Electronic device for storing image, and operation method thereof

Abstract

An electronic device and a method for storing an image are provided. The electronic device may comprise: a display; a memory for storing instructions; and at least one processor including processing circuitry, wherein the instructions are executed by the at least one processor to cause the electronic device to: acquire a plurality of first image frames; acquire a still image; on the basis of at least some of the plurality of first image frames and the still image, acquire at least one image frame in which at least a partial area is generated by using a machine-learned artificial intelligence model; acquire a video on the basis of at least some of the plurality of first image frames and the at least one image frame; store the video in the memory in association with the still image; and play the video when the still image is displayed.

Description

Electronic device for storing images and method of operating the same

[0001] The present disclosure relates to an electronic device for storing an image and a method of operating the same.

[0002] With the recent development of digital technology, various types of electronic devices such as mobile communication terminals, smart phones, tablet PCs (personal computers), notebooks, wearable devices, and digital cameras are being widely used.

[0003] An electronic device including a digital camera can receive an image through a lens, acquire an image using an image sensor, convert the image of a subject into an electrical signal immediately after capturing without a separate development or printing process, acquire a digital signal based on the electrical signal, and store the digital signal in a memory. In addition, the stored image can be displayed through a display. An electronic device including a digital camera can display a preview image generated based on a plurality of image frames of a subject acquired through an image sensor when the camera is running, even if an image is not captured, and store a still image captured in an internal memory according to a shooting request.

[0004] An electronic device can display a screen including a preview image based on an image stream in which image frames are output from an image sensor. The electronic device can store image frames corresponding to the preview image displayed on the screen in memory. For example, the electronic device can store image frames included in the image stream in memory for a defined time period.

[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] An electronic device according to one embodiment of the present invention comprises a display, a memory storing instructions, and at least one processor including processing circuitry, wherein the instructions are collectively or individually executed by the at least one processor, such that the electronic device: acquires a plurality of first image frames, acquires a still image, acquires at least one image frame in which at least a portion of a region is generated using a machine-learned artificial intelligence model based on at least some of the plurality of first image frames or the still image, acquires a moving image based on at least some of the plurality of first image frames and the at least one image frame, stores the moving image in the memory in association with the still image, and when displaying the still image, plays the moving image.

[0007] According to one embodiment of the present invention, an electronic device includes a display, a memory storing instructions, and at least one processor, wherein the instructions are executed by the at least one processor, such that the electronic device: obtains a still image, inputs the still image into a machine-learned captioning artificial intelligence model that outputs at least one of text or a parameter related to the movement of a subject in the image as the image is input, obtains at least one of the text or the parameter related to the subject in the still image as an output of the machine-learned artificial intelligence captioning model, inputs the at least one of the text or the parameter and the still image into a machine-learned generative artificial intelligence model, obtains a moving image including a plurality of virtual image frames based on an output of the generative artificial intelligence model, stores the moving image in the memory in association with the still image, and when displaying the still image, plays the moving image.

[0008] According to one embodiment of the present invention, a method of operating an electronic device may include an operation of storing a plurality of first image frames in a memory of the electronic device, an operation of obtaining a still image, an operation of obtaining at least one image frame in which at least a portion of an area is generated using a machine-learned artificial intelligence model based on at least a portion of the plurality of first image frames or the still image, an operation of obtaining a moving image based on at least a portion of the plurality of first image frames and the at least one image frame, an operation of obtaining a moving image based on the plurality of second image frames, an operation of storing the moving image in the memory in association with the still image, and an operation of playing the moving image when displaying the still image.

[0009] In connection with the description of the drawings, the same or similar reference numerals may be used for the same or similar components.

[0010] FIG. 1 is a block diagram of an electronic device within a network environment according to one embodiment of the present disclosure.

[0011] FIG. 2 is a block diagram of a camera module of an electronic device according to one embodiment of the present disclosure.

[0012] Figure 3 illustrates an example of an electronic device that displays still images and moving images associated with still images.

[0013] FIG. 4 is a diagram illustrating an overview of an electronic device according to an embodiment of the present disclosure, which acquires and displays a moving image based on a plurality of first image frames, or at least a portion of a still image.

[0014] FIG. 5 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to obtain and play a moving image associated with a still image using an artificial intelligence model.

[0015] FIG. 6 is a drawing for explaining an operation of an electronic device according to an embodiment of the present disclosure to obtain a second image frame using a machine-learned artificial intelligence model based on first image frames and a still image.

[0016] FIG. 7 is a drawing for explaining an operation of an electronic device according to one embodiment of the present disclosure to associate a video and a still image and store them as one video file in memory.

[0017] FIG. 8 is a drawing for explaining an operation of an electronic device according to one embodiment of the present disclosure to store a video and a still image as separate image files in separate areas of a memory, respectively.

[0018] FIG. 9 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to identify a subject in a still image and obtain a second image frame that constitutes a moving image based on the identified subject.

[0019] FIG. 10 illustrates an example of an electronic device identifying a subject in a still image according to an embodiment of the present disclosure.

[0020] FIG. 11 illustrates an example of an electronic device according to an embodiment of the present disclosure, wherein a second image frame for composing a video is obtained using a machine-learned artificial intelligence model based on a first image frame among a plurality of first image frames based on an identified subject.

[0021] FIG. 12 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to generate a second image based on whether the identity of an object of interest of a subject in a still image can be maintained in the second image.

[0022] Figure 13 is a drawing for explaining objects of interest related to the subject.

[0023] FIG. 14 is a drawing for explaining a case in which an object of interest set in relation to a subject is excluded from a first image frame according to one embodiment of the present disclosure.

[0024] FIG. 15 is a drawing for explaining a case in which an object of interest set in relation to a subject is included in a first image frame according to one embodiment of the present disclosure.

[0025] FIG. 16 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to determine whether the similarity of an object of interest can be maintained based on characteristic information of the subject.

[0026] FIG. 17 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure to identify a similarity value of an object of interest based on first feature information and second feature information.

[0027] FIG. 18 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to acquire at least one image frame based on motion information identified within a plurality of first image frames.

[0028] FIG. 19 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to select a plurality of second image frames from a plurality of first image frames and acquire at least one image frame.

[0029] FIG. 20 is an example for explaining an operation of an electronic device according to an embodiment of the present disclosure to select a plurality of second image frames from a plurality of first image frames and acquire at least one image frame.

[0030] FIG. 21 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to acquire a second image frame or omit acquisition based on whether an identified area corresponding to a subject is included in a first image frame.

[0031] Figure 22 is a drawing for explaining a case where an identified area corresponding to a subject is included within a first image frame.

[0032] FIG. 23 is a drawing for explaining an operation of an electronic device according to an embodiment of the present disclosure to acquire a still image and a moving image based on a plurality of first image frames acquired from a camera in response to receiving a user input for capturing a still image.

[0033] FIG. 24 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to acquire a video based on a classification to which a scene or subject belongs, or to omit acquisition.

[0034] FIG. 25 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to acquire a video in response to receiving a user input through a UI within an application.

[0035] FIG. 26 is a diagram illustrating an example of an electronic device according to an embodiment of the present disclosure obtaining a second video based on a still image and a first video stored in association with the still image.

[0036] FIG. 27 is a diagram illustrating an example of an electronic device displaying a UI for a command to acquire a moving image based on a still image according to an embodiment of the present disclosure.

[0037] FIG. 28 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure to receive at least one image frame generated using a machine-learned artificial intelligence model stored in a server.

[0038] FIG. 29 is a flowchart of an operation of an electronic device according to an embodiment of the present disclosure, in which a video including a plurality of virtual images generated using a machine-learned artificial intelligence model based on a still image is acquired, and the acquired video is played back.

[0039] FIG. 30 illustrates an example in which an electronic device according to an embodiment of the present disclosure acquires a plurality of virtual images based on a still image using a machine-learned captioning artificial intelligence model and a machine-learned generative artificial intelligence model.

[0040] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present invention. However, the disclosed embodiments may be implemented in various different forms and are not limited to the embodiments described herein.

[0041] FIG. 1 is a block diagram of an electronic device (101) within a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with the electronic device (102) via a first network (198) (e.g., a short-range wireless communication network), or may communicate with at least one of the electronic device (104) or the server (108) via a second network (199) (e.g., a long-range wireless communication network). 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 operations. According to one embodiment, as at least a part of the data processing or operations, the processor (120) may store commands or data received from other components (e.g., a sensor module (176) or a communication module (190)) in a volatile memory (132), process the commands or data stored in the volatile memory (132), and store result data in a non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., a central processing unit or an application processor) or an auxiliary processor (123) (e.g., a graphics processing unit, a neural processing unit (NPU), an image signal processor, a sensor hub processor, or a communication processor) that can operate independently or together with the main processor (121). For example, when the electronic device (101) includes the main processor (121) and the auxiliary processor (123), the auxiliary processor (123) may be configured to use less power than the main processor (121) or to be specialized for a given function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as a part thereof.

[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. According to one embodiment, the display module (160) may include a touch sensor configured to detect a touch, or a pressure sensor configured to measure the intensity of a force generated by the touch.

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

[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 as, for example, 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, for example, by the communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device via the at least one selected antenna. In some embodiments, in addition to the radiator, another component (e.g., a radio frequency integrated circuit (RFIC)) may be additionally formed as a part of the antenna module (197).

[0060] According to various embodiments, the antenna module (197) may form a mmWave antenna module. In one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent a first side (e.g., a bottom side) of the printed circuit board and capable of supporting a designated high-frequency band (e.g., a mmWave band), and a plurality of antennas (e.g., an array antenna) disposed on or adjacent a second side (e.g., a top side or a side side) of the printed circuit board and capable of transmitting or receiving signals in the designated high-frequency band.

[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. 2 is a block diagram (200) illustrating a camera module (180) according to various embodiments. Referring to FIG. 2, the camera module (180) may include a lens assembly (210), a flash (220), an image sensor (230), an image stabilizer (240), a memory (250) (e.g., a buffer memory), or an image signal processor (260). The lens assembly (210) may collect light emitted from a subject that is a target of image capturing. The lens assembly (210) may include one or more lenses. According to one embodiment, the camera module (180) may include a plurality of lens assemblies (210). In this case, the camera module (180) may form, for example, a dual camera, a 360-degree camera, or a spherical camera. Some of the plurality of lens assemblies (210) may have the same lens properties (e.g., angle of view, focal length, autofocus, f-number, or optical zoom), or at least one lens assembly may have one or more lens properties that are different from the lens properties of the other lens assemblies. A lens assembly (210) may include, for example, a wide-angle lens or a telephoto lens.

[0064] The flash (220) can emit light used to enhance light emitted or reflected from a subject. According to one embodiment, the flash (220) can include one or more light-emitting diodes (e.g., red-green-blue (RGB) LED, white LED, infrared LED, or ultraviolet LED), or a xenon lamp. The image sensor (230) can acquire an image corresponding to the subject by converting light emitted or reflected from the subject and transmitted through the lens assembly (210) into an electrical signal. According to one embodiment, the image sensor (230) can include one image sensor selected from among image sensors having different properties, such as an RGB sensor, a black and white (BW) sensor, an IR sensor, or a UV sensor, a plurality of image sensors having the same property, or a plurality of image sensors having different properties. Each image sensor included in the image sensor (230) can be implemented using, for example, a CCD (charged coupled device) sensor or a CMOS (complementary metal oxide semiconductor) sensor.

[0065] The image stabilizer (240) can move at least one lens or image sensor (230) included in the lens assembly (210) in a specific direction or control the operating characteristics of the image sensor (230) (e.g., adjusting the read-out timing, etc.) in response to the movement of the camera module (180) or the electronic device (101) including the same. This allows compensating for at least some of the negative effects of the movement on the captured image. In one embodiment, the image stabilizer (240) can detect such movement of the camera module (180) or the electronic device (101) using a gyro sensor (not shown) or an acceleration sensor (not shown) disposed inside or outside the camera module (180). In one embodiment, the image stabilizer (240) can be implemented as, for example, an optical image stabilizer. The memory (250) can temporarily store at least a portion of the image acquired through the image sensor (230) for the next image processing task. For example, when image acquisition is delayed due to the shutter, or when multiple images are acquired at high speed, the acquired original image (e.g., a Bayer-patterned image or a high-resolution image) is stored in the memory (250), and a corresponding copy image (e.g., a low-resolution image) can be previewed through the display module (160). Thereafter, when a specified condition is satisfied (e.g., a user input or a system command), at least a portion of the original image stored in the memory (250) can be acquired and processed, for example, by the image signal processor (260). According to one embodiment, the memory (250) can be configured as at least a portion of the memory (130) or as a separate memory that operates independently therefrom.

[0066] The image signal processor (260) can perform one or more image processing operations on an image acquired through an image sensor (230) or an image stored in a memory (250). The one or more image processing operations may include, for example, depth map generation, 3D modeling, panorama generation, feature extraction, image synthesis, or image compensation (e.g., noise reduction, resolution adjustment, brightness adjustment, blurring, sharpening, or softening). Additionally or alternatively, the image signal processor (260) may perform control (e.g., exposure time control, read-out timing control, etc.) for at least one of the components included in the camera module (180) (e.g., image sensor (230)). An image processed by the image signal processor (260) may be stored back in the memory (250) for further processing or provided to an external component of the camera module (180) (e.g., memory (130), display module (160), electronic device (102), electronic device (104), or server (108)). According to one embodiment, the image signal processor (260) may include at least one of the processors (120). It may be configured as a separate processor that is configured as a part of the processor (120) or operates independently of the processor (120). If the image signal processor (260) is configured as a separate processor from the processor (120), at least one image processed by the image signal processor (260) may be displayed through the display module (160) as is or after undergoing additional image processing by the processor (120).

[0067] According to one embodiment, the electronic device (101) may include a plurality of camera modules (180), each having different properties or functions. In this case, for example, at least one of the plurality of camera modules (180) may be a wide-angle camera, and at least another may be a telephoto camera. Similarly, at least one of the plurality of camera modules (180) may be a front camera, and at least another may be a rear camera.

[0068] 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.

[0069] 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 component (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.

[0070] 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).

[0071] 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.

[0072] 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.

[0073] 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.

[0074] Figure 3 illustrates an example of an electronic device that displays still images and moving images associated with still images.

[0075] Referring to FIG. 3, an electronic device (e.g., the electronic device (101) of FIG. 1) according to one embodiment may, in response to receiving a user input for acquiring a still image (321) while displaying a preview image acquired through a camera (e.g., the camera module (180) of FIG. 1) through a display, acquire a plurality of image frames (322, 323, 324, 325) associated with the still image (321). An operation of acquiring a plurality of image frames (322, 323, 324, 325) associated with the still image (321) in response to receiving the user input of FIG. 3 may be related to the example illustrated in FIG. 23.

[0076] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) can acquire a plurality of image frames (e.g., 411 to 416 of FIG. 4) through a camera module (e.g., the camera module (180) of FIG. 1, the camera module (180) of FIG. 2). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can acquire an image stream including a plurality of image frames (e.g., 411 to 416 of FIG. 4) through the camera module (e.g., the camera module (180) of FIG. 1)) based on the execution of a camera application for providing a function of capturing an image. The acquired plurality of image frames (e.g., 411 to 416 of FIG. 4) can be displayed on a display (e.g., the display module (160) of FIG. 1) as a preview image in the order in which they were acquired. According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may store a plurality of image frames (e.g., 411 to 416 of FIG. 4) in a memory (e.g., the memory (130) of FIG. 1). For example, the plurality of image frames may be stored in the memory (e.g., the memory (130) of FIG. 1) for a defined time period from the time at which they were acquired. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may store a plurality of image frames (e.g., 411 to 416 of FIG. 4) acquired through a camera module (e.g., the camera module (180) of FIG. 1) in a ring buffer format in the memory (e.g., the memory (130) of FIG. 1).

[0077] According to one embodiment, when a user input for obtaining a still image (e.g., a still image (416) of FIG. 4) is received while an electronic device (e.g., an electronic device (101) of FIG. 1) displays a preview image through a display (e.g., a display module (160) of FIG. 1), the electronic device (e.g., an electronic device (101) of FIG. 1) may obtain a plurality of image frames (e.g., 322, 323, 324, 325 of FIG. 3) for a predetermined period of time from among a plurality of image frames stored in a memory. For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may acquire a plurality of image frames (e.g., 322, 323, 324, 325 of FIG. 3) during a specific period (340) before a time point (330) at which a user input for acquiring a still image (e.g., a still image (321) of FIG. 3) is received. For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may acquire a plurality of image frames during a specific period (350) before and after a time point (330) at which a user input for acquiring a still image is received.

[0078] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may generate a video based on a plurality of image frames acquired within a specified time interval (T) based on a user input for acquiring a still image. For example, the specified time interval (T) may be, but is not limited to, 2 seconds or more and 5 seconds or less.

[0079] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may acquire a video based on a plurality of acquired image frames. For example, the electronic device (e.g., electronic device (101) of FIG. 1) may acquire a video based on a plurality of image frames (322, 323, 324, and 325) among the plurality of acquired image frames during a previous specific period (340) based on a time point (330) at which the user input of FIG. 3 is received.

[0080] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may store an acquired moving image in memory in association with a still image. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may encode some of a plurality of image frames (322, 323, 324, and 325) among a plurality of image frames acquired during a specific period (340) into a moving image and store the encoded image together with a still image (e.g., 321 of FIG. 3) in an extra area of ​​a multimedia file in an image format (e.g., jpg). A method for storing an acquired moving image in memory in association with a still image will be described in detail with reference to FIGS. 7 and 8 as described below.

[0081] Referring to FIG. 3, an electronic device (e.g., the electronic device (101) of FIG. 1) according to one embodiment may display a moving image stored in association with a still image (321) based on an application that displays at least one image. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may execute an application that displays a list of at least one image. On the initial execution screen of the application, at least one object (310) corresponding to at least one image may be displayed at a predetermined interval. The electronic device may display a still image (321) in response to receiving a user input for selecting one object (311) among the at least one object (310).

[0082] An electronic device (e.g., the electronic device (101) of FIG. 1) according to one embodiment may display a UI object (312) for playing a video associated with the still image (321) while displaying a still image (321). When the electronic device (e.g., the electronic device (101) of FIG. 1) receives a specific user input through the UI object, the electronic device (e.g., the electronic device (101) of FIG. 1) may play a video stored in a memory (e.g., the memory (130) of FIG. 1) in association with the still image (321). In the present disclosure, an operation of the electronic device (e.g., the electronic device (101) of FIG. 1) playing a video may correspond to an operation of updating and displaying a plurality of image frames (322, 323, 324, 325) on a display (e.g., the display module (160) of FIG. 1) at predetermined intervals. For example, an electronic device (e.g., an electronic device (101) of FIG. 1) can update and display a plurality of image frames (322, 323, 324, and 325) acquired in association with a still image (321) on a display (e.g., a display module (160) of FIG. 1) at 1 / 60 second intervals.

[0083] Hereinafter, with reference to FIGS. 4 to 30, a method for an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment of the present disclosure to obtain a video or motion photo associated with a still image (e.g., the still image (424) of FIG. 4) will be described. In the present disclosure, a motion photo may be referred to as a multimedia file of an image format (e.g., jpg) that includes a still image (e.g., the still image (424) of FIG. 4) and a video that are stored in a memory (e.g., the memory (130) of FIG. 1) in association with each other.

[0084] In addition, the still image, the first image frame, the first region, the second region, the first part, the second part, the first image, the second image, the subject, or the object of interest, etc., mentioned with reference to the drawings of the present disclosure are mentioned for convenience in explaining the operation of the electronic device (e.g., the electronic device (101) of FIG. 1) and are not limited to the examples illustrated in any one drawing. For example, in the present disclosure, a “first image frame” is used to explain the operation of the electronic device (e.g., the electronic device (101) of FIG. 1) based on one image frame (e.g., the first image frame (413)) among a plurality of first image frames (411 to 415) acquired by the electronic device (101), and the image corresponding to the first image frame (413) is not limited to that illustrated in a specific drawing of the present disclosure.

[0085] FIG. 4 is a diagram illustrating an overview of an electronic device acquiring at least one virtual image and a moving image based on at least a portion of a plurality of image frames or still images and playing the acquired moving image, according to an embodiment of the present disclosure.

[0086] An electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment of the present invention may acquire a plurality of first image frames (411 to 415) and a still image (416) capturing the movement of a subject, as indicated by identification number 410. The plurality of first image frames (411 to 415) and the still image (416) may be acquired through a camera (e.g., the camera module (180) of FIG. 1) as described above with reference to FIG. 3, but is not limited thereto. For example, the plurality of first image frames (411 to 415) and the still image (416) may be acquired from data stored in a memory (e.g., the memory (130) of FIG. 1).

[0087] An electronic device according to one embodiment (e.g., electronic device (101) of FIG. 1) can obtain at least one image frame (421 to 423) based on at least some of a plurality of first image frames (411 to 415), with reference to identification number 420.

[0088] In one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may select at least one image frame (413 to 416) from among a plurality of first image frames (411 to 415). For example, the electronic device may select at least one image frame (413 to 416) based on information about movement of the electronic device (e.g., the electronic device (101) of FIG. 1) during a time period in which the plurality of first image frames (411 to 415) were acquired. The electronic device (e.g., the electronic device (101) of FIG. 1) may select the remaining frames (413 to 416) excluding image frames (411, 412) corresponding to a period in which the magnitude of the movement is greater than or equal to a threshold. An electronic device (e.g., electronic device (101) of FIG. 1) can acquire at least one image frame (421 to 423) based on at least one selected image frame (413 to 416). An operation of selecting at least one image frame (413 to 416) based on information about movement of the electronic device (e.g., electronic device (101) of FIG. 1) will be described in detail with reference to FIGS. 19 and 20.

[0089] For example, an electronic device (e.g., electronic device (101) of FIG. 1) can obtain a second image frame (421) in which at least a portion of an area is generated based on a first image frame (413) and / or a still image (416) among a plurality of first image frames (411 to 415).

[0090] For example, an electronic device (e.g., electronic device (101) of FIG. 1) can obtain a fourth image frame (422) in which at least a portion of an area is generated based on a third image frame (414) and / or a still image (416) among a plurality of first image frames (411 to 415).

[0091] For example, an electronic device (e.g., electronic device (101) of FIG. 1) can obtain a sixth image frame (423) in which at least a portion of an area is generated based on a fifth image frame (415) and / or a still image (416) among a plurality of first image frames (411 to 415).

[0092] In an electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1), at least some of the generated second image frame (421), fourth image frame (422), or sixth image frame (423) may include an image generated using a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (1130) of FIG. 11). For example, the second image frame (421) may include a second image (e.g., the second image (632) of FIG. 6) generated using a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (1130) of FIG. 11). An operation of acquiring at least one image frame (421 to 423) based on at least some of the plurality of first image frames (411 to 415) or still images (416) will be described in detail with reference to drawings subsequent to FIG. 5.

[0093] An electronic device according to an embodiment (e.g., electronic device (101) of FIG. 1), referring to identification number 430, may acquire a moving image based on at least some of a plurality of first image frames (411 to 416), at least one acquired image frame (421 to 423), or at least one still image (424), and play back the acquired moving image in association with the still image.

[0094] An electronic device (e.g., electronic device (101) of FIG. 1) can acquire a video based on at least some of a plurality of first image frames (411 to 416), and at least one of the acquired image frames (421 to 423), a second image frame (421), a fourth image frame (422), and a sixth image frame (423).

[0095] The electronic device (401) in the identification number 430 of FIG. 4 may correspond to the electronic device (101) of FIG. 1 and FIG. 3.

[0096] According to one embodiment, the electronic device (401) can store the acquired video in memory in association with the acquired still image (424). When the electronic device (401) displays the still image (424), it can play the video stored in association with the still image (424). For example, the electronic device (401) can execute an application that displays a list of at least one image. At least one object (431) corresponding to at least one image can be displayed at a predetermined interval on the initial execution screen of the application.

[0097] According to one embodiment, the electronic device (401) may display a still image (424) in a certain area (433) of the display in response to receiving a user input selecting one object (432) from among at least one object (431). The still image (424) may correspond to the still image (416) of the identification number 410.

[0098] The electronic device (401) can display a UI object (434) for playing a video associated with the still image (424) while displaying the still image (424) in a certain area (433) of the display. For example, the UI object (434) can be displayed in a part of the certain area (433).

[0099] When the electronic device (401) receives a specific user input through the UI object (434), the electronic device can play a video stored in the memory (e.g., the memory (130) of FIG. 1) in association with the still image (424). For example, the electronic device can display the second image frame (421), the fourth image frame (422), and the sixth image frame (423) acquired in association with the still image (424) by updating them at predetermined intervals through the display, as indicated by identification numbers 435, 436, and 437. When playback of the video is complete, the electronic device can display the still image (424) again in a certain area (433) or play the video again.

[0100] According to an embodiment, an electronic device (401) can acquire a video based on at least one acquired virtual image (421 to 423), referring to identification numbers 420 and 430 of FIG. 4. The electronic device (401) can play the acquired video based on reception of a user input for selecting a UI object (434). For example, the electronic device (401) can acquire a video composed of a plurality of image frames (435, 436, 437) including a subject based on at least one virtual image (421 to 423) including a subject corresponding to a subject in a still image (424). In FIG. 4, it is illustrated that a video is acquired based on at least one virtual image (421 to 423), but the present invention is not limited thereto. For example, at least some of the plurality of first image frames (411 to 415) stored in a memory (e.g., memory (130) of FIG. 1) may correspond to some of the frames constituting the acquired video.

[0101] FIG. 5 is a flowchart of an operation of an electronic device (e.g., electronic device (101) of FIG. 1) according to an embodiment of the present disclosure, obtaining and playing a moving image associated with a still image (e.g., still image (610) of FIG. 6) using a machine-learned artificial intelligence model (e.g., machine-learned artificial intelligence model (601) of FIG. 6).

[0102] In operation 510, an electronic device according to an embodiment (e.g., electronic device (101) of FIG. 1) may acquire a plurality of first image frames.

[0103] According to one embodiment, the plurality of first image frames mentioned with reference to FIG. 5 may include a plurality of image frames acquired by the electronic device (e.g., the electronic device (101) of FIG. 1) described above with reference to FIG. 3 through a camera module (e.g., the camera module (180) of FIG. 1), but the plurality of first image frames are not limited to those acquired through the camera module (e.g., the camera module (180) of FIG. 1). For example, the plurality of first image frames may include at least one image frame received from an external electronic device (e.g., the electronic device (102) of FIG. 1) using a communication module (e.g., the communication module (190) of FIG. 1). For example, the plurality of first image frames may include at least one image frame received from an external server (e.g., the server (108) of FIG. 1) using a communication module (e.g., the communication module (190) of FIG. 1). For example, the plurality of first image frames may include at least one of the plurality of image frames acquired through a camera module (e.g., the camera module (180) of FIG. 1), at least one image frame received from an external electronic device (e.g., the electronic device (102) or electronic device (104) of FIG. 1), or at least one image frame received from a server (e.g., the server (108) of FIG. 1).

[0104] In operation 520, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may obtain a still image (e.g., the still image (620) of FIG. 6). According to an embodiment, the still image may correspond to a still image (e.g., the still image (321) of FIG. 3) obtained by the electronic device (e.g., the electronic device (101) of FIG. 1) in response to a specific user input while the camera (e.g., the camera module (180) of FIG. 1) is running, as described above with reference to FIG. 3, but is not limited thereto. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may receive a still image (e.g., the still image (620) of FIG. 6) from an external electronic device (e.g., the electronic device (102) of FIG. 1) using a communication module (e.g., the communication module (190) of FIG. 1). For example, an electronic device (e.g., an electronic device (101) of FIG. 1) can receive a still image (e.g., a still image (6200) of FIG. 6) from an external server (e.g., a server (108) of FIG. 1) using a communication module (e.g., a communication module (190) of FIG. 1). For example, in one embodiment, an operation of an electronic device (e.g., an electronic device (101) of FIG. 1) acquiring a still image (e.g., a still image (6200) of FIG. 6) may correspond to an operation of reading a still image (e.g., a still image (6200) of FIG. 6) stored in a memory (e.g., a memory (130) of FIG. 1).

[0105] In FIG. 5, operation 520 is illustrated as being performed after operation 510, but the order in which operations 510 and 520 are performed is not limited thereto. For example, an electronic device (e.g., the electronic device (101) of FIG. 1) may perform operation 520 before operation 510. For example, an electronic device (e.g., the electronic device (101) of FIG. 1) may perform operations 510 and 520 in parallel.

[0106] In operation 530, an electronic device according to an embodiment (e.g., electronic device (101) of FIG. 1) may obtain at least one image frame (e.g., 630 of FIG. 6) in which at least a portion (e.g., 632 of FIG. 6) is generated using a machine-learned artificial intelligence model (e.g., 601 of FIG. 6) based on at least some of a plurality of first image frames (e.g., the plurality of first image frames (e.g., 411 to 415 of FIG. 4) of FIG. 4). For example, an electronic device according to one embodiment (e.g., the electronic device (101) of FIG. 1) may obtain a second image frame (e.g., the second image frame (630) of FIG. 6) using a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (601) of FIG. 6) based on a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4) and a still image (e.g., the still image (620) of FIG. 6). A detailed description of an operation of obtaining the second image frame (e.g., the second image frame (630) of FIG. 6) using a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (601) of FIG. 6) will be described later with reference to FIG. 6.

[0107] For example, an electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1) may, in operation 530, repeatedly perform an operation of obtaining an image frame (e.g., the second image frame (630) of FIG. 6) in which at least a portion of an image frame is generated using a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (601) of FIG. 6) for at least one other image frame (e.g., the third image frame (414) of FIG. 4) excluding the first image frame (610) among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4). For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may obtain a plurality of image frames (e.g., at least one image frame (421 to 423) of FIG. 4) by repeating an operation of obtaining a second image frame (e.g., a second image frame (630) of FIG. 6) using the machine-learned artificial intelligence model (e.g., a machine-learned artificial intelligence model (601) of FIG. 6) described above in operation 530. For example, an electronic device (e.g., the electronic device (101) of FIG. 1) may, in operation 530, repeat an operation of obtaining a second image frame (e.g., the second image frame (630) of FIG. 6) using the machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (601) of FIG. 6) described above, but may omit an operation of obtaining an image frame including a virtual image generated through the machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (601) of FIG. 6) for some of the image frames (e.g., some of the image frames (411, 412) of FIG. 4)) among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4).An example in which an electronic device (e.g., the electronic device (101) of FIG. 1) according to one embodiment omits an operation of obtaining an image frame including a virtual image will be described in detail in the description of FIG. 12, FIG. 19, and FIG. 21 to be described later.

[0108] In operation 540, an electronic device according to an embodiment (e.g., electronic device (101) of FIG. 1) may acquire a video based on at least some of a plurality of first image frames (e.g., a plurality of first image frames (411 to 415) of FIG. 4) and / or at least one image frame acquired in operation 530 (e.g., at least one image frame (421 to 423) of FIG. 4).

[0109] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may acquire a video based on at least some of a plurality of first image frames (e.g., a plurality of first image frames (411 to 415) of FIG. 4) and at least one image frame acquired in operation 530 (e.g., at least one image frame (421 to 423) of FIG. 4). The operation of obtaining a video based on at least some of the plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4) and at least one image frame obtained in operation 530 (e.g., at least one image frame (421 to 423) of FIG. 4) by an electronic device (e.g., the electronic device (101) of FIG. 1) in operation 540 can be understood similarly to the operation of generating a video based on at least one image frame (421 to 423) described above with reference to FIG. 4. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can obtain a video based on at least one image frame (e.g., at least one image frame (421 to 423) of FIG. 4) obtained through a machine-learned artificial intelligence model (601).

[0110] Although FIG. 4 only illustrates an example of obtaining a video based on at least one image frame (e.g., at least one image frame (421 to 423) of FIG. 4) including a virtual image obtained using a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (601) of FIG. 6), the example of FIG. 4 does not exclude a case where an electronic device (e.g., the electronic device (101) of FIG. 1) obtains a video based on at least some of the image frames among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4) in operation 540.

[0111] In the present disclosure, a video is not limited to a video format file. For example, in the present disclosure, a video may be stored together with a still image (620) and constitute part of an image format file. A case in which a video is stored together with a still image (620) and constitutes part of an image format file will be described later in the description of operation 550 below.

[0112] In operation 550, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may store an acquired video in a memory (e.g., the memory (130) of FIG. 1) in association with a still image (620). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may store still image data (e.g., the still image data (711) of FIG. 7) corresponding to a still image (e.g., the still image (620) of FIG. 6)) and the acquired video together with the still image data (e.g., the still image data (711) of FIG. 7) in an extra area excluding an area in which the still image data (e.g., the still image data (711) of FIG. 7) is stored among an area of ​​a multimedia file (e.g., a jpg). A detailed description of an example of storing a video acquired by an electronic device (e.g., electronic device (101) of FIG. 1) in association with a still image (e.g., 620 of FIG. 6) in a memory (e.g., memory (130) of FIG. 1) according to one embodiment will be described later with reference to FIGS. 7 and 8.

[0113] In operation 560, an electronic device according to an embodiment (e.g., electronic device (101) of FIG. 1) may play a stored moving image in association with a still image (e.g., 620 of FIG. 6) when a stored still image (e.g., 620 of FIG. 6) is displayed.

[0114] In operation 560, the operation of the electronic device (e.g., the electronic device (101) of FIG. 1) playing a stored video in association with a still image (e.g., 620 of FIG. 6) when the stored still image (e.g., 620 of FIG. 6) is displayed may be understood in the same manner as the description of the operation of playing a stored video in association with a still image (e.g., the still image (424) of FIG. 4) when the still image (e.g., the still image (424) of FIG. 4) is displayed, as described above with reference to FIGS. 3 and 4. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may play a video in response to receiving a specific user input to play a video stored in a memory (e.g., 130 of FIG. 1) in association with the still image (e.g., 620 of FIG. 6) when displaying the still image (e.g., 620 of FIG. 6). For example, an electronic device (e.g., electronic device (101) of FIG. 1) may display at least some of a plurality of first image frames (e.g., a plurality of first image frames (411 to 415) of FIG. 4) or at least one image frame obtained in operation 530 (e.g., at least one image frame (421 to 423) of FIG. 4) on a display (e.g., 160 of FIG. 1) at predetermined intervals while a video is being played.

[0115] FIG. 6 is a drawing for explaining an operation of an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment of the present disclosure to obtain a second image frame (630) using a machine-learned artificial intelligence model (601) based on a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4) and a still image (620).

[0116] The example illustrated in Fig. 6 can be understood as being related to operation 530 of Fig. 5.

[0117] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may utilize a machine-learned artificial intelligence model (601). For example, the electronic device may obtain output data based on specific input data by utilizing the machine-learned artificial intelligence model (601) stored in a memory (e.g., the memory (130) of FIG. 1). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may transmit specific input data to an external server (e.g., the server (108) of FIG. 1) storing the machine-learned artificial intelligence model (601) by utilizing a communication module (e.g., the communication module (190) of FIG. 1), and may receive output data of the machine-learned artificial intelligence model (601) from the external server (108).

[0118] In the present disclosure, the artificial intelligence (AI) model may include, but is not limited to, a generative AI model. For example, the AI ​​model may include an image captioning AI model. For example, the AI ​​model may include a scene analysis AI model. The generative AI model may refer to an AI model that is machine-learned to generate content based on an input prompt. For example, the generative AI model may include text requesting the generation of an image, or a neural network model that outputs a new image in response to an image input. The image captioning AI model may refer to an AI model that outputs a caption (text) for an input image. The scene analysis AI model may refer to an AI model that classifies the scene of an image into categories.

[0119] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may obtain at least one image frame (630) including a virtually generated image using a machine-learned artificial intelligence model (601). For example, referring to FIG. 6, the electronic device (e.g., the electronic device (101) of FIG. 1) may input a first image frame (610) and a still image (620) among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4) into the machine-learned artificial intelligence model (601) to obtain a second image frame (630). In FIG. 6, the second image frame (630) may correspond to the second image frame (421) of FIG. 4.

[0120] According to one embodiment, at least a portion (632) of the acquired second image frame (630) may include a virtual image generated by a machine-learned artificial intelligence model (601). For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may acquire a second image frame (630) in which an image corresponding to at least a portion of a first image frame (610) is placed in a portion (631) and a virtual image generated by the machine-learned artificial intelligence model (601) is placed in a portion (632) excluding the portion. For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may acquire a second image frame (630) in which a virtual image generated based on feature information of a subject is placed in at least a portion (632).

[0121] In addition, although FIG. 6 illustrates that an image generated by a machine-learned artificial intelligence model (601) is placed in a portion (632) of a second image frame (630) of an electronic device (e.g., the electronic device (101) of FIG. 1), the present invention is not limited thereto. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can obtain an image frame in which the entire region is generated using the machine-learned artificial intelligence model (601). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can obtain an image frame generated without the first image frame (610).

[0122] FIG. 7 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure to associate a video and a still image and store them as a single video file in a memo. FIG. 8 is a diagram illustrating an operation of an electronic device according to an embodiment of the present disclosure to store a video and a still image as separate video files in separate areas of a memory.

[0123] The examples illustrated in FIGS. 7 and 8 may be examples of still images (e.g., still images (620) of FIG. 6) and moving images stored in a memory (e.g., memory (130) of FIG. 1) according to an embodiment of the present invention when an electronic device (e.g., electronic device (101) of FIG. 1) performs operation 550 of FIG. 5.

[0124] Referring to FIG. 7, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may store still image data (711) and acquired video data (721) as files in a single image format (e.g., jpg) in a first area (700) of a memory (e.g., the memory (130) of FIG. 1). For example, data (711) corresponding to a still image (620) may be stored in a first part (710) of a first area (700) of a memory (e.g., the memory (130) of FIG. 1), and data (721) corresponding to an acquired video may be stored in a second part (720) excluding the first part (710). The second part (720) of the first area (700) may be related to an extra area mentioned in the description of operation 550 of FIG. 5. For example, an electronic device (e.g., an electronic device (101) of FIG. 1) can store still image data (711) together with the still image data (711) in an extra area (720) excluding an area (710) in which still image data (711) is stored among multimedia file (e.g., jpg) areas.

[0125] Referring to FIG. 8, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may store data (830) corresponding to a video acquired by the electronic device (e.g., the electronic device (101) of FIG. 1) in a second area (802) different from a first area (801) of a memory (e.g., the memory (130) of FIG. 1) in which still image data (811) is stored. For example, the still image data (811) may be stored in a first part (810) of the first area (801) of the memory (e.g., the memory (130) of FIG. 1)), and the video data (830) may be stored in a second area (802) of the memory (e.g., the memory (130) of FIG. 1). For example, video connection information (821) may be stored in a second portion (820) of a first area (801) of a memory (e.g., memory (130) of FIG. 1). The video connection information (821) may include, but is not limited to, information related to an address value of a second area (802) of a memory (e.g., memory (130) of FIG. 1) in which video data (830) is stored, information about the size of the video data (830), and information about a file name of the video.

[0126] The drawings regarding the memory (e.g., memory (130) of FIG. 1) and data storage structure in FIGS. 7 and 8 are merely examples for explaining a method of storing a moving image in association with a still image (e.g., still image (620) of FIG. 6), and do not limit the structure in which the memory (e.g., memory (130) of FIG. 1), data of a still image (e.g., still image (620) of FIG. 6), or data of a moving image is stored in the memory (e.g., memory (130) of FIG. 1) of the electronic device (e.g., electronic device (101) of FIG. 1) of the present disclosure. In addition, the ratio of the memory space (e.g., memory (130) of FIG. 1) occupied by still image data (711, 811) and video data (721, 830) in FIGS. 7 and 8 is an example for explaining the storage method, and the ratio of the sizes of still image data (711, 811) and video data (721, 830) is not limited as shown in FIGS. 7 and 8.

[0127] FIG. 9 is a flowchart (900) of an operation in which an electronic device (e.g., electronic device (101) of FIG. 1) according to one embodiment of the present disclosure identifies a subject (e.g., subject (1030) of FIG. 10) in a still image (1010) and obtains a second image frame (e.g., second image frame (1150) of FIG. 11) that constitutes a moving image based on the identified subject (e.g., subject (1030) of FIG. 10). FIG. 10 illustrates an example in which an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment of the present disclosure identifies a subject (1030) in a still image (1010). FIG. 11 illustrates an example in which an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment of the present disclosure obtains a second image frame (1150) composing a video by using a machine-learned artificial intelligence model (1130) based on a first image frame (1110) among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4) based on the identified subject (1030).

[0128] Referring to FIGS. 9 and 10 , in operation 910, an electronic device (e.g., the electronic device (101) of FIG. 1 ) according to an embodiment may identify a subject (e.g., a person (1030) of FIG. 10 ) in a still image (1010). For example, the electronic device (e.g., the electronic device (101) of FIG. 1 ) may identify a person (1030) through image recognition in a still image (1010) of a person walking on a beach. In the present disclosure, the subject may be referred to as meaning at least one of objects included in the still image (1010) (e.g., the person (1030) of FIG. 10 ), but is not limited thereto. For example, the subject may be referred to as meaning an area (1020) of the image corresponding to the subject (1030) in the still image.

[0129] Referring to FIGS. 9 and 11, in operation 920, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may identify a virtual area (1120) corresponding to a subject in a first image frame (1110) among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4). An electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may identify, among the virtual areas (1120) corresponding to a subject (e.g., a person) in the first image frame (1110), an area overlapping the first image frame (1110) (e.g., 1121 of FIG. 11) and an area out of the first image frame (1110) (e.g., 1122 of FIG. 11). In the present disclosure, an area (e.g., 1121 in FIG. 11) overlapping with a first image frame (1110) among a virtual area (1120) may be referred to as a 'first part' of the virtual area (1120). An area (e.g., 1122 in FIG. 11) outside the first image frame (1110) among a virtual area (1120) may be referred to as a 'second part' of the virtual area (1120).

[0130] The first image frame (1110) of FIG. 11 may correspond to the first image frame (413) among the plurality of first image frames (411 to 415) of FIG. 4.

[0131] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may identify a virtual area (1120) corresponding to a subject (e.g., the subject (1030) of FIG. 10) based on a first image frame (1110). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may identify a virtual area (1120) corresponding to the subject in the first image frame (1110) based on information about the subject (1030) in the still image (1010) of FIG. 10 identified in operation 920. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may identify a virtual area (1120) for allowing the subject to appear based on the first image frame (1110).

[0132] An electronic device (e.g., electronic device (101) of FIG. 1) according to one embodiment can identify a virtual area (e.g., 1120 of FIG. 11) by comparing a first image frame (e.g., 1110 of FIG. 11) with a still image (e.g., 1125 of FIG. 11). For example, the electronic device (e.g., electronic device (101) of FIG. 1) can determine the size and position of a virtual area (1120) corresponding to a subject in the first image frame (1110) based on information regarding at least a portion of the size, color, or position of the subject (1030) of the still image (1020) identified in operation 920.

[0133] According to one embodiment, the size and position of the area corresponding to the subject of the first image frame (1110) may be determined based on, but is not limited to, specific setting values ​​stored in a memory (e.g., memory (130) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1). For example, the electronic device (e.g., electronic device (101) of FIG. 1) may determine the size and position of the area corresponding to the subject using a machine-learned artificial intelligence model (e.g., 1130 of FIG. 11).

[0134] In Fig. 11, for the convenience of explanation, the identified virtual area (1120) is depicted as a visible area, but this does not mean that the identified virtual area (1120) is limited to a visible area. For example, the identified virtual area (1120) may mean an area corresponding to an image frame (1150) to be generated through an artificial intelligence model (1130) to obtain at least one image frame (e.g., the second image frame (1150) of Fig. 11) based on the first image frame (1110).

[0135] In operation 920 of FIG. 9 and FIG. 11, only an example of an electronic device (e.g., the electronic device (101) of FIG. 1) identifying an area (1120) corresponding to a subject (1030) within a first image frame (1110) according to an embodiment is described, but is not limited thereto. For example, in operation 920, the electronic device (e.g., the electronic device (101) of FIG. 1) may repeatedly perform an operation of identifying an area corresponding to a subject (1030) for at least some of a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4).

[0136] According to one embodiment, at least some of the identified virtual regions (1120) may include regions (1122) that fall outside the first image frame (1110).

[0137] Referring to FIGS. 9 and 11, in operation 930, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may acquire a first image (1141) corresponding to a first portion (1121) of an identified virtual area (1120) included in a first image frame (1110). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may identify a first image (1141) corresponding to a first portion (1121) that is an area overlapping with the identified virtual area (1120) in the first image frame (1110).

[0138] In FIG. 11, the first portion (1121) is illustrated as being a portion of the identified virtual area (1120), but is not limited thereto. For example, if the identified virtual area (1120) is included in the first image frame (1110), the first portion (1121) may be an area corresponding to the identified virtual area (1120).

[0139] Referring to FIGS. 9 and 11, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may, in operation 940, obtain a second image (1142) through a machine-learned artificial intelligence model (1130) based on a still image (1125) and / or a first image frame (1110). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may obtain a second image (1142) based on an output obtained by inputting the still image (1125) and the first image frame (1110) into the machine-learned artificial intelligence model (1130). The machine-learned artificial intelligence model (1130) of FIG. 11 may correspond to the machine-learned artificial intelligence model (601) of FIG. 6. For example, the machine-learned artificial intelligence model (1130) can generate a virtual image (e.g., the second image (1142) of FIG. 11) using at least one of a still image, a first image frame (1110), or a first image (1141) as a prompt, but the input data of the machine-learned artificial intelligence model (1130) is not limited thereto. For example, an electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1) can input the first image frame (1110), the still image (1125), the size of the virtual area (1120), the size of the first part (1121) of the virtual area (1120), and / or the size of the second part (1122) of the virtual area (1120) as a prompt of the machine-learned artificial intelligence model (1130).

[0140] According to one embodiment, the second image (1142) may include an image corresponding to at least a portion of the subject. For example, if a portion of the subject is excluded from the first image frame (1110), the second image (1142) may be an image virtually created of the portion of the subject excluded from the first image frame (1110).

[0141] Referring to FIGS. 9 and 11, in operation 950, an electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may obtain a second image frame (1150) based on the first image (1141) obtained in operation 930 and the second image (1142) obtained in operation 940. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may obtain a second image frame (1150) by placing the first image (1141) obtained in operation 930 in a first area (1151) and placing the second image (1142) obtained in operation 940 in a second area (1152) excluding the first area (1151). The second image frame (1150) of FIG. 11 may correspond to the second image frame (421) of FIG. 4 or the second image frame (630) of FIG. 6.

[0142] FIG. 12 is a flowchart illustrating an operation of an electronic device according to an embodiment of the present disclosure to generate a second image based on whether the identity of an object of interest of a subject in a still image can be maintained in the second image. FIG. 13 is a diagram illustrating an object of interest related to a subject. FIG. 14 is a diagram illustrating a case in which an object of interest set in relation to a subject is excluded from a first image frame according to an embodiment of the present disclosure. FIG. 15 is a diagram illustrating a case in which an object of interest set in relation to a subject is included in a first image frame according to an embodiment of the present disclosure.

[0143] According to one embodiment, an object of interest (1320) may be referred to as at least one object (e.g., an animal in the still image (1310) of FIG. 13) among sub-objects (e.g., an animal's face (1320), an animal's torso (1330), an animal's tail (1340), and animal's legs (1340) in the still image (1310) of FIG. 13) that constitute a subject (e.g., an animal in the still image (1310) of FIG. 13) in a still image (e.g., a still image (1310) of FIG. 13) or a first image frame (e.g., a first image frame (1410) of FIG. 14). For example, hypothetically, in the still image (1310) illustrated in FIG. 13, the object of interest may include an object that determines the identity of the subject, such as the animal's face (1320) in the still image (1310).

[0144] FIGS. 13 to 15 are examples for explaining the flowchart (1200) illustrated in FIG. 12, and the still images, first image frames, first images, second images, subjects, and objects of interest mentioned with reference to FIGS. 13 to 15 can be understood to correspond to the descriptions or examples of the still images, first image frames, first images, second images, subjects, and objects of interest included in drawings other than FIGS. 13 to 15, respectively.

[0145] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may store information about an object of interest (e.g., an object of interest (1320) in a still image (1310)) set for a specific subject (e.g., an animal in a still image (1310) of FIG. 13). For example, if the subject is a human, the electronic device (e.g., the electronic device (101) of FIG. 1) may set the corresponding object of interest to a human face and store it in a memory (e.g., the memory (130) of FIG. 1). For example, if the subject is an animal, the electronic device (e.g., the electronic device (101) of FIG. 1) may set the corresponding object of interest to an animal face and store it in a memory (e.g., the memory (130) of FIG. 1). For example, an electronic device (e.g., electronic device (101) of FIG. 1) can set an object of interest corresponding to a subject being glasses as a glasses frame and store it in a memory (e.g., memory (130) of FIG. 1).

[0146] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may determine, in operation 1210, whether an object of interest (e.g., a human face) of a subject (e.g., a human) should be generated in a second portion (e.g., 1122 of FIG. 11) outside a first image frame (e.g., 1110 of FIG. 11) among the virtual areas (e.g., 1120 of FIG. 11) identified in operation 920 of FIG. 9. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may perform identification of an object of interest (e.g., a human face) using, as input data, the first image frame, or the second portion (e.g., 1122 of FIG. 11) outside the first image frame (e.g., 1110 of FIG. 11) among the virtual areas (e.g., 1120 of FIG. 11)). If the electronic device (e.g., the electronic device (101) of FIG. 1) fails to identify an object of interest (e.g., a human face) within the second portion (e.g., 1122 of FIG. 11), the electronic device may determine that an object of interest (e.g., a human face) should be generated in the second portion (e.g., 1122 of FIG. 11).

[0147] According to one embodiment, referring to FIG. 14, an electronic device (e.g., electronic device (101) of FIG. 1) can indirectly determine whether an object of interest (e.g., an animal's face) should be generated in a second portion (e.g., 1422 of FIG. 14) by determining whether an object of interest (e.g., an animal's face) is included in a first portion (e.g., 1421 of FIG. 14) overlapping a first image frame (e.g., 1410 of FIG. 14) among the identified virtual areas (e.g., 1420 of FIG. 14). For example, an electronic device (e.g., electronic device (101) of FIG. 1) may determine whether an object of interest (e.g., an animal's face) should be generated in a second portion (e.g., 1422 of FIG. 14, 1522 of FIG. 15) based on whether an object corresponding to an object of interest (e.g., an animal's face) exists among sub-objects (e.g., an animal's torso (1440), an animal's chest (1450), an animal's legs (1460) of FIG. 14) of a first image (1430) corresponding to a first portion (e.g., 1421 of FIG. 14, 1521 of FIG. 15) of a virtual area (e.g., 1420 of FIG. 14, 1520 of FIG. 15)) of the first image (1430). For example, an electronic device (e.g., electronic device (101) of FIG. 1) may determine that an object of interest should be created in a second portion (e.g., 1422 of FIG. 14) based on determining that a first portion (e.g., 1421 of FIG. 14) of a virtual area (e.g., 1420 of FIG. 14) does not contain an object of interest. For example, an electronic device (e.g., electronic device (101) of FIG. 1) may determine that an object of interest (1550) set corresponding to an animal as a subject is included in a first image (1540) of FIG. 15.An electronic device (e.g., electronic device (101) of FIG. 1) may determine that an object of interest (e.g., 1550 of FIG. 15) does not need to be generated in a second portion (e.g., 1522 of FIG. 15) based on determining that an object of interest (e.g., 1550 of FIG. 15) is included in a first image (e.g., 1540 of FIG. 15) corresponding to a first portion (e.g., 1521 of FIG. 15) of a virtual area (e.g., 1520 of FIG. 15).

[0148] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may, at operation 1220, acquire a second image (not shown) based on a still image (e.g., still image (1310) of FIG. 13) and / or a first image frame (e.g., first image frame (1510) of FIG. 15) based on determining that an object of interest (e.g., an animal's face) of a subject (e.g., an animal) does not need to be generated in a second portion (e.g., 1522 of FIG. 15) of a virtual area (e.g., 1520 of FIG. 15). Operation 1220 may correspond to operation 940 of FIG. 9 described above. For example, a still image (1310) of FIG. 13 and a second image obtained based on the first image frame (1510) of FIG. 15 may be understood as a virtual image corresponding to a second portion (1522) outside the first image frame (1510) of a separate virtual area (1520), although not shown to avoid repetitive explanation.

[0149] According to one embodiment, in response to determining that an object of interest (e.g., an animal's face) of a subject (e.g., an animal) should be generated in a second portion (e.g., 1422 of FIG. 14) of a virtual area (e.g., 1420 of FIG. 14) in operation 1230, an electronic device (e.g., an electronic device (101) of FIG. 1) may determine whether the identity of an object of interest (e.g., an object of interest (1320) of FIG. 13) included in a still image (e.g., a still image (1310) of FIG. 13) and an object of interest (e.g., an animal's face) included in a second image (not shown) can be maintained.

[0150] In the present disclosure, the 'identity' of an object in an image may refer to an attribute of the object that distinguishes whether objects in different images are the same object. According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may determine whether objects in different images are the same based on whether similarity between objects in different images is maintained. For example, if similarity is maintained between objects in different images, the electronic device (e.g., the electronic device (101) of FIG. 1) may determine that objects in different images are the same. For example, if similarity is lost between objects in different images, the electronic device (e.g., the electronic device (101) of FIG. 1) may determine that objects in different images are different. According to one embodiment, the electronic device (e.g., the electronic device (101) of FIG. 1) may compare feature information of objects and determine whether similarity between objects is maintained based on a similarity value identified. The operation of judging the similarity of objects will be described in detail with reference to Fig. 16.

[0151] According to one embodiment, an object of interest (e.g., an animal's face) to be included in a second image (not shown) may mean an object of interest to be included in the acquired second image (not shown) when the second image (not shown) is acquired through a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (1130) of FIG. 11) based on, for example, a still image (1310) and a first image frame (1410).

[0152] The operation of determining whether the similarity of an object of interest (e.g., an animal face) can be maintained will be described in detail with reference to FIGS. 16 and 17.

[0153] Regarding operation 1240 performed by an electronic device (e.g., electronic device (101) of FIG. 1) according to one embodiment, for convenience, additional reference will be made to FIG. 4, FIG. 10, and FIG. 11.

[0154] According to one embodiment, the electronic device (e.g., the electronic device (101) of FIG. 1) may, in response to determining that identity is lost in operation 1230, omit the operation of acquiring a second image frame (e.g., the second image frame (422) of FIG. 4) and acquire a video. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may omit the operation of acquiring a second image frame (e.g., the second image frame (422) of FIG. 4) and acquire a video.

[0155] An electronic device (e.g., electronic device (101) of FIG. 1) according to one embodiment can determine whether to acquire image frames (e.g., 421 to 423 of FIG. 4) in which at least a portion of an area is generated through a machine-learned artificial intelligence model (e.g., machine-learned artificial intelligence model (1130) of FIG. 11) for each of a plurality of image frames (e.g., 411 to 415 of FIG. 4) by determining whether similarity between objects in a still image (e.g., still image (416) of FIG. 4) and a plurality of image frames (e.g., 411 to 415 of FIG. 4) can be maintained. For example, an electronic device (e.g., the electronic device (101) of FIG. 1) may omit, in operation 1230, an operation (e.g., operations 940 to 950 of FIG. 9) of obtaining a second image frame (e.g., 1150 of FIG. 11) in which at least a portion (e.g., 1122 of FIG. 11) is generated using a machine-learned artificial intelligence model (e.g., 1130 of FIG. 11) based on determining that the similarity between an object of interest (e.g., a human face) included in a still image (e.g., 1125 of FIG. 11) and an object of interest (e.g., a human face) that should be included in a second portion (e.g., 1122 of FIG. 11) out of a first image frame (e.g., 1110 of FIG. 11) of a virtual area (e.g., 1120 of FIG. 11) for a first image frame (e.g., 1110 of FIG. 11) is lost. According to an example, an electronic device (e.g., electronic device (101) of FIG. 1) may, in response to determining that identity can be maintained at operation 1240, acquire a second image (1141) based on the still image (1125), the first image frame (1110), and the feature information of the subject (1030).

[0156] In the present disclosure, for example, feature information may mean, but is not limited to, information for determining similarity between a subject (e.g., 1030 of FIG. 10) extracted from at least some of a plurality of first image frames (e.g., image frames (413 to 415) of some of the plurality of first image frames of FIG. 4) and an object of interest (e.g., a human face, an animal face). For example, the 'feature information' of the subject or object may mean information about the shape, color, size, and / or position of sub-objects (e.g., a human face, an upper garment, a lower garment, a shoe, or a hat) of the subject (e.g., 1030 of FIG. 10).

[0157] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may store feature information about an object of interest (e.g., an animal's face (1320) of FIG. 13) among subjects (e.g., animals) in an image (e.g., 1310 of FIG. 13). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may cluster feature information of objects of interest with which similarity is maintained and store the clustered feature information in a memory (e.g., the memory (130) of FIG. 1), an external electronic device (e.g., the electronic device (102), the electronic device (104) of FIG. 1), or an external server (e.g., the server (108) of FIG. 1). According to one embodiment, the electronic device (e.g., the electronic device (101) of FIG. 1) may store modeling information generated based on clustered feature information for a specific object of interest (e.g., a human face, an animal face).

[0158] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may, at operation 1240, input clustered feature information as input data to a machine-learned artificial intelligence model (e.g., 1130 of FIG. 11) to generate an image (e.g., second image (1142) of FIG. 11) containing an object of interest (e.g., a human face). For example, if an object of interest is included in a second portion (1122) that is outside a first image frame (e.g., 1110 of FIG. 11), an electronic device (e.g., an electronic device (101 of FIG. 1)) may input clustered feature information about an object of interest (e.g., a human face) of a subject (e.g., a human) into a machine-learned artificial intelligence model (e.g., a machine-learned artificial intelligence model (1130 of FIG. 11)) to generate a second image (e.g., a second image (1142 of FIG. 11) that includes an object of interest (e.g., a human face) that maintains similarity with the object of interest (e.g., a human face) included in a still image (e.g., a still image (1125) of FIG. 11). Accordingly, an electronic device (e.g., an electronic device (101 of FIG. 1)) according to an embodiment of the present disclosure may generate a second image (e.g., a second image (1142) of FIG. 11) that includes an object of interest (e.g., a human face) that maintains similarity with the object of interest (e.g., a human face) included in a virtual region (e.g., a virtual region (1120) of FIG. 11) in a first image frame (e.g., a second image (1142) of FIG. 11) among a virtual region (e.g., a virtual region (1120) of FIG. 11). Even if an area corresponding to an object of interest (e.g., a human face, an animal face) whose feature information similarity must be maintained is included in an area (e.g., a second part (1122) of FIG. 11) that is outside the first image frame (1110) of FIG. 11), a second image frame (e.g., a second image frame (1150) of FIG. 11) that includes an object of interest (e.g., a human face) whose similarity to the object of interest (e.g., a human face) in a still image (e.g., a still image (1125) of FIG. 11) is maintained can be generated.

[0159] In the present disclosure, the operation of the electronic device (e.g., the electronic device (101) of FIG. 1) acquiring a second image (1141) in operation 1240 can be understood as additionally considering feature information to acquire the second image (1141) based on the still image (1125) and the first image frame (1110), compared to operation 1220. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can provide feature information of the subject (1030) as at least a part of an input (e.g., a prompt) of a machine-learned artificial intelligence model (1130) to acquire the second image (1141). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can train the artificial intelligence model (1130) using the feature information of the subject (1030) before acquiring the second image (1141).

[0160] FIG. 16 is a flowchart (1600) of an operation for determining whether the similarity of an object of interest can be maintained based on the characteristic information of the subject by an electronic device according to an embodiment of the present disclosure. FIG. 17 is a diagram for explaining an operation for identifying a similarity value of an object of interest based on first characteristic information and second characteristic information by an electronic device according to an embodiment of the present disclosure.

[0161] Action 1600 of FIG. 16 may correspond to action 1230 of FIG. 12.

[0162] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may, in operation 1610, identify a similarity value by comparing first feature information and second feature information.

[0163] For example, the first feature information may correspond to feature information obtained from a subject (e.g., an animal) included in a still image (1710). The second feature information may correspond to feature information obtained from a subject (e.g., a part of an animal) included in a second image (1730). For example, the first feature information may include information about an object of interest (1720) included in the still image (1710). For example, the second feature information may include information about an object of interest (1740) included in the second image (1730).

[0164] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may extract feature points of sub-objects of a subject (1030) from feature information, and identify a similarity value of first feature information and second feature information based on the extracted feature points. In the present disclosure, feature points may be understood as coordinate values ​​determined in correspondence with the positional relationship of sub-objects constituting the subject among the feature information of the subject. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may extract a first feature point determined in correspondence with the positional relationship between human body parts (e.g., eyes, nose, mouth) included in a face among the feature information of the subject (1030) in a still image (1125), and may extract a second feature point in correspondence with the positional relationship between human body parts included in the face of the subject among the second feature information. For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may determine a similarity value by comparing the positions of the extracted first feature point and the second feature point, but the method of determining the similarity value based on the feature information is not limited thereto. For example, referring to FIG. 17, an electronic device (e.g., an electronic device (101) of FIG. 1) may determine a similarity value based on an arrangement of colors included in an object of interest (1720) in a still image (1730) and an object of interest (1740) in a second image (1730).

[0165] In the present disclosure, the still image (1710) and the second image (1730) illustrated in FIG. 17 are for convenience of explanation, and the images or images used to explain the operation are not limited to those illustrated in FIG. 17. For example, the operation 1610 described with reference to the still image (1710) and the second image (1730) of FIG. 17 can be similarly described with reference to the still image (1125) and the second image (1141) of FIG. 11.

[0166] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may determine that the similarity of an object of interest can be maintained if the similarity value is greater than or equal to a set first threshold value in operation 1620. For example, the first threshold value may be a specific value preset within the electronic device (e.g., electronic device (101) of FIG. 1). For example, the first threshold value may be a specific value determined in parallel while operation 1620 is performed.

[0167] FIG. 18 is a flowchart (1800) of an operation of an electronic device according to an embodiment of the present disclosure to acquire at least one image frame based on motion information identified within a plurality of first image frames.

[0168] According to one embodiment, operations 1810 to 1820 in the flowchart (1800) of FIG. 18 may correspond to operation 530 of FIG. 5.

[0169] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may, in operation 1810, identify movement information of a subject within a plurality of image frames. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may identify a change in the motion of the subject between two frames among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may identify the motion of the subject for each of a first image frame (e.g., the first image frame (413) of FIG. 4) and a third image frame (e.g., the third image frame (414) of FIG. 4) among the plurality of first image frames using a deep learning artificial intelligence model. An electronic device (e.g., the electronic device (101) of FIG. 1) can repeatedly perform an operation of identifying a change in motion of a subject between two image frames among a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can identify a change in motion of the subject for each of a third image frame (e.g., the third image frame (414) of FIG. 4) and a fifth image frame (e.g., the fifth image frame (415) of FIG. 4). According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may sequentially, reversely, or in parallel perform an operation of recognizing the movement of a subject through two-dimensional rendering of each image frame to obtain at least one image frame (fusion map), and an operation of identifying a subtle movement between two image frames and performing additional correction based on the identified movement (residual).

[0170] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may, in operation 1820, obtain at least one image frame using an artificial intelligence model based on motion information of an identified subject. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may obtain at least one image frame based on a change in the identified motion of the subject for a first image frame (e.g., 413 of FIG. 4), a third image frame (e.g., 414 of FIG. 4), and each of the two image frames. According to one embodiment, the electronic device (e.g., the electronic device (101) of FIG. 1) may use motion information of the identified subject, a fusion map result between the two image frames, and a residual result when obtaining the at least one image frame in operation 1820. For example, an electronic device (e.g., electronic device (101) of FIG. 1) may input two image frames (e.g., 421 and 423 of FIG. 4), motion information of a subject (e.g., a person) within the two image frames (e.g., 421 and 423 of FIG. 4), a fusion map result between the two image frames (e.g., 421 and 423 of FIG. 4), and a residual result as input data of a machine-learned artificial intelligence model (e.g., 601 of FIG. 6), thereby generating at least one new image frame (e.g., 422 of FIG. 4) including motion information between the two image frames (e.g., 421 and 423 of FIG. 4).

[0171] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may acquire a video by inserting at least one acquired image frame between two selected image frames from among a plurality of first image frames, or before and after the two selected image frames. The subject in the video acquired in this way may appear to move more slowly compared to a case where the video is acquired based on the plurality of first image frames without inserting at least one image frame. In addition, due to the addition of the motion of the subject between two image frames from among the plurality of first image frames, the acquired video may include more sophisticated motion of the subject than before. In addition, the electronic device (e.g., the electronic device (101) of FIG. 1) may supplement the number of image frames for generating the video of the set length by inserting at least one acquired image frame between, or before or after, two image frames of the plurality of first image frames, even if the number of the plurality of first image frames is insufficient to generate the video of the set length by generating the video associated with the still image using at least some of the plurality of first image frames.

[0172] FIG. 19 is a flowchart (1900) of an operation of an electronic device according to an embodiment of the present disclosure to select a plurality of second image frames from among a plurality of first image frames and acquire at least one image frame. FIG. 20 is an example for explaining an operation of an electronic device according to an embodiment of the present disclosure to select a plurality of second image frames from among a plurality of first image frames and acquire at least one image frame.

[0173] Operations 1910 to 1930 illustrated in the flowchart (1900) of FIG. 19 may be related to operation 530 of FIG. 5. For example, operation 530 of the flowchart (500) of FIG. 5 may include operations 1910 to 1930.

[0174] When an electronic device (e.g., the electronic device (101) of FIG. 1) acquires a plurality of first image frames (2021, 2031) through a camera module (e.g., the camera module (180) of FIG. 1), there may be at least one image frame in which the subject is not completely captured among the plurality of first image frames (2021, 2031) due to movement of the electronic device (e.g., the electronic device (101) of FIG. 1) that is not intended by the user.

[0175] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may, in operation 1910, identify information regarding a degree of movement of the electronic device (e.g., the electronic device (101) of FIG. 1) during a first period (2010) during which a plurality of first image frames (2021, 2031) are generated. For example, the first period (2010) may be a period (e.g., 3 s) during which the plurality of first image frames (2021, 2031) acquired by the electronic device (e.g., the electronic device (101) of FIG. 1) are acquired through a camera module (e.g., the camera module (180) of FIG. 1). For example, the degree of movement of the electronic device (e.g., the electronic device (101) of FIG. 1) may be expressed as a number in a specific unit. For example, the degree of movement of an electronic device (e.g., electronic device (101) of FIG. 1) can be expressed as a number greater than or equal to 0 and less than or equal to 10.

[0176] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) can identify a degree of movement of the electronic device (e.g., the electronic device (101) of FIG. 1) through a sensor module (176). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can identify a degree of inclination of the electronic device (e.g., the electronic device (101) of FIG. 1) using a gyro sensor in the sensor module (176). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) can identify information about a movement of the electronic device (e.g., the electronic device (101) of FIG. 1) based on acceleration information acquired through an acceleration sensor (e.g., the sensor module (176) of FIG. 1).

[0177] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) can identify information about a degree of movement of the electronic device (e.g., electronic device (101) of FIG. 1) during a first period (2010) based on motion vectors of a plurality of first image frames (2021, 2031).

[0178] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may recognize a subject within a plurality of first image frames (2021, 2031) and identify information about a degree of movement of the electronic device (e.g., electronic device (101) of FIG. 1) during a first period (2010) based on positional information of the recognized subject.

[0179] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) can identify information about a degree of movement of the electronic device (e.g., electronic device (101) of FIG. 1) during a first period (2010) based on at least one of a sensor module (176), a motion vector, or positional information of a subject.

[0180] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may store information about a degree of movement of the electronic device (e.g., electronic device (101) of FIG. 1) during a first period (2010) corresponding to each of a plurality of first image frames (2021, 2031) in a memory (e.g., memory (130) of FIG. 1).

[0181] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may, in operation 1920, select a plurality of second image frames (2031) acquired during a second period (2030) in which the degree of movement of the identified electronic device (e.g., the electronic device (101) of FIG. 1) is less than or equal to a second threshold. For example, referring to FIG. 20, if the first period (2010) is 5 seconds, the electronic device (e.g., the electronic device (101) of FIG. 1) may select three image frames (2031) acquired during the second period (2030) as the plurality of second image frames (2031) by determining that the degree of movement of the electronic device (e.g., the electronic device (101) of FIG. 1) during the second period (2030) corresponding to 3 seconds is less than the second threshold. For example, under the same premise as the example above, an electronic device (e.g., electronic device (101) of FIG. 1) may determine that the degree of movement of the electronic device (e.g., electronic device (101) of FIG. 1) during a first period (2020) corresponding to 2 seconds exceeds a second threshold value, and may exclude two image frames (2021) acquired during the first period (2020) from a plurality of second image frames (2031).

[0182] According to one embodiment, the second threshold value may be preset and stored in a memory (e.g., memory (130) of FIG. 1) of an electronic device (e.g., electronic device (101) of FIG. 1), but is not limited thereto. For example, the electronic device (e.g., electronic device (101) of FIG. 1) may determine the second threshold value based on the type, size, or position of the subject within a plurality of first image frames (2021, 2031) while performing operation 1910 or operation 1920.

[0183] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may, in operation 1920, delete data corresponding to at least one remaining image frame (2021) excluding the plurality of second image frames based on selection of the plurality of second image frames (2031). As a result, the electronic device (e.g., the electronic device (101) of FIG. 1) may manage memory (e.g., the memory (130) of FIG. 1) space more efficiently.

[0184] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may, in operation 1930, obtain at least one image frame (2040) based on at least some of the selected plurality of second image frames (2031). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may obtain at least one image frame (2040) in which at least a portion of an area is generated through a machine-learned artificial intelligence model (e.g., the machine-learned artificial intelligence model (601) of FIG. 6) based on the selected plurality of second image frames (2031).

[0185] In Fig. 20, only an example is illustrated in which the number of the selected plurality of second image frames (2031) matches the number of at least one acquired image frame (2040), but this is not limited thereto. For example, an operation of generating an image frame including a virtual image corresponding to some of the image frames of the selected plurality of second image frames (2031) by another operation of the present disclosure may be omitted.

[0186] According to one embodiment, when the number (e.g., 3) of the plurality of second image frames (e.g., 2031 of FIG. 20) selected in operation 1920 is less than the set number (e.g., 4) for generating a video, the electronic device (e.g., the electronic device (101 of FIG. 1)) may generate at least one image frame including motion information of a subject (e.g., a person) included in a still image (e.g., 1120 of FIG. 11) based on at least one of the plurality of second image frames (e.g., 2031 of FIG. 20) selected or the still image (e.g., 1120 of FIG. 11), as described in operation 1820 of FIG. 18. According to one embodiment, in operation 1930, an electronic device (e.g., the electronic device (101) of FIG. 1) may acquire at least one image frame (e.g., 2024 of FIG. 20) constituting at least a portion of a video based on a plurality of second image frames (2031) having relatively less shaking and a degree of movement of the electronic device (e.g., the electronic device (101) of FIG. 1) being less than or equal to a second threshold value among a plurality of first image frames (2021, 2031) acquired by the electronic device (e.g., the electronic device (101) of FIG. 1). As a result, the electronic device (e.g., the electronic device (101) of FIG. 1) may acquire a more stabilized video. In operation 1930 of FIG. 19, at least one image frame (e.g., 2024 of FIG. 20) acquired by the electronic device (e.g., the electronic device (101) of FIG. 1) may be associated with at least one image frame (e.g., 421 to 423 of FIG. 4) acquired by the electronic device (e.g., the electronic device (101) of FIG. 1) through operation 530.

[0187] FIG. 21 is a flowchart (2100) of an operation of an electronic device according to an embodiment of the present disclosure to acquire a second image based on whether an identified area corresponding to a subject is included within a first image frame, or to omit acquisition thereof. FIG. 22 is a diagram illustrating a case where an identified area corresponding to a subject is included within a first image frame.

[0188] In FIG. 21, operation 2110 is illustrated as being performed after operation 930 of FIG. 9, but is not limited thereto. For example, an operation of an electronic device (e.g., the electronic device (101) of FIG. 1) acquiring a first image (2230) included in a first image frame (2210) may be performed after operation 2110, or may be performed in parallel with operation 2110.

[0189] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may determine whether the area (2220) identified in operation 2110 is included in the first image frame (2210). For example, referring to FIG. 22, if the identified area (2220) corresponds to a subject (e.g., a person), the electronic device (e.g., electronic device (101) of FIG. 1) may determine that the identified area is included in the first image frame (2210).

[0190] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may perform operation 940 of FIG. 9 based on determining that the area (2220) identified in operation 2110 is outside the first image frame (2210). That is, the electronic device (e.g., electronic device (101) of FIG. 1) may perform an operation of acquiring a second image (e.g., 1142 of FIG. 11) using a machine-learned artificial intelligence model (e.g., 1130 of FIG. 11) based on determining that the identified area (2220) is outside the first image frame (2210).

[0191] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may obtain a second image frame (e.g., 1150 of FIG. 11) based on the first image (2230) based on determining that the area (2220) identified in operation 2120 is included in the first image frame (2210). For example, the electronic device (e.g., electronic device (101) of FIG. 1) may omit an operation (e.g., operation 940 of FIG. 9) of obtaining a second image (e.g., 1130 of FIG. 11) based on determining that the area (2220) identified in operation 2110 is included in the first image frame (2210). For example, an electronic device (e.g., electronic device (101) of FIG. 1) may omit an operation (e.g., operation 940 of FIG. 9) for acquiring a second image (e.g., 1130 of FIG. 11) and acquire a first image (2230) as a second image frame (e.g., 1150 of FIG. 11).

[0192] FIG. 23 is a drawing for explaining an operation of an electronic device according to an embodiment of the present disclosure to acquire a still image and a moving image based on a plurality of first image frames acquired from a camera in response to receiving a user input for capturing a still image.

[0193] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may receive a user input (2330) for acquiring a still image (2340) while displaying a preview image (2310) acquired through a camera (e.g., the camera module (180) of FIG. 1) through a display (160), and in response to this, acquire a plurality of first image frames (2320) associated with the still image (2340). This may be understood in accordance with what has been described with reference to the example illustrated in FIG. 3. The operation of acquiring the plurality of first image frames (2320) in FIG. 23 may correspond to operation 510 of FIG. 5.

[0194] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may store a plurality of acquired first image frames (2320) in a memory (e.g., the memory (130) of FIG. 1). The identification number 2340 illustrated in FIG. 23 is intended to visually represent an example in which the electronic device (e.g., the electronic device (101) of FIG. 1) stores the acquired plurality of first image frames (2320) in a space (2350) of the memory (e.g., the memory (130) of FIG. 1), and the structure of the memory (e.g., the memory (130) of FIG. 1) and the data structure of the plurality of first image frames (2320) are not limited as illustrated in FIG. 23. For example, the plurality of first image frames (2320) may be stored separately in different spaces in the memory (e.g., the memory (130) of FIG. 1).

[0195] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may acquire a still image (2340) in response to receiving a user input (2330) for acquiring a still image (2340) after the execution of a camera (e.g., the camera (180) of FIG. 1). For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may acquire the still image (2340) based on an image frame acquired through a camera (e.g., the camera (180) of FIG. 1) after receiving the user input (2330), but is not limited thereto. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may acquire, as a still image, an image frame acquired before a specific point in time based on the point in time at which the user input (2330) is received. The operation of acquiring the still image (2340) in FIG. 23 may correspond to operation 520 of FIG. 5.

[0196] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may acquire a video in response to receiving a user input (2330). The operation of acquiring the video may include operations 530 and 540 of FIG. 5. For example, the electronic device (e.g., electronic device (101) of FIG. 1) may, in response to receiving a user input (2330), acquire at least one image frame (e.g., 421 to 423 of FIG. 4) in which at least a portion (e.g., 632 of FIG. 6) is generated using a machine-learned artificial intelligence model (e.g., 601 of FIG. 6) based on at least a portion of the acquired plurality of first image frames (2320) or still images (2340). For example, an electronic device (e.g., electronic device (101) of FIG. 1) can acquire a video based on at least some of a plurality of first image frames (2320) and at least one acquired image frame (e.g., 421 to 423 of FIG. 4).

[0197] According to one embodiment, the operation of an electronic device (e.g., the electronic device (101) of FIG. 1) acquiring a moving image in response to receiving a user input (2330) may be performed in parallel with, but is not limited to, the operation of storing a still image (2340) in a memory (e.g., the memory (130) of FIG. 1). For example, the operation of an electronic device (e.g., the electronic device (101) of FIG. 1) acquiring a moving image in response to receiving a user input (2330) may be performed before or after the operation of storing a still image (2340) in a memory (e.g., the memory (130) of FIG. 1).

[0198] FIG. 24 is a flowchart (2400) of an operation of an electronic device according to an embodiment of the present disclosure to acquire a video based on a classification to which a scene or subject belongs, or to omit acquisition.

[0199] In the flowchart (2400) of FIG. 24, it is illustrated that an electronic device (e.g., the electronic device (101) of FIG. 1) performs operation 2410 after operation 520 of the flowchart (500) of FIG. 5, but the timing at which the electronic device performs operation 2410 is not limited thereto. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may perform operation 2410 before operation 520, or may perform operation 2410 in parallel with operation 520.

[0200] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may determine, at operation 2410, a classification to which a scene or subject included in at least one of a plurality of first image frames (e.g., the plurality of first image frames (411 to 415) of FIG. 4) or a still image (e.g., a still image (416) of FIG. 4) belongs.

[0201] For example, an electronic device (e.g., an electronic device (101) of FIG. 1) can determine a category to which a scene or subject of a plurality of first image frames (e.g., a plurality of first image frames (411 to 415) of FIG. 4) or a still image (e.g., a still image (416) of FIG. 4) belongs through a module that analyzes the scene.

[0202] For example, an electronic device (e.g., an electronic device (101) of FIG. 1) can classify a plurality of first image frames (e.g., a plurality of first image frames (411 to 415) of FIG. 4) or a still image (e.g., a still image (416) of FIG. 4) through an artificial intelligence scene analysis model that analyzes a scene. The artificial intelligence scene analysis model can classify an image based on attributes or metadata of at least one input image.

[0203] For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may determine a classification to which a plurality of image frames having a receipt as a subject, and a subject of a still image belong, as 'document', 'paper', 'receipt', etc. For example, an electronic device (e.g., an electronic device (101) of FIG. 1) may determine a classification to which a plurality of image frames including a moving person as a subject (e.g., a plurality of first image frames (411 to 415) of FIG. 4) and a scene of a still image (e.g., a still image (416) of FIG. 4) belong, as 'portrait'. In addition, in the same example, the classification to which the subject belongs may be determined as 'person'.

[0204] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may determine, in operation 2420, whether the classification determined in operation 2410 satisfies a set video acquisition condition. The electronic device (e.g., electronic device (101) of FIG. 1) may determine whether the video acquisition condition is satisfied based on whether the classification for the scene is included in the set classification.

[0205] For example, if the analysis result of a scene corresponding to some of a plurality of first image frames (e.g., 411 to 415 of FIG. 4) and a still image (e.g., 416 of FIG. 4) exceeds the third threshold value set for the degree of movement of the terminal, the electronic device (e.g., the electronic device (101) of FIG. 1) may determine that the acquisition condition of the video is not satisfied.

[0206] For example, an electronic device (e.g., electronic device (101) of FIG. 1) may determine that the subject's movement is not significant and thus does not satisfy the video acquisition conditions when the subject belongs to a category such as 'receipt' or 'book'.

[0207] For example, an electronic device (e.g., electronic device (101) of FIG. 1) may determine that a scene that is classified as a 'portrait' requires a lot of post-processing and thus does not satisfy the video acquisition conditions.

[0208] For example, an electronic device (e.g., electronic device (101) of FIG. 1) may determine that a video acquisition condition is not satisfied because the scene is classified as requiring an operation to synthesize multiple frames when the scene belongs to a category of 'night shooting'.

[0209] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may acquire a video if the video acquisition condition is satisfied as a result of the determination in operation 2420, and store the acquired video in memory in association with a still image.

[0210] This operation may correspond to operations 540 and 550 of FIG. 5.

[0211] According to one embodiment, if the electronic device (e.g., the electronic device (101) of FIG. 1) determines in operation 2420 that the video acquisition condition is not satisfied, in operation 2430, the electronic device may skip acquisition of the video and store the still image in the memory. For example, if the electronic device (e.g., the electronic device (101) of FIG. 1) determines in operation 2420 that the video acquisition condition is not satisfied, the electronic device may not include a video associated with the still image (e.g., 424 of FIG. 4), and may generate a multimedia file including the still image (e.g., 424 of FIG. 4) and store the multimedia file in the memory (e.g., the memory (130) of FIG. 1).

[0212] According to one embodiment, an electronic device (e.g., the electronic device (101) of FIG. 1) may determine a camera shooting mode based on the determination result of operation 2420 in operation 2430. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may determine the camera shooting mode to be a designated camera shooting mode for generating a motion photo based on determining that a video acquisition condition is satisfied in operation 2420. For example, the electronic device (e.g., the electronic device (101) of FIG. 1) may determine the camera shooting mode to be a general camera shooting mode based on determining that a video acquisition condition is not satisfied in operation 2420.

[0213] According to one embodiment, when an electronic device (e.g., the electronic device (101) of FIG. 1) drives a camera (e.g., the camera module (180) of FIG. 1) in a shooting mode to acquire a motion photo and acquires a still image according to a capture command, the electronic device (e.g., the electronic device (101) of FIG. 1) may acquire a still image (e.g., 416 of FIG. 4) with reduced quality compared to when the camera is driven in a general shooting mode. For example, when an electronic device (e.g., electronic device (101) of FIG. 1) operates a camera (e.g., camera module (180) of FIG. 1) in a shooting mode for acquiring a motion photo and acquires a still image (e.g., 416 of FIG. 4) according to a capture command, image processing for quality improvement (e.g., bokeh effect processing, noise processing, sharpening processing, upscaling processing) applied to the still image acquired based on a general camera shooting mode may be omitted.

[0214] An electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1) may, in operation 2430, additionally perform image processing (e.g., bokeh effect processing, noise processing, sharpening processing, upscaling processing) for quality improvement on a still image (e.g., still image (416) of FIG. 4) based on the determination result of operation 2420). For example, when an electronic device (e.g., the electronic device (101) of FIG. 1) acquires a still image (e.g., 416 of FIG. 4) according to a capture command while driving a camera (e.g., the camera module (180) of FIG. 1) in a shooting mode for acquiring a motion photo, the electronic device may perform image processing (e.g., bokeh effect processing, noise processing, sharpening processing, upscaling processing) to improve the quality of the still image (e.g., 416 of FIG. 4) based on a determination that the video acquisition condition is not satisfied in operation 2420.

[0215] An electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may store a still image on which image processing for quality improvement has been performed in a memory. By operation 2420 of the electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment, acquisition of a moving image associated with the still image is not limited. For example, even if the electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment determines that a moving image acquisition condition is not satisfied in operation 2420, the electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may acquire a moving image associated with the still image by a set specific input (e.g., a user input for controlling the electronic device (e.g., the electronic device (101) of FIG. 1) to acquire a moving image when taking a still image) or an additional operation.

[0216] FIG. 25 is a flowchart (2500) of an operation of an electronic device according to an embodiment of the present disclosure to acquire a video in response to receiving a user input through a UI within an application. FIG. 26 is a diagram illustrating an example of an electronic device according to an embodiment of the present disclosure to acquire a second video based on a still image and a first video stored in association with the still image. FIG. 27 is a diagram illustrating an example of an electronic device according to an embodiment of the present disclosure to display a UI for a command to acquire a video based on a still image.

[0217] Referring to FIG. 25, an electronic device (e.g., electronic device (101) of FIG. 1) according to an embodiment may, in operation 2510, execute an application (146) that displays a list of at least one image including a still image (e.g., 431 of FIG. 4). For example, a thumbnail of at least one image stored in a memory may be displayed on the execution screen of the application (146).

[0218] Referring to FIG. 25, an electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1) may, in response to receiving a user input for selecting a still image from a list in operations 2520 and 2530, display a UI for obtaining a video associated with the still image.

[0219] For example, referring to FIG. 26, an electronic device (e.g., electronic device (101) of FIG. 1) may, in response to receiving a user input for selecting a still image (2610) from a list of images (e.g., 431 of FIG. 4), display an object (2620) for editing the still image (2610). The electronic device (e.g., electronic device (101) of FIG. 1) may, in response to receiving a specific user input (e.g., touch) for the object (2620) for editing the still image (2610), display a UI object (2630) for generating a second moving image whose shake is corrected based on a first moving image associated with the still image. For example, the first video may be a video composed of some of the image frames among a plurality of first image frames (e.g., the plurality of first image frames (322 to 325) of FIG. 3) acquired through a camera module (e.g., the camera module (180) of FIG. 1). For example, the second video may be a video acquired through operations corresponding to operations 530 and 540 of FIG. 5 (e.g., the video illustrated in the identification number 430 of FIG. 4).

[0220] For example, referring to FIG. 27, an electronic device (e.g., the electronic device (101) of FIG. 1) may display a still image (2710) upon receiving a user input for selecting the still image (2710). In response to receiving a specific user input (2720), the electronic device (e.g., the electronic device (101) of FIG. 1) may display a UI object (2730) for generating a moving image associated with the still image (2710) based on the still image (2710). For example, the specific user input (2720) may be a set touch (e.g., a long touch) input to an area of ​​the displayed still image (2710).

[0221] Referring to FIG. 25, an electronic device according to an embodiment (e.g., the electronic device (101) of FIG. 1) may receive a user input through a UI and, in response to receiving the user input, obtain a moving image associated with a still image in operations 2540 and 2550.

[0222] For example, referring to FIG. 26, an electronic device (e.g., the electronic device (101) of FIG. 1) may display operations 510 to 550 of FIG. 5 in response to receiving a user input for a UI object (2630) indicated as 'shake correction'. At this time, a plurality of first image frames may correspond to a plurality of image frames constituting a first video, which are stored in a memory (e.g., the memory (130) of FIG. 1) in association with a still image (2610). An electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment of the present disclosure may provide a function that allows a user to determine whether to selectively generate a second video including an image generated using an artificial intelligence model even after storing a still image and a first video associated with the still image in a memory.

[0223] FIG. 28 is a flowchart of an operation of an electronic device (2801) according to an embodiment of the present disclosure receiving at least one image frame (e.g., 630 of FIG. 6) generated using a machine-learned artificial intelligence model (e.g., 601 of FIG. 6) stored in a server (2808).

[0224] The electronic device (2801) of FIG. 28 may correspond to the electronic device (101) of FIG. 1 and the electronic device (401) of FIG. 4. The server (2808) of FIG. 28 may correspond to the server (108) of FIG. 1.

[0225] Operations 2811 and 2812 of the electronic device (2801) of FIG. 28 may correspond to operations 510 and 520 of FIG. 5, respectively. Operations 2813, 2814, and 2815 of the electronic device (2801) of FIG. 28 may correspond to operations 540 and 550 of FIG. 5, respectively. Operation 2815 of the electronic device (2801) of FIG. 28 may correspond to operations including operations 560 and 570 of FIG. 5.

[0226] An electronic device (2801) according to one embodiment can transmit (2821) a plurality of first image frames (e.g., 411 to 415 of FIG. 4) and a still image (e.g., 416 of FIG. 4) to a server (2808). The server (2808) can be an external device capable of storing and controlling a machine-learned artificial intelligence model (e.g., 601 of FIG. 6).

[0227] According to an embodiment, an electronic device (2801) may receive (2822) from a server (2808) at least one image frame obtained by performing operation 2831 corresponding to operation 530 of FIG. 5 . In FIG. 28 , only an example of the electronic device (2801) obtaining at least one image frame from the server (2808) is illustrated, but the present invention is not limited thereto. For example, the electronic device (2801) may receive from the server (2808) a video including at least one image frame obtained from the server (2808).

[0228] FIG. 29 is a flowchart (2900) of an operation of an electronic device according to an embodiment of the present disclosure to acquire a video including a plurality of virtual images generated using a machine-learned artificial intelligence model based on a still image and to play the acquired video. FIG. 30 illustrates an example of an electronic device according to an embodiment of the present disclosure to acquire a plurality of virtual images using a machine-learned captioning artificial intelligence model and a machine-learned generative artificial intelligence model based on a still image.

[0229] Operations 2910, 2940, 2950, ​​and 2960 of FIG. 29 may correspond to operations 520, 550, 560, and 570 of FIG. 5. Hereinafter, operations 2920 and 2930 of FIG. 29 will be described with reference to FIG. 29 and FIG. 30.

[0230] An electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment may, at operation 2920, obtain at least one (3030) of text or parameters related to a subject in a still image (3010) based on an output obtained from a machine-learned captioning artificial intelligence model (3020) of the still image (3010). The machine-learned captioning artificial intelligence model may correspond to the image captioning artificial intelligence model described above with reference to FIG. 5.

[0231] For example, an electronic device (e.g., the electronic device (101) of FIG. 1) can obtain text (3030), such as 'child walking on beach', 'child on the beach', or 'girl walking toward the sea', associated with a still image (3010) using a machine-learned captioning artificial intelligence model (3020). In addition, although not included in the example illustrated in FIG. 30, the electronic device (e.g., the electronic device (101) of FIG. 1) can obtain parameters associated with the still image (3010) using the machine-learned captioning artificial intelligence model (3020). In the present disclosure, the parameters associated with the still image (3010) may be referred to as attribute information regarding an object included in the still image (3010).

[0232] An electronic device according to one embodiment (e.g., electronic device (101) of FIG. 1) may, at operation 2930, obtain a video including a plurality of virtual images (3050) using a machine-learned generative artificial intelligence model (3040).

[0233] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) can input at least one of the text or parameters (3030) obtained in operation 2920 and a still image (3010) into a machine-learned generative artificial intelligence model (3040). The electronic device (e.g., electronic device (101) of FIG. 1) can store the machine-learned generative artificial intelligence model (3040) in a memory (e.g., memory (130) of FIG. 1), but is not limited thereto. For example, 'input' may include an action of an electronic device (e.g., electronic device (101) of FIG. 1) transmitting at least one of the text or parameters (3030) obtained in action 2920, and a still image (3010) to a server (e.g., server (108) of FIG. 1) to utilize a machine-learned generative artificial intelligence model (3040) stored in the server (e.g., server (108) of FIG. 1).

[0234] According to one embodiment, an electronic device (e.g., electronic device (101) of FIG. 1) may acquire a video including a plurality of virtual image frames (3050) based on the output of a machine-learned generative artificial intelligence model (3040). In the present disclosure, the plurality of virtual image frames (3050) may be referred to as including a virtual image frame associated with a still image (3010). The virtual image frame may be referred to as an image frame generated by the artificial intelligence model, rather than an image frame acquired through a camera.

[0235] An electronic device (e.g., the electronic device (101) of FIG. 1) according to an embodiment of the present disclosure can, when a still image (3010) of a specific subject (e.g., a person) is stored in a memory (e.g., the memory (130) of FIG. 1), obtain a moving image including the movement of the subject through at least one artificial intelligence model (3020, 3040) based on a single still image (3010) rather than a plurality of image frames. Accordingly, even if a user obtains only the still image (3010) through a camera module (e.g., the camera module (180) of FIG. 1), the electronic device (e.g., the electronic device (101) of FIG. 1) can subsequently obtain a moving image associated with the still image (3010) to generate a motion photo.

[0236] When a video is acquired based on some of a plurality of image frames acquired through a camera module (e.g., a camera module (180) of FIG. 1) in an electronic device (e.g., an electronic device (101) of FIG. 1), the movement of the electronic device (e.g., an electronic device (101) of FIG. 1) or the movement of a subject before and after a user input for capturing a still image is received is included in the video, so that shaking of the terminal unintended by the user may be included in the video, or a part of the subject may not be displayed in at least a part of the video.

[0237] The present disclosure relates to an electronic device and method for generating a moving image that stabilizes shaking caused by movement of a terminal before and after receiving a user input for capturing a still image, or movement of a subject, in an electronic device that acquires a moving image associated with a still image.

[0238] In one embodiment of the present disclosure, an electronic device may include a display, a memory for storing instructions, and at least one processor including processing circuitry. The instructions may be collectively or individually executed by the at least one processor, such that the electronic device acquires a plurality of first image frames, acquires a still image, acquires at least one image frame in which at least a portion of a region is generated using a machine-learned artificial intelligence model based on at least some of the plurality of first image frames or the still image, acquires a moving image based on at least some of the plurality of first image frames and the at least one image frame, stores the moving image in association with the still image in the memory, and, when displaying the still image, plays the moving image.

[0239] In addition, the instructions may be collectively or individually executed by the at least one processor to cause the electronic device to identify a subject in the still image, identify a virtual area corresponding to the subject in a first image frame among the plurality of first image frames, obtain a first image corresponding to a first part of the identified virtual area included in the first image frame, and, based on the still image and the first image frame, obtain a second image corresponding to a second part of the identified virtual area excluding the first part through the machine-learned artificial intelligence model, and obtain a second image frame in which the first image is disposed in the first area and the second image is disposed in the second area excluding the first area.

[0240] Additionally, the instructions may be collectively or individually executed by the at least one processor to cause the electronic device to determine whether the first image includes an object of interest related to the subject, and in response to determining that the first image includes the object of interest, acquire the second image based on the still image and the first image frame, and in response to determining that the object of interest is excluded from the first image, determine whether identity between the object of interest included in the still image and the object of interest to be included in the second image can be maintained, and in response to determining that the similarity can be maintained, acquire the second image based on the still image, the first image frame, and feature information of the subject, and in response to determining that the similarity is lost, omit acquisition of the second image frame.

[0241] Additionally, the commands may be collectively or individually executed by the at least one processor to cause the electronic device to compare first feature information obtained from a subject included in the still image with second feature information obtained from a subject included in the second image to identify a similarity value, and determine that the similarity of the object of interest can be maintained if the similarity value is equal to or greater than a set first threshold value.

[0242] Additionally, the instructions may be executed by the at least one processor to cause the electronic device to identify, based on the still image and at least one image frame among the first plurality of image frames, motion information of a subject within the first plurality of image frames, and to obtain, based on the motion information of the identified subject, at least one image frame in which at least a portion of the region is generated through the machine-learned artificial intelligence model.

[0243] Additionally, the instructions may be executed by the at least one processor to cause the electronic device to identify, based on the first plurality of image frames, information about a degree of movement of the electronic device during a first period during which the first plurality of image frames were generated, select a plurality of second image frames obtained during a second period during which the identified degree of movement of the electronic device is less than or equal to a second threshold value among the first plurality of image frames, and obtain the at least one image frame based on at least some of the selected plurality of second image frames.

[0244] Additionally, the instructions may be collectively or individually executed by the at least one processor to cause the electronic device to determine whether the identified area is included in the first image frame, acquire the second image based on determining that at least a portion of the identified area is outside the first image frame, acquire the second image frame based on the first image and the second image, omit acquisition of the second image based on determining that the identified area is included in the first image frame, and acquire the second image frame based on the first image.

[0245] Additionally, the electronic device may further include a camera.

[0246] Additionally, the instructions may be executed by the at least one processor to cause the electronic device to obtain the plurality of first image frames based on at least a portion of a preview image obtained through the camera and displayed through the display, receive a user input for capturing the still image, and obtain the still image and the moving image in response to receiving the user input.

[0247] Additionally, the instructions may be executed by the at least one processor to cause the electronic device to determine a classification to which a scene or subject included in at least one of the plurality of first image frames or the still image belongs, acquire the moving image if the classification satisfies a moving image acquisition condition, and store the moving image in the memory in association with the still image, and skip acquisition of the moving image and store the still image in the memory if the classification does not satisfy the moving image acquisition condition.

[0248] Additionally, the instructions may be executed by the at least one processor to cause the electronic device to: execute an application that displays a list of at least one video including the still image; and, in response to receiving a user input for selecting the still image from the list, display a UI for obtaining the video; and obtain the video in response to a user input through the UI.

[0249] In addition, the electronic device further includes a wireless communication module, and the instructions are executed by the at least one processor to cause the electronic device to transmit the plurality of first image frames and the still image to an external server storing the machine-learned artificial intelligence model using the wireless communication module, and to receive the at least one image frame or the moving image from the server.

[0250] In one embodiment of the present disclosure, an electronic device includes a display, a memory storing commands, and at least one processor, wherein the commands are executed by the at least one processor, such that the electronic device obtains a still image, inputs the still image into a machine-learned captioning artificial intelligence model that outputs at least one of text or a parameter related to the movement of a subject in the image as the image is input, obtains at least one of the text or the parameter related to the subject in the still image as an output of the machine-learned artificial intelligence captioning model, inputs the at least one of the text or the parameter and the still image into a machine-learned generative artificial intelligence model, obtains a moving image including a plurality of virtual image frames based on an output of the generative artificial intelligence model, stores the moving image in the memory in association with the still image, and when displaying the still image, plays the moving image.

[0251] In one embodiment of the present disclosure, a method of operating an electronic device may include an operation of storing a plurality of first image frames in a memory of the electronic device, an operation of obtaining a still image, an operation of obtaining at least one image frame in which at least a portion of the image is generated using a machine-learned artificial intelligence model based on at least some of the plurality of first image frames or the still image, an operation of obtaining a moving image based on at least some of the plurality of first image frames and the at least one image frame, an operation of obtaining a moving image based on the plurality of second image frames, an operation of storing the moving image in the memory in association with the still image, and an operation of playing the moving image when displaying the still image.

[0252] In addition, the operation of obtaining at least one image frame may include an operation of identifying a subject in the still image, an operation of identifying a virtual area corresponding to the subject in a first image frame among the plurality of first image frames, an operation of obtaining a first image corresponding to a first part of the identified virtual area included in the first image frame, an operation of obtaining a second image corresponding to a second part of the identified virtual area excluding the first part through the machine-learned artificial intelligence model based on the still image and the first image frame, and an operation of obtaining a second image frame in which the first image is arranged in the first area and the second image is arranged in the second area excluding the first area.

[0253] In addition, the method further includes an operation of determining whether an object of interest related to the subject is included in the first image, an operation of obtaining the second image based on the still image and the first image frame in response to determining that the object of interest is included in the first image, an operation of determining whether identity between the object of interest included in the still image and the object of interest included in the second image can be maintained in response to determining that the object of interest is excluded from the first image, and an operation of obtaining the second image based on the still image, the first image frame, and feature information of the subject in response to determining that the similarity can be maintained, and an operation of obtaining the second image based on the subject in response to determining that the similarity is lost can be omitted.

[0254] In addition, the operation of determining whether the similarity can be maintained may include comparing first feature information obtained from the subject included in the first image frame with second feature information of the subject included in the second image to identify a similarity value, and determining that the similarity of the object of interest can be maintained when the similarity value is equal to or greater than a set first threshold value.

[0255] In addition, the operation of determining whether the identity can be maintained may include an operation of determining a similarity value by comparing first feature information obtained from a subject included in the still image with second feature information obtained from a subject included in the second image, and an operation of determining that the similarity can be maintained if the similarity value is greater than or equal to a first threshold value.

[0256] In addition, the operation of obtaining the at least one virtual image may include an operation of identifying motion information of a subject within the plurality of first image frames based on the still image and at least one image frame among the plurality of first image frames, and an operation of obtaining the at least one virtual image through the machine-learned artificial intelligence model based on the motion information of the identified subject.

[0257] In addition, the operation of obtaining the at least one virtual image may include an operation of identifying information about a degree of movement of the electronic device during a first period during which the first plurality of image frames were generated, based on the first plurality of image frames, an operation of selecting a plurality of second image frames obtained during a second period during which the identified degree of movement of the electronic device is less than or equal to a second threshold value among the first plurality of image frames, and an operation of obtaining the at least one image frame based on at least some of the selected plurality of second image frames.

[0258] In addition, the operation of acquiring the video may include: an operation of acquiring the plurality of first image frames based on at least a portion of a preview image acquired through a camera of the electronic device and displayed through the display, an operation of receiving a user input for capturing the still image, and an operation of acquiring the video in response to receiving the user input.

[0259] The methods according to the embodiments described in the claims or specification of the present disclosure may be implemented in the form of hardware, software, or a combination of hardware and software.

[0260] When implemented in software, a computer-readable storage medium storing one or more programs (software modules) may be provided. The one or more programs stored in the computer-readable storage medium are configured for execution by one or more processors within an electronic device. The one or more programs include instructions that cause the electronic device to execute methods according to embodiments described in the claims or specification of the present disclosure.

[0261] In the present disclosure, the functions or operations performed by the electronic device may be performed by one or more processors executing one or more instructions stored in a memory. The functions or operations of the electronic device mentioned in the present disclosure may be performed by one processor executing one or more instructions, or may be performed by a combination of multiple processors executing one or more instructions. The processor mentioned in the present disclosure may be understood to include a circuit for performing operations or controlling other components of the electronic device. For example, the one or more processors may include a central processing unit (CPU), a microprocessor unit (MPU), an application processor (AP), a communication processor (CP), a neural processing unit (NPU), a system on a chip (SoC), or an integrated circuit (IC) configured to execute one or more instructions. The one or more processors may be configured to perform the operations of the electronic device described above.

[0262] In the present disclosure, a program (software module, software) may be stored in a non-volatile memory including a random access memory (RAM), a flash memory, a read only memory (ROM), an electrically erasable programmable read only memory (EEPROM), a magnetic disc storage device, a compact disc ROM (CD-ROM), digital versatile discs (DVDs) or other forms of optical storage devices, a magnetic cassette. Or, it may be stored in a memory formed by a combination of some or all of these. The memory may be formed by a single storage medium, or may be formed by a combination of a plurality of storage media. The one or more commands may be stored in a single storage medium, or may be distributed and stored in a plurality of storage media.

[0263] Additionally, the program may be stored on an attachable storage device that is accessible via a communication network such as the Internet, an intranet, a local area network (LAN), a wide LAN (WLAN), or a storage area network (SAN), or a combination thereof. Such a storage device may be connected to a device performing an embodiment of the present disclosure via an external port. Additionally, a separate storage device on the communication network may be connected to a device performing an embodiment of the present disclosure.

[0264] In the specific embodiments of the present disclosure described above, components included in the disclosure are expressed in the singular or plural form, depending on the specific embodiment presented. However, the singular or plural expressions are selected to suit the presented situation for convenience of explanation, and the present disclosure is not limited to singular or plural components. Components expressed in the plural form may be composed of singular elements, or components expressed in the singular form may be composed of plural elements.

[0265] Additionally, in the present disclosure, terms such as “part”, “module”, etc. may refer to a hardware component such as a processor or circuit, and / or a software component executed by a hardware component such as a processor.

[0266] A "component" or "module" may be implemented by a program stored in an addressable storage medium and executed by a processor. For example, a "component" or "module" may be implemented by components such as software components, object-oriented software components, class components, and task components, as well as processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.

[0267] The specific implementations described in this disclosure are merely exemplary and do not limit the scope of the present disclosure in any way. For the sake of brevity, descriptions of conventional electronic components, control systems, software, and other functional aspects of the systems may be omitted.

[0268] Additionally, in the present disclosure, “comprising at least one of a, b, or c” may mean “comprising only a, including only b, including only c, or including a combination of two or more (including a and b, including b and c, including a and c, or including all of a, b, and c).

[0269] While the detailed description of this disclosure has described specific embodiments, it should be understood that various modifications are possible without departing from the scope of this disclosure. Therefore, the scope of this disclosure should not be limited to the described embodiments, but should be defined not only by the scope of the claims described below, but also by equivalents thereof.

Claims

1. In electronic devices, display; memory that stores commands; and comprising at least one processor comprising processing circuitry; The instructions are collectively or individually executed by the at least one processor, such that the electronic device: Acquire multiple first image frames, Acquire still images, Obtaining at least one image frame in which at least a portion of a region is generated using a machine-learned artificial intelligence model based on at least a portion of the plurality of first image frames or still images, Obtaining a video based on at least some of the plurality of first image frames and at least one image frame, storing the above video in the above memory in association with the above still image, and An electronic device that, when displaying the still image, causes the moving image to be played.

2. In paragraph 1, The above instructions are collectively or individually executed by the at least one processor, so that the electronic device: Identifying a subject within the still image, Identifying a virtual area corresponding to the subject within a first image frame among the plurality of first image frames, Acquire a first image corresponding to a first portion of the identified virtual area included within the first image frame, Based on the still image and the first image frame, a second image corresponding to a second portion of the identified virtual area excluding the first portion is obtained through the machine-learned artificial intelligence model, An electronic device that obtains a second image frame in which the first image is placed in a first area and the second image is placed in a second area excluding the first area.

3. In paragraph 2, The above instructions are collectively or individually executed by the at least one processor, so that the electronic device: Determine whether the first image includes an object of interest related to the subject, In response to determining that the object of interest is included in the first image, acquiring the second image based on the still image and the first image frame, In response to determining that the object of interest is excluded from the first image: Determine whether the identity of the object of interest included in the still image and the object of interest included in the second image can be maintained; In response to determining that the above similarity can be maintained, the second image is acquired based on the still image, the first image frame, and the feature information of the subject, and An electronic device that, in response to determining that the similarity is lost, causes acquisition of the second image frame to be omitted.

4. In paragraph 3, The above instructions are collectively or individually executed by the at least one processor, so that the electronic device: Identifying a similarity value by comparing first feature information obtained from a subject included in the still image with second feature information obtained from a subject included in the second image, An electronic device that determines that the similarity of the object of interest can be maintained when the similarity value is equal to or greater than a set first threshold value.

5. In paragraph 1, The above instructions are executed by the at least one processor, so that the electronic device: Based on the still image and at least one image frame among the plurality of first image frames, identifying motion information of a subject within the plurality of first image frames, and An electronic device that obtains at least one image frame in which at least a portion of the region is generated through the machine-learned artificial intelligence model based on the movement information of the identified subject.

6. In paragraph 1, The above instructions are executed by the at least one processor, so that the electronic device: Based on the plurality of first image frames, information about the degree of movement of the electronic device during the first period in which the plurality of first image frames were generated is identified, Selecting a plurality of second image frames acquired during a second period in which the degree of movement of the identified electronic device is less than or equal to a second threshold value among the plurality of first image frames, and An electronic device that obtains at least one image frame based on at least some of the plurality of second image frames selected above.

7. In paragraph 2, The above instructions are collectively or individually executed by the at least one processor, so that the electronic device: Determining whether the identified area is included within the first image frame, Based on the determination that at least a portion of the identified area is outside the first image frame: Obtain the second image above, Obtaining the second image frame based on the first image and the second image, Based on the determination that the identified area is included within the first image frame: Omitting the acquisition of the second image above, An electronic device that obtains the second image frame based on the first image.

8. In paragraph 1, Including more cameras, The above instructions are executed by the at least one processor, so that the electronic device: Acquiring the plurality of first image frames based on at least a portion of a preview image acquired through the camera and displayed through the display, Receives user input for capturing the above still image, and An electronic device that acquires the still image and the moving image in response to receiving the user input.

9. In paragraph 1, The above instructions are executed by the at least one processor, so that the electronic device: Determine a classification to which a scene or subject included in at least one of the plurality of first image frames or the still images belongs, If the above classification satisfies the video acquisition condition, the video is acquired, and the video is stored in the memory in association with the still image, An electronic device that skips acquisition of the video and stores the still image in the memory when the above classification does not satisfy the above video acquisition condition.

10. In paragraph 1, The above instructions are executed by the at least one processor, so that the electronic device: Running an application that displays a list of at least one image containing the still image, and In response to receiving a user input for selecting the still image from the above list, displaying a UI for obtaining the video, and An electronic device that obtains the video in response to a user input through the UI.

11. In paragraph 1, Including a wireless communication module. The above instructions are executed by the at least one processor, so that the electronic device: Using the wireless communication module, the plurality of first image frames and the still image are transmitted to an external server storing the machine-learned artificial intelligence model, and An electronic device that receives at least one image frame or the video from the server.

12. In the method of operating an electronic device, An operation of storing a plurality of first image frames in a memory of the electronic device; The act of acquiring a still image; An operation of obtaining at least one image frame in which at least a portion of a region is generated using a machine-learned artificial intelligence model based on at least a portion of the plurality of first image frames or still images; An operation of obtaining a video based on at least some of the plurality of first image frames and at least one image frame; An operation of obtaining a video based on the plurality of second image frames; An operation of storing the above video in the memory in association with the above still image; and A method comprising an action of playing the moving image when displaying the still image.

13. In paragraph 12, The operation of obtaining at least one image frame is: An action of identifying a subject within the still image; An operation of identifying a virtual area corresponding to the subject within a first image frame among the plurality of first image frames; An operation of acquiring a first image corresponding to a first portion of the identified virtual area included within the first image frame; An operation of obtaining a second image corresponding to a second portion of the identified virtual area excluding the first portion, through the machine-learned artificial intelligence model, based on the still image and the first image frame; and A method comprising an operation of obtaining a second image frame in which the first image is placed in a first region and the second image is placed in a second region excluding the first region.

14. In paragraph 13, An operation of determining whether the first image includes an object of interest related to the subject; In response to determining that the object of interest is included in the first image, an operation of acquiring the second image based on the still image and the first image frame; In response to determining that the object of interest is excluded from the first image: An operation of determining whether the identity of the object of interest included in the still image and the object of interest included in the second image can be maintained; and In response to determining that the above similarity can be maintained, further comprising an operation of acquiring the second image based on the still image, the first image frame, and the feature information of the subject, and A method for omitting an operation of acquiring the second image frame in response to determining that the above similarity is lost.

15. In paragraph 14, The action to determine whether the above similarity can be maintained is: Identifying a similarity value by comparing first feature information obtained from a subject included in the first image frame with second feature information of a subject included in the second image, A method for determining that the similarity of the object of interest can be maintained when the similarity value is greater than or equal to a set first threshold value.

Images