelligence (200) cannot estimate or predict the mask area (e.g., mask area (305) of FIG. 6) generated through the mask area setting unit (203).

[0102] According to one embodiment, a mask area deformed through a deformation unit (205) (e.g., a deformed mask area (315) disclosed in FIGS. 5C, 6, 7B, 8B, and / or 9D) may include an anchor point (e.g., an anchor point (810) of FIG. 8B) generated within a mask area generated through a mask area setting unit (203).

[0103] According to one embodiment, the processor (120) can check whether the mask area generated through the mask area setting unit (203) includes a shadow image area (e.g., shadow image area (710) of FIG. 7A). For example, if the mask area generated through the mask area setting unit (203) includes a shadow image area (e.g., shadow image area (710) of FIG. 7A), the processor (120) can use the deformation unit (205) to deform the generated mask area and shadow image area generated through the mask area setting unit (203) to have different outlines (e.g., shapes) or boundaries.

[0104] According to various embodiments, the processor (120) may control the overall operation of the electronic device (101) and the signal flow between internal components, and may perform a function of processing data. The processor (120) may include, for example, a central processing unit (CPU), an application processor, and / or a communication processor. The processor (120) may include a single core processor or a multi-core processor. The processor (120) may be composed of at least one processor. For example, the processor (120) may include an application processor (e.g., the main processor (121) of FIG. 1A) and a sensor hub processor (e.g., the auxiliary processor (123) of FIG. 1A). According to various embodiments, the processor (120) may include at least one of an application processor, a microprocessor unit (MPU), and a data processing unit (DPU).

[0105] According to various embodiments, an operation executed in the electronic device (101) may be performed and / or executed by at least one instruction stored in the processor (120) and / or the memory (130). For example, in this document, an embodiment in which the electronic device (101) may perform a certain operation may be interpreted to mean that the operation is performed by at least one instruction stored in the processor (120) and / or the memory (130).

[0106] According to one embodiment, the generative artificial intelligence (200) may be included in the electronic device (101). According to various embodiments, the generative artificial intelligence (200) may also be included in the server (108) disclosed in FIG. 1A. According to various embodiments, the generative artificial intelligence (200) may be included in at least one of the electronic device (101) and the server (108) disclosed in FIG. 1A.

[0107] According to one embodiment, the generative artificial intelligence (200) may generate a second image (e.g., the first image (310) of FIG. 3b) that includes a mask area (e.g., the deformed mask area (315) disclosed in FIGS. 5c, 6, 7b, 8b, and / or 9d) deformed through a deformation unit (205) transmitted through the processor (120) based on information related thereto, in which the selected object image area (e.g., the object image area (301) of FIG. 3a) is changed to a background image area (e.g., the background image area (302) of FIG. 3c)).

[0108] According to one embodiment, the generative artificial intelligence (200) may generate a second image (e.g., the second image (320) of FIG. 3c) in which an object image area (e.g., the object image area (301) of FIG. 3a) is deleted from the first image (e.g., the first image (310) of FIG. 3a) based on information related to a first image (e.g., the first image (310) of FIG. 3a) including a mask area (e.g., the deformed mask area (315) disclosed in FIG. 5c, FIG. 6, FIG. 7b, FIG. 8b, and / or FIG. 9d) deformed through a deformation unit (205) transmitted through the processor (120). A second image (e.g., a second image (320) of FIG. 3c) from which an object image area (e.g., an object image area (301) of FIG. 3a) has been deleted through generative artificial intelligence (200) can be displayed through a display device (260). For example, a second image (e.g., a second image (320) of FIG. 3c) from which an object image area (e.g., an object image area (301) of FIG. 3a) has been deleted through generative artificial intelligence (200) can include a background image area (e.g., a background image area (302) of FIG. 3c) generated in the area from which the object image area (e.g., an object image area (301) of FIG. 3a) has been deleted.

[0109] According to various embodiments, the generative artificial intelligence (200) may receive information transmitted via the processor (120) (e.g., the second image (320) of FIG. 3c). For example, the generative artificial intelligence (200) may receive information related to a first image (e.g., the first image (310) of FIG. 3a) via the processor (120) and a deformed mask area (e.g., the deformed mask area (315) disclosed in FIGS. 5c, 6, 7b, 8b, and / or 9d) via the deformer (205). For example, the generative artificial intelligence (200) may receive, through the processor (120), information related to a first image (e.g., the first image (310) of FIG. 3b) that includes a deformed mask area (e.g., the deformed mask area (315) disclosed in FIGS. 5c, 6, 7b, 8b, and / or 9d) through the deformable portion (205). For example, the generative artificial intelligence (200) may process information transmitted through the processor (120) and then transmit the processed information to the processor (120).

[0110] In one embodiment, the generative artificial intelligence (200) may generate a plan for performing a task based on information received from the processor (120). For example, the plan may be generated by a system based on the generative artificial intelligence (200). For example, the system based on the generative artificial intelligence (200) may include a rule-based system, a neural network-based system (e.g., a feedforward neural network (FNN)) and / or a recurrent neural network (RNN)) system. For example, the plan may be selected from a predefined data set or may be generated in real time in response to a user request (e.g., input). For example, the generative artificial intelligence (200) may select at least one plan from a plurality of predefined plans.

[0111] According to various embodiments, the generative artificial intelligence (200) may transmit the results produced according to the generated plan to the processor (120). The processor (120) may display the results produced according to the plan through the display (260). For example, the generative artificial intelligence (200) may include a learning model learned using an artificial intelligence algorithm. The generative artificial intelligence (200) may include a learning model learned using at least one of machine learning, neural network, genetic, deep learning, and classification algorithms as an artificial intelligence algorithm. For example, the generative artificial intelligence (200) may be implemented based on machine learning, a neural network (NN), or an artificial neural network (ANN). For example, an artificial neural network may include a computational model implemented in software or hardware that mimics the computational ability of a biological system by using a plurality of artificial neurons connected through connection lines.

[0112] FIG. 3A is a diagram schematically illustrating a first image displayed through a display of an electronic device according to an embodiment of the present invention. FIG. 3B is a diagram schematically illustrating a mask area generated in relation to an object image area in a first image of an electronic device according to an embodiment of the present invention. FIG. 3C is a diagram schematically illustrating a second image in which an object image area is deleted and a background image area is filled in a first image of an electronic device according to an embodiment of the present invention.

[0113] According to various embodiments, operations corresponding to the embodiments related to the first image (310) and the second image (320) disclosed below can be performed using the components disclosed in FIG. 2 described above.

[0114] Referring to FIG. 3A, the electronic device (101) may display a first image (310) stored in the memory (130) through the display (260) based on a user input signal. For example, the electronic device (101) may display the first image (310) stored in the memory (130) through a user interface based on a user input signal. For example, the first image (310) may include an object image area (301) and / or a background image area (302). For example, the object image area (301) may include a specific object, such as a human shape. For example, the background image area (302) may include a specific image, such as a building shape. According to various embodiments, the object image area (301) and the background image area (302) are not limited to the above-described examples and may include images of various other shapes.

[0115] According to one embodiment, FIG. 3A may be a screen in which an execution screen of a specific application (e.g., a gallery or photo editor) selected by a user is displayed through a display (260) to edit a first image (310).

[0116] According to one embodiment, while the first image (310) is displayed through the display (260) or the user interface, the processor (120) may receive an input (e.g., an input signal) for selecting an object image area (301) (e.g., a specific object such as a human figure) included in the first image (310). For example, the processor (120) may receive a user input related to a selection signal of the object image area (301) included in the first image (310). For example, a user of the electronic device (101) may select the object image area (301) using a finger or a stylus pen to delete the object image area (301) within the first image (310). For example, the user input may include a touch or press (e.g., a long press) on the object image area (301) within the first image (310). For example, the user input may include an input of a stylus pen to an object image area (301) within a first image (310). For example, the processor (120) may use the segmentation unit (201) to identify an outline (e.g., a shape) or boundary of an object image area (301) (e.g., a specific object such as a human figure) selected by a user of the electronic device (101).

[0117] Referring to FIG. 3B, the processor (120) may generate a mask area (305) (e.g., mask map) related to the object image area (301) identified through the segmentation area (201) using the mask area setting unit (203). For example, the processor (120) may use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) to have a different outline (e.g., shape) or boundary. For example, the processor (120) may use the deformation unit (205) to deform the size of the mask area (305) generated through the mask area setting unit (203) to be larger than the object image area (301). For example, the generated mask area (305) may include an area that is expanded by about 5 to 10% of the size and / or width of the object image area (301) selected in the first image (310). For example, when the generated mask area (305) is deformed, the deformed mask area may include the deformed mask area (315) disclosed in FIG. 5c, FIG. 6, FIG. 7b, FIG. 8b, and / or FIG. 9d. For example, the processor (120) may use the deformation unit (205) to deform the size of the mask area (305) generated through the mask area setting unit (203) to be larger than the object image area (301) or to have various shapes (e.g., an outline or boundary), thereby making it difficult for the generative artificial intelligence (200) to estimate or predict the object image area (301).

[0118] According to one embodiment, the processor (120) may transmit information related to a first image (310) including a deformed mask area (e.g., a deformed mask area (315) disclosed in FIGS. 5C, 6, 7B, 8B, and / or 9D) and / or the generated mask area (305) to the generative artificial intelligence (200) via the deformable portion (205).

[0119] Referring to FIG. 3c, the generative artificial intelligence (200) can generate a second image (320) in which an object image area (301) is deleted from the first image (310) based on information related to a first image (310) including a mask area (e.g., a deformed mask area (315) disclosed in FIG. 5c, FIG. 6, FIG. 7b, FIG. 8b, and / or FIG. 9d) deformed through a deformation unit (205) transmitted through the processor (120) and / or the generated mask area (305). For example, the generative artificial intelligence (200) may generate a second image (320) in which an object image area (301) selected by a user is changed to a background image area (302), based on information related to a first image (310) including a transformed mask area (e.g., a transformed mask area (315) disclosed in FIGS. 5C, 6, 7B, 8B, and / or 9D) transmitted through the processor (120) and / or the generated mask area (305).

[0120] According to one embodiment, the generative artificial intelligence (200) can fill in the area from which the object image area (301) (e.g., a specific object) is deleted with at least a portion of the background image area (302). For example, the generative artificial intelligence (200) can fill in the mask area deformed through the deformation portion (205) with at least a portion of the background image area (302). For example, the generative artificial intelligence (200) can overlap the mask area deformed through the deformation portion (205) with at least a portion of the background image area (302). For example, the generative artificial intelligence (200) can replace and / or change the area from which the object image area (301) is deleted or the mask area (305) with at least a portion of the background image area (302). For example, the second image (320) can include the background image area (302) from which the object image area (301) is deleted. The second image (320) generated through the generative artificial intelligence (200) may be transmitted to the processor (120). The processor (120) may display the second image (320) through the display (260). For example, the processor (120) may delete an object image area (301) (e.g., a specific object such as a human figure) from the first image (310) and obtain a second image (320) in which only a background image area (302) desired by a user of the electronic device (101) is displayed. For example, the second image (320) may include an image in which an object image area (301) selected by the user is deleted and filled with or overlapped with a background image area (302).

[0121] FIG. 4 is a schematic diagram illustrating an example in which an electronic device according to one embodiment of the present invention generates a mask area for an object image area.

[0122] According to one embodiment, when a user of an electronic device (101) selects an object image area (301) (e.g., a specific object such as a human figure) included in a first image (310) to delete the object image area (301), the processor (120) may use the segmentation unit (201) to identify an outline (e.g., a shape) or boundary of the object image area (301) selected by the user of the electronic device (101).

[0123] According to one embodiment, the processor (120) may use the mask area setting unit (203) to generate a mask area (305) related to the outline (e.g., shape) of the identified object image area (301). For example, the processor (120) may use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) to have a different outline (e.g., shape) or boundary. For example, the processor (120) may use the deformation unit (205) to deform the size of the mask area (305) generated through the mask area setting unit (203) to be larger than the object image area (301).

[0124] According to one embodiment, the processor (120) may use the deformation unit (205) to expand an outer region (e.g., an outline region) of the object image region (301) to generate a mask region (305). For example, the mask region (305) may include an area that is expanded by about 5 to 10% of the size and / or width of the object image region (301). For example, if the mask region (305) is expanded to be larger than the object image region (301), the generative artificial intelligence (200) may not be able to estimate or predict the shape of the object image region (301). For example, if the generative artificial intelligence (200) is unable to estimate or predict the shape of the object image region (301), the generative artificial intelligence (200) may not generate an unnecessary image that the user does not want in the area where the object image region (301) is deleted.

[0125] FIGS. 5A to 5C are schematic diagrams illustrating embodiments in which an electronic device according to one embodiment of the present invention transforms an object image area into a polygonal shape.

[0126] According to one embodiment, when a user of an electronic device (101) selects an object image area (301) (e.g., a specific object) included in a first image (310) to delete the object image area (301), the processor (120) can use the segmentation unit (201) to confirm the shape of the object image area (301) selected by the user.

[0127] According to one embodiment, when a user of the electronic device (101) selects an object image area (301) (e.g., a specific object) included in a first image (310) to delete the object image area (301), the processor (120) may use the segmentation unit (201) to check the outline or boundary of the object image area (301) selected by the user.

[0128] Referring to FIG. 5A, the processor (120) may use the mask area setting unit (203) to generate a mask area (305) related to the outline (e.g., shape) of the object image area (301) (e.g., a specific object) identified through the segmentation unit (201). For example, the mask area (305) generated through the mask area setting unit (203) may include a plurality of first points (510) included in each corner of the inner and outer sides of the edge.

[0129] Referring to FIG. 5B, the processor (120) may recognize, by using the deformation unit (205), a plurality of second points (520) located at the outermost side in a mask area (305) including a plurality of first points (510), as points for deformation into a polygonal shape (e.g., a shape having a plurality of outlines). For example, the processor (120) may generate a mask area (315) deformed into a polygonal shape (e.g., an outline) by using a plurality of second points (520) located at the outermost side in a mask area (305) including a plurality of first points (510).

[0130] Referring to FIG. 5c, the processor (120) may use the deformation unit (205) to connect a plurality of second points (520) and deform the mask area (305) into a polygonal shape (530). For example, the polygonal shape (530) may include an outline or boundary connecting a plurality of second points (520) located at the outermost side in the mask area (305) including a plurality of first points (510).

[0131] According to one embodiment, the processor (120) may connect a plurality of second points (520) located at the outermost side of the generated mask area (305) and generate a deformed mask area (315). For example, the deformed mask area (315) may include a polygonal shape (530) (e.g., an outline of the polygon). For example, the mask area (315) deformed into a polygonal shape (530) may include an outline (e.g., a shape) without an interior angle greater than about 180°. For example, the polygon may include an outline or boundary having a plurality of vertices.

[0132] According to one embodiment, when a plurality of second points (520) located at the outermost side of the generated mask area (305) are connected, the generated mask area (305) is described as being changed into a deformed mask area (315) including a polygonal shape (530) (e.g., an outline of the polygon), but is not limited thereto, and may be deformed to have various outlines or boundaries, such as a substantially convex polygonal shape, a semicircular shape, or a circle. For example, when the generated mask area (305) is deformed into a deformed mask area (315) including a polygonal shape (530), the generative artificial intelligence (200) may not be able to estimate or predict the shape of the object image area (301). For example, if the generative artificial intelligence (200) cannot estimate or predict the outline (e.g., shape) of the object image area (301), the generative artificial intelligence (200) may not generate another image that the user does not want in the area where the object image area (301) has been deleted.

[0133] FIG. 6 is a schematic diagram illustrating an example in which an electronic device according to one embodiment of the present invention creates holes of irregular size around a mask area.

[0134] According to one embodiment, when a user of an electronic device (101) selects an object image area (301) to delete the object image area (301) included in the first image (310), the processor (120) can use the segmentation unit (201) to confirm an outline (e.g., shape) of the object image area (301) selected by the user.

[0135] According to one embodiment, the processor (120) may use the mask area setting unit (203) to generate a mask area (305) related to the object image area (301) identified through the segmentation unit (201). For example, the processor (120) may use the mask area setting unit (203) to generate a mask area (305) related to the outline (e.g., shape) of the object image area (301) identified through the segmentation unit (201).

[0136] According to one embodiment, the processor (120) may use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203). For example, the processor (120) may use the deformation unit (205) to create at least one irregularly sized hole (610) around the mask area (305) generated through the mask area setting unit (203) and generate a deformed mask area (315). For example, at least one irregularly sized hole (610) may be formed at a location such that the generative artificial intelligence (200) cannot estimate or predict the mask area (305) generated through the mask area setting unit (203). For example, if a deformed mask area (315) including at least one irregularly sized hole (610) around the mask area (305) is generated, the generative artificial intelligence (200) may not be able to estimate or predict the shape of the object image area (301). For example, if the generative artificial intelligence (200) cannot estimate or predict the shape of the object image area (301), the generative artificial intelligence (200) may not generate a new image that the user does not want in the area where the object image area (301) has been deleted.

[0137] FIG. 7A is a diagram schematically illustrating a first image including an object image area and a shadow image area displayed through a display of an electronic device according to an embodiment of the present invention. FIG. 7B is a diagram schematically illustrating a mask area generated including an object image area and a shadow image area in a first image of an electronic device according to an embodiment of the present invention. FIG. 7C is a diagram schematically illustrating a second image in which an object image area and a shadow image area are deleted and a background image area is filled in a first image of an electronic device according to an embodiment of the present invention.

[0138] Referring to FIG. 7A, the electronic device (101) may display a first image (310) stored in the memory (130) through the display (260) based on a user's input signal. For example, the first image (310) may include an object image area (301), a shadow image area (710), and / or a background image area (302).

[0139] According to one embodiment, FIG. 7a may be a screen in which an execution screen of a specific application (e.g., a gallery or photo editor) selected by a user to edit a first image (310) is displayed through a display (260).

[0140] According to one embodiment, the processor (120) may receive a user input related to selection of an object image area (301) and / or a shadow image area (710) included in a first image (310). For example, a user of the electronic device (101) may select an object image area (301) and / or a shadow image area (710) using a finger or a stylus pen to delete the object image area (301) and / or the shadow image area (710) within the first image (310). For example, the user input may include a touch or press (e.g., a long press) on the object image area (301) and / or the shadow image area (710) within the first image (310). For example, the user input may include an input of a stylus pen on the object image area (301) and / or the shadow image area (710) within the first image (310). For example, the processor (120) can use the segmentation unit (201) to check the outline (e.g., shape) of the object image area (301) and / or shadow image area (710) selected by the user.

[0141] Referring to FIG. 7B, the processor (120) may use the mask area setting unit (203) to generate a mask area (305) related to an outline (e.g., shape) of an object image area (301) and / or a shadow image area (710) identified through the segmentation unit (201). For example, the processor (120) may use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) to have a different outline (e.g., shape or boundary).

[0142] According to one embodiment, the processor (120) may use the deformation unit (205) to form a mask area (315) by deforming the size of the mask area (305) generated through the mask area setting unit (203) to be larger than the object image area (301) and / or the shadow image area (710). For example, the processor (120) may use the deformation unit (205) to generate a mask area (315) by deforming the size of the mask area (305) generated through the mask area setting unit (203) to be larger than the object image area (301) and / or the shadow image area (710), thereby preventing the generative artificial intelligence (200) from estimating or predicting the shape of the object image area (301) and / or the shadow image area (710).

[0143] According to one embodiment, the processor (120) can transmit information related to a first image (310) including a deformed mask area (315) through the deformable portion (205) to the generative artificial intelligence (200).

[0144] Referring to FIG. 7c, the generative artificial intelligence (200) can generate a second image (320) in which the object image area (301) and / or the shadow image area (710) are deleted from the first image (310) based on information related to the first image (310) including the mask area (315) deformed through the deformation unit (205) transmitted through the processor (120).

[0145] According to one embodiment, the generative artificial intelligence (200) can fill in the area where the object image area (301) and / or the shadow image area (710) is deleted with at least a portion of the background image area (302). For example, the generative artificial intelligence (200) can overlap the area where the object image area (301) and / or the shadow image area (710) is deleted with at least a portion of the background image area (302). For example, the generative artificial intelligence (200) can fill in the deformed mask area (315) through the deformer (205) with at least a portion of the background image area (302). For example, the generative artificial intelligence (200) can replace the area where the object image area (301) and / or the shadow image area (710) is deleted or the deformed mask area (315) with at least a portion of the background image area (302). For example, the second image (320) generated through the generative artificial intelligence (200) may be transmitted to the processor (120). The processor (120) may display the second image (320) using the display (260). For example, the processor (120) may delete the object image area (301) and / or the shadow image area (710) from the first image (310) and obtain the second image (320) desired by the user of the electronic device (101).

[0146] FIG. 8A is a diagram schematically illustrating a first image including an object image area and a background image area displayed through a display of an electronic device according to an embodiment of the present invention. FIG. 8B is a diagram schematically illustrating a mask area and anchor points generated for an object image area in a first image of an electronic device according to an embodiment of the present invention. FIG. 8C is a diagram schematically illustrating a second image including a background image area and an object image area deleted from a first image of an electronic device according to an embodiment of the present invention.

[0147] Referring to FIG. 8A, the electronic device (101) can display a first image (310) stored in the memory (130) through the display (260) based on a user's input signal. For example, the first image (310) can include an object image area (301) and / or a background image area (302).

[0148] According to one embodiment, FIG. 8A may be a screen in which an execution screen of a specific application (e.g., a gallery or photo editor) selected by a user is displayed through a display (260) to edit a first image (310).

[0149] According to one embodiment, the processor (120) may receive a user input related to selection of an object image area (301) (e.g., a specific object such as a human figure) included in a first image (310). For example, a user of the electronic device (101) may select an object image area (301) using a finger or a stylus pen to delete the object image area (301) within the first image (310). For example, the user input may include a touch or press (e.g., a long press) on the object image area (301) within the first image (310). For example, the user input may include an input of a stylus pen on the object image area (301) within the first image (310). For example, the processor (120) may use the segmentation unit (201) to identify an outline (e.g., a shape) of an object image area (301) selected by the user.

[0150] Referring to FIG. 8B, the processor (120) may use the mask area setting unit (203) to generate a mask area (305) related to the object image area (301) identified through the segmentation unit (201). For example, the processor (120) may use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) to have a different outline (e.g., shape) and generate a deformed mask area (315).

[0151] According to one embodiment, the processor (120) may use the deformation unit (205) to form (e.g., create) at least one anchor point (810) in the mask area (305) generated through the mask area setting unit (203), and generate a deformed mask area (315). The anchor point (810) may include a hole or a punching. For example, the processor (120) may use the deformation unit (205) to form (e.g., create) at least one anchor point (810) in the mask area (305) generated through the mask area setting unit (203), and generate a deformed mask area (315) including at least one anchor point (810) formed in the generated mask area (305), thereby preventing the generative artificial intelligence (200) from estimating or predicting the object image area (301).

[0152] According to one embodiment, the processor (120) can transmit information related to a first image (310) including a deformed mask area (315) through the deformable portion (205) to the generative artificial intelligence (200).

[0153] Referring to FIG. 8c, the generative artificial intelligence (200) can generate a second image (320) in which an object image area (301) is deleted from the first image (310) based on information related to the first image (310) including a mask area (315) deformed through a deformation unit (205) transmitted through the processor (120).

[0154] According to one embodiment, the generative artificial intelligence (200) can fill in the area from which the object image area (301) is deleted with at least a portion of the background image area (302). For example, the generative artificial intelligence (200) can fill or overlap the deformed mask area (315) with at least a portion of the background image area (302) through the deformer (205). For example, the generative artificial intelligence (200) can replace the area from which the object image area (301) is deleted or the deformed mask area (315) with at least a portion of the background image area (302). For example, the second image (320) can include the background image area (302) from which the object image area (301) is deleted. The second image (320) generated by the generative artificial intelligence (200) can be transmitted to the processor (120). The processor (120) can display the second image (320) using the display (260). For example, the processor (120) can delete the object image area (301) from the first image (310) and obtain a second image (320) in which only the background image area (302) desired by the user of the electronic device (101) is displayed.

[0155] FIG. 9A is a diagram schematically illustrating a first image displayed through a display of an electronic device according to an embodiment of the present invention. FIG. 9B is a diagram schematically illustrating an embodiment of moving an object image area in a first image of an electronic device according to an embodiment of the present invention. FIG. 9C is a diagram schematically illustrating a mask area generated for an object image area in a first image of an electronic device according to an embodiment of the present invention. FIG. 9D is a diagram schematically illustrating an embodiment of transforming a mask area generated in relation to an object image area in a first image of an electronic device according to an embodiment of the present invention into a polygonal shape. FIG. 9E is a diagram schematically illustrating an embodiment of deleting an object image area in a first image of an electronic device and moving the object image area according to an embodiment of the present invention.

[0156] Referring to FIG. 9A, the electronic device (101) may display a first image (310) stored in the memory (130) through the display (260) based on a user's input signal. For example, the first image (310) may include an object image area (301) and / or a background image area (302). For example, the object image area (301) (e.g., a specific object) may be positioned in a first direction (e.g., the -x-axis direction) of the first image (310).

[0157] According to one embodiment, FIG. 9A may be a screen in which an execution screen of a specific application (e.g., a gallery or photo editor) selected by a user is displayed through a display (260) to edit a first image (310).

[0158] According to one embodiment, the processor (120) may receive a user input related to selection and movement of an object image area (301) included in a first image (310). For example, a user of the electronic device (101) may select (e.g., touch or press) and drag the object image area (301) using a finger or a stylus pen to move and delete the object image area (301) in a second direction (e.g., in the x-axis direction) within the first image (310). For example, the user input may include a touch, a press (e.g., a long press), or a drag operation on the object image area (301) within the first image (310). For example, the user input may include an input (e.g., touch and drag) of a stylus pen on the object image area (301) within the first image (310).

[0159] Referring to FIG. 9B, the processor (120) may receive a user input (e.g., a touch and a drag) to move an object image area (301) within a first image (310) from a first direction (e.g., a -x-axis direction) to a second direction (e.g., an x-axis direction). For example, the processor (120) may move the object image area (301) from the first direction (e.g., a -x-axis direction) to the second direction (e.g., an x-axis direction) based on the user input (e.g., a drag) to move the object image area (301) from the first direction (e.g., a -x-axis direction) to the second direction (e.g., an x-axis direction). For example, an object (901) moved in the second direction (e.g., an x-axis direction) may be positioned in the second direction (e.g., an x-axis direction) of the display (260). For example, the processor (120) can use the segmentation unit (201) to check the outline (e.g., shape) of the object image area (301) selected by the user.

[0160] Referring to FIG. 9c, the processor (120) can use the mask area setting unit (203) to create a mask area (305) related to the object image area (301) identified through the segmentation unit (201).

[0161] Referring to FIG. 9D, the processor (120) can use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) to have a different outline (e.g., shape). For example, the processor (120) can use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) into a polygonal shape (530). For example, the polygonal shape (530) can include an outline or boundary of the polygon. For example, the processor (120) can prevent the generative artificial intelligence (200) from estimating or predicting the object image area (301) by using the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) into a deformed mask area (315) including a polygonal shape (530) (e.g., an outline of a polygon).

[0162] According to one embodiment, the processor (120) can transmit information related to a first image (310) including a deformed mask area (315) through the deformable portion (205) to the generative artificial intelligence (200).

[0163] Referring to FIG. 9e, the generative artificial intelligence (200) can generate a second image (320) including an object (901) in which an object image area (301) is deleted from the first image (310) and the object image area (301) is moved in a second direction (e.g., x-axis direction) based on information related to a first image (310) including a mask area (315) that is deformed through a deformation unit (205) transmitted through a processor (120).

[0164] According to one embodiment, the generative artificial intelligence (200) may fill the deleted area of ​​the object image area (301) with at least a portion of the background image area (302) and transmit a second image (320) including the object (901) moved in the second direction (e.g., the x-axis direction) to the processor (120). The processor (120) may display the second image (320) using the display (260).

[0165] FIG. 10 is a flowchart schematically illustrating a method of processing an image using an electronic device according to one embodiment of the present invention.

[0166] The method disclosed below may include, for example, the embodiments disclosed in FIGS. 1A to 9E. The method disclosed below may apply, for example, the embodiments disclosed in FIGS. 2 to 9E. For example, the method disclosed below is not limited to the operations described below, and may perform operations related to at least some of the embodiments disclosed in FIGS. 2 to 9E. In embodiments related to the method disclosed below, the operations may be performed sequentially, but may not necessarily be performed sequentially. For example, the order of the operations may be changed. For example, the order of the operations may be performed in parallel. For example, not all of the operations may be performed, but at least some of the operations may be performed. The operations disclosed below may be performed by instructions stored in the processor (120) and / or the memory (130) of the electronic device (101).

[0167] According to one embodiment, the electronic device (101) can display a first image (310) stored in the memory (130) through the display (260) based on a user's input signal (e.g., selection). For example, the user of the electronic device (101) can execute a specific application (e.g., a gallery or photo editor) and edit the first image (310).

[0168] In operation 1010, the processor (120) can display a first image (310) including an object image area (301) and a background image area (302) through a user interface based on a user input signal.

[0169] According to one embodiment, the processor (120) can display a first image (310) including an object image area (301) and a background image area (302) through the display (260) based on a user's input signal.

[0170] In operation 1020, while the first image (310) is displayed through the display device (260) (e.g., user interface), the processor (120) may receive an input (e.g., a selection signal) for selecting an object image area (301) included within the first image (310).

[0171] In operation 1030, the processor (120) can use the segmentation unit (201) to identify the outline (e.g., shape) of the selected object image area (301) based on the input.

[0172] In operation 1040, the processor (120) can use the mask area setting unit (203) to generate a mask area (305) related to the outline of the identified object image area (301).

[0173] In operation 1050, the processor (120) can use the deformation unit (205) to deform the mask area (305) generated through the mask area setting unit (203) to have a different outline (e.g., shape).

[0174] In operation 1060, the processor (120) can generate a second image (302) that changes the selected object image area (301) into the background image area (302) through generative artificial intelligence (200) based on information related to the first image (310) including the mask area (315) transformed through the deformation unit (205).

[0175] According to one embodiment, the processor (120) can display the second image (320) transmitted through the generative artificial intelligence (200) using the display (260).

[0176] An electronic device (101) according to one embodiment of the present invention may include a display (260), at least one processor (120), and a memory (130) including one or more storage media for storing instructions. According to one embodiment, the instructions, when individually or integrally executed by the at least one processor (120), cause the electronic device (101) to display a first image (310) including an object image area (301) (e.g., a specific object) and a background image area (302) through a user interface, and while the first image (310) is displayed, receive an input for selecting the object image area (301) included in the first image (310), and based on the input, identify an outline of the selected object image area (301), generate a mask area (305) related to the outline of the identified object image area (301), and transform the generated mask area (305) to have a different outline (e.g., a shape), and based on information related to the first image (310) including the transformed mask area (315), generate the selected object image through a generative artificial intelligence (200). It is possible to create a second image (320) by changing the area (301) to the background image area (302).

[0177] According to one embodiment, the generated mask area (305) may include an area that is extended beyond the selected object image area (301).

[0178] According to one embodiment, the deformed mask area (315) may include holes (610) of irregular size.

[0179] According to one embodiment, the instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to determine whether the selected object image area (301) includes a shadow image area (710), and, if the selected object image area (301) includes the shadow image area (710), to transform the selected object image area (301) and the shadow image area (710) to have different outlines.

[0180] According to one embodiment, the generative artificial intelligence (200) may be included in the electronic device (101).

[0181] According to one embodiment, the generative artificial intelligence (200) may be included in a server (108).

[0182] According to one embodiment, the deformed mask area (315) may include an area deformed into a polygonal shape (530).

[0183] According to one embodiment, the modified mask area (315) may include an anchor point (810) formed within the generated mask area (305).

[0184] According to one embodiment, the instructions, when individually or integrally executed by the at least one processor (120), may cause the electronic device (101) to delete the selected object image area (301) through the generative artificial intelligence (200) based on information related to the first image (310) including the transformed mask area (315), and to fill the deleted object image area (301) with the background image area (302).

[0185] According to one embodiment, the instructions, when individually or collectively executed by the at least one processor (120), may cause the electronic device (101) to prevent the generative artificial intelligence (200) from estimating the deformed mask area (315).

[0186] A method for processing an image using an electronic device (101) according to one embodiment of the present invention may include an operation of displaying a first image (310) including an object image area (301) and a background image area (302) through a user interface. According to one embodiment, the method may include an operation of receiving an input for selecting the object image area (301) included in the first image (310) while the first image (310) is displayed. According to one embodiment, the method may include an operation of confirming an outline of the selected object image area (301) based on the input. According to one embodiment, the method may include an operation of generating a mask area (305) related to the outline of the confirmed object image area (301). According to one embodiment, the method may include an operation of modifying the generated mask area (305) to have a different outline. According to one embodiment, the method may include an operation of generating a second image (320) by changing the selected object image area (301) to the background image area (302) through generative artificial intelligence (200) based on information related to the first image (310) including the transformed mask area (315).

[0187] According to one embodiment, the generated mask area (305) may include an area that is extended beyond the selected object image area (301).

[0188] According to one embodiment, the deformed mask area (315) may include holes (610) of irregular size.

[0189] According to one embodiment, the method may further include an operation of checking whether the selected object image area (301) includes a shadow image area (710), and, if the object image area (301) includes a shadow image area (710), an operation of transforming the selected object image area (301) and the shadow image area (710) to have different outlines.

[0190] According to one embodiment, the generative artificial intelligence (200) may be included in the electronic device (101).

[0191] According to one embodiment, the generative artificial intelligence (200) may be included in a server (108).

[0192] According to one embodiment, the deformed mask area (315) may include an area deformed into a polygonal shape (530).

[0193] According to one embodiment, the modified mask area (315) may include an anchor point (810) formed within the generated mask area (305).

[0194] According to one embodiment, the method may further include an operation of deleting the object image area (301) through the generative artificial intelligence (200) based on information related to the first image (310) including the deformed mask area (315), and filling the deleted object image area (301) with the background image area (302).

[0195] According to one embodiment, the method may further include an operation of preventing the generative artificial intelligence (200) from estimating the deformed mask area (315).

[0196] Although the present invention has been described above according to various embodiments of the present invention, it is obvious that changes and modifications made by a person having ordinary skill in the art to which the present invention pertains within a scope that does not deviate from the technical characteristics of the present invention also belong to the present invention.

Claims

1. In an electronic device (101), display (260); at least one processor (120); and A memory (130) comprising one or more storage media storing instructions, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: A first image (310) including an object image area (301) and a background image area (302) is displayed through a user interface, While the first image (310) is displayed, an input is received for selecting the object image area (301) included in the first image (310), Based on the above input, the outline of the selected object image area (301) is confirmed, Create a mask area (305) related to the outline of the object image area (301) confirmed above, The above generated mask area (305) is transformed to have a different outline, An electronic device that generates a second image (320) by changing the selected object image area (301) to the background image area (302) through generative artificial intelligence (200) based on information related to the first image (310) including the transformed mask area (315).

2. In paragraph 1, An electronic device in which the above-mentioned generated mask area (305) includes an area that is extended beyond the above-mentioned selected object image area (301).

3. In paragraph 1 or 2, The above-mentioned modified mask area (315) is an electronic device including a hole (610) of irregular size.

4. In any one of paragraphs 1 to 3, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Check whether the above selected object image area (301) includes a shadow image area (710), An electronic device that, when the selected object image area (301) includes the shadow image area (710), transforms the selected object image area (301) and the shadow image area (710) to have different outlines.

5. In any one of paragraphs 1 to 4, The above generative artificial intelligence (200) is an electronic device included in the above electronic device (101).

6. In any one of paragraphs 1 to 4, The above generative artificial intelligence (200) is an electronic device included in the server (108).

7. In paragraph 1 or 2, The above-mentioned deformed mask area (315) is an electronic device including an area deformed into a polygonal shape (530).

8. In paragraph 1 or 2, The above-described modified mask area (315) is an electronic device including an anchor point (810) formed within the above-described generated mask area (305).

9. In paragraph 1, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: Based on the information related to the first image (310) including the transformed mask area (315), the selected object image area (301) is deleted through the generative artificial intelligence (200). An electronic device that causes the background image area (302) to be filled in the deleted object image area (301).

10. In any one of paragraphs 1 to 9, The above instructions, when individually or collectively executed by the at least one processor (120), cause the electronic device (101) to: An electronic device that prevents the generative artificial intelligence (200) from estimating the transformed mask area (315).

11. A method for processing an image using an electronic device (101), An operation of displaying a first image (310) including an object image area (301) and a background image area (302) through a user interface; An operation of receiving an input for selecting the object image area (301) included in the first image (310) while the first image (310) is displayed; An operation of checking the outline of the selected object image area (301) based on the above input; An operation of generating a mask area (305) related to the outline of the above-mentioned confirmed object image area (301); An operation of transforming the above-mentioned generated mask area (305) to have a different outline; A method including an operation of generating a second image (320) by changing the selected object image area (301) to the background image area (302) through generative artificial intelligence (200) based on information related to the first image (310) including the transformed mask area (315).

12. In paragraph 11, The above generated mask area (305) includes an area that is extended beyond the selected object image area (301), The above-mentioned modified mask area (315) is a method including holes (610) of irregular size.

13. In paragraph 11 or 12, An operation for checking whether the above-mentioned selected object image area (301) includes a shadow image area (710); and A method including an operation of transforming the selected object image area (301) and the shadow image area (710) to have different outlines when the selected object image area (301) includes the shadow image area (710).

14. In any one of paragraphs 11 to 13, The above generative artificial intelligence (200) is a method included in the electronic device (101) or server (108).

15. In paragraph 11, A method further comprising an operation of deleting the selected object image area (301) through the generative artificial intelligence (200) based on information related to the first image (310) including the transformed mask area (315) and filling the deleted object image area (301) with the background image area (302).

Images