Electronic device for smoothing histogram of image, operating method thereof, and recording medium

Abstract

An electronic device according to an embodiment comprises at least one processor and a memory for storing instructions, wherein the instructions, when executed by the at least one processor, may cause the electronic device: execute a function for changing at least one pixel value among a plurality of pixel values of a first image; on the basis of providing information about the first image to an artificial intelligence (AI) model in response to execution of the function, be set to acquire, from the artificial intelligence model, N parameter sets for changing the at least one pixel value by using histograms of the first image, wherein N is a natural number of 1 or greater, and each of the N parameter sets includes at least one parameter related to a histogram of each of a plurality of regions of the first image; and on the basis of sequentially changing the at least one pixel value of the first image N times by using the N parameter sets by using the histogram of each of the plurality of regions of the first image, acquire a second image in which the at least one pixel value has been changed among the plurality of pixel values of the first image.

Description

Electronic device for smoothing the histogram of an image, method of operation thereof, and recording medium

[0001] Various embodiments relate to an electronic device for smoothing the histogram of an image, a method of operating the same, and a recording medium.

[0002] The term "electronic device" may refer to devices that perform specific functions according to an installed program, ranging from home appliances to electronic notebooks, portable multimedia players, mobile communication terminals, tablet PCs, video / audio devices, desktop / laptop computers, or in-vehicle navigation systems. For example, these electronic devices can output stored information as sound or video. As the integration density of electronic devices increases and ultra-high-speed, high-capacity wireless communication becomes commonplace, various functions can recently be integrated into a single electronic device, such as a mobile communication terminal. For example, not only communication functions but also entertainment functions such as games, multimedia functions such as music / video playback, communication and security functions for mobile banking, or functions such as schedule management and electronic wallets are being integrated into a single electronic device.

[0003] Images captured by electronic devices require image quality improvement depending on the application. In particular, images containing a mixture of dark and bright areas may make it difficult to visually obtain information. Consequently, there is a growing need to enhance image contrast to alter the brightness distribution.

[0004] The information described above may be provided as related art for the purpose of aiding understanding of the present disclosure. No claim or determination is made as to whether any of the foregoing may be applied as prior art related to the present disclosure.

[0005] According to one embodiment, the electronic device may include at least one processor and a memory for storing instructions.

[0006] According to one embodiment, the instructions may be configured to cause the electronic device to perform a function to change at least one pixel value among a plurality of pixel values ​​of a first image when executed by the at least one processor.

[0007] According to one embodiment, the instructions may be configured such that, when executed by the at least one processor, the electronic device obtains N sets of parameters for changing the at least one pixel value using a histogram of the first image from an artificial intelligence (AI) model based on providing information about the first image to an artificial intelligence (AI) model in response to executing the function, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters may include at least one parameter associated with the histogram of each of the plurality of regions of the first image.

[0008] According to one embodiment, the instructions may be configured such that, when executed by the at least one processor, the electronic device obtains a second image in which the at least one pixel value among the plurality of pixel values ​​of the first image has been changed, based on sequentially changing the at least one pixel value of the first image N times using the histogram of each of the plurality of regions of the first image using the N parameter sets.

[0009] According to one embodiment, the method of operating an electronic device may include an operation of performing a function to change at least one pixel value among a plurality of pixel values ​​of a first image.

[0010] According to one embodiment, a method of operating an electronic device includes the operation of obtaining N sets of parameters for changing at least one pixel value using a histogram of the first image from the artificial intelligence model, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters may include at least one parameter associated with a histogram of each of the plurality of regions of the first image.

[0011] According to one embodiment, a method of operating an electronic device may include an operation of obtaining a second image in which the at least one pixel value among the plurality of pixel values ​​of the first image has been changed, based on sequentially changing the at least one pixel value of the first image N times using the histogram of each of the plurality of regions of the first image using the N parameter sets.

[0012] According to one embodiment, in a storage medium for storing computer-readable instructions, the instructions cause the electronic device to perform at least one operation when executed by at least one processor of the electronic device, and the at least one operation may include an operation to perform a function for changing at least one pixel value among a plurality of pixel values ​​of a first image.

[0013] According to one embodiment, in a storage medium for storing computer-readable instructions, the instructions cause the electronic device to perform at least one operation when executed by at least one processor of the electronic device, and the at least one operation includes obtaining N sets of parameters for changing the at least one pixel value using a histogram of the first image from the artificial intelligence model, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters may include at least one parameter associated with the histogram of each of the plurality of regions of the first image.

[0014] According to one embodiment, in a storage medium for storing computer-readable instructions, the instructions cause the electronic device to perform at least one operation when executed by at least one processor of the electronic device, and the at least one operation may include an operation of obtaining a second image in which the at least one pixel value among the plurality of pixel values ​​of the first image has been changed, based on changing the at least one pixel value of the first image sequentially N times using the histogram of each of the plurality of regions of the first image using the N parameter sets.

[0015] FIG. 1 is a block diagram of an electronic device in a network environment according to various embodiments.

[0016] FIG. 2 is a diagram illustrating the operation of an electronic device according to one embodiment acquiring a second image in which at least one pixel value among a plurality of pixel values ​​of a first image has been changed.

[0017] FIG. 3 is a diagram illustrating the operation of an electronic device adjusting a histogram based on the CLAHE (contrast limited adaptive histogram equalization) algorithm according to one embodiment.

[0018] FIG. 4 is a diagram illustrating the operation of an electronic device adjusting a histogram based on a rescale algorithm according to one embodiment.

[0019] FIG. 5 is a schematic block diagram of an electronic device according to one embodiment.

[0020] FIG. 6a is a diagram illustrating an operation in which an electronic device, according to one embodiment, performs a histogram equalization operation N times on a histogram of a first image to obtain a second image.

[0021] FIG. 6b is a diagram illustrating an operation in which an electronic device, according to one embodiment, performs a histogram equalization operation N times on a histogram of a first image to obtain a second image.

[0022] FIG. 7a is a diagram illustrating the operation of an artificial intelligence model acquiring N sets of parameters according to one embodiment.

[0023] FIG. 7b is a diagram illustrating the operation of an artificial intelligence model acquiring N sets of parameters according to one embodiment.

[0024] FIG. 7c is a diagram illustrating the operation of an artificial intelligence model acquiring N sets of parameters according to one embodiment.

[0025] FIG. 8 is a flowchart illustrating the operation of an electronic device acquiring a second image in which the pixel values ​​of a first image have been changed, according to one embodiment.

[0026] FIG. 9a is a flowchart illustrating the operation of an electronic device, according to a comparative embodiment, to acquire a second image from a first image using a set of parameters acquired to equalize the histogram of the first image twice.

[0027] FIG. 9b is a flowchart illustrating the operation of an electronic device, according to one embodiment, to acquire a second image from a first image using a set of parameters acquired to equalize the histogram of a first image twice.

[0028] FIGS. 10a and FIGS. 10b are drawings for explaining the operation of an electronic device, according to one embodiment, to equalize the histogram of a first image using a first parameter set corresponding to a first order among parameter sets obtained to equalize the histogram of a first image twice.

[0029] FIG. 10c is a diagram illustrating the operation of an electronic device, according to one embodiment, to smooth a histogram corresponding to a first region among a plurality of regions of a first image using a first parameter set.

[0030] FIGS. 11a and FIGS. 11b are drawings for explaining the operation of an electronic device, according to one embodiment, to equalize the histogram of a third image using a second parameter set corresponding to a second order among parameter sets obtained to equalize the histogram of a first image twice.

[0031] FIG. 11c is a diagram illustrating the operation of an electronic device, according to one embodiment, to smooth a histogram corresponding to a first region among a plurality of regions of a third image using a second parameter set.

[0032] FIG. 1 is a block diagram of an electronic device (101) in a network environment (100) according to various embodiments. Referring to FIG. 1, in the network environment (100), the electronic device (101) may communicate with an electronic device (102) through a first network (198) (e.g., a short-range wireless communication network) or may communicate with at least one of an electronic device (104) or a server (108) through a second network (199) (e.g., a long-range wireless communication network). According to one embodiment, the electronic device (101) may communicate with the electronic device (104) through a server (108). According to one embodiment, the electronic device (101) may include a processor (120), memory (130), input module (150), sound output module (155), display module (160), audio module (170), sensor module (176), interface (177), connection terminal (178), haptic module (179), camera module (180), power management module (188), battery (189), communication module (190), subscriber identification module (196), or antenna module (197). In some embodiments, at least one of these components (e.g., connection terminal (178)) may be omitted from the electronic device (101), or one or more other components may be added. In some embodiments, some of these components (e.g., sensor module (176), camera module (180), or antenna module (197)) may be integrated into a single component (e.g., display module (160)).

[0033] The processor (120) can control at least one other component (e.g., hardware or software component) of the electronic device (101) connected to the processor (120) by executing software (e.g., program (140)), for example, and can perform various data processing or operations. According to one embodiment, as at least part of the data processing or operations, the processor (120) can store commands or data received from other components (e.g., sensor module (176) or communication module (190)) in volatile memory (132), process the commands or data stored in volatile memory (132), and store the resulting data in non-volatile memory (134). According to one embodiment, the processor (120) may include a main processor (121) (e.g., central processing unit or application processor) or an auxiliary processor (123) that can operate independently or together with it (e.g., graphics processing unit, neural processing unit (NPU), image signal processor, sensor hub processor, or communication processor). For example, if the electronic device (101) includes a main processor (121) and an auxiliary processor (123), the auxiliary processor (123) may be configured to use lower power than the main processor (121) or to be specialized for a designated function. The auxiliary processor (123) may be implemented separately from the main processor (121) or as part thereof.

[0034] The auxiliary processor (123) may control at least some of the functions or states associated with at least one component of the electronic device (101) (e.g., display module (160), sensor module (176), or communication module (190)) 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. According to one embodiment, the auxiliary processor (123) (e.g., image signal processor or communication processor) may be implemented as part of another functionally related component (e.g., camera module (180) or communication module (190)). According to one embodiment, the auxiliary processor (123) (e.g., neural network processing unit) may include a hardware structure specialized for processing an artificial intelligence model. The artificial intelligence model may be generated through machine learning. Such learning may be performed, for example, on the electronic device (101) itself where the artificial intelligence is performed, or through a separate server (e.g., server (108)). The learning algorithm may 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 may include a plurality of artificial neural network layers.An artificial neural network may be 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 the hardware structure, the artificial intelligence model may include a software structure, either additionally or substantially.

[0035] The memory (130) can store various data used by at least one component of the electronic device (101) (e.g., processor (120) or sensor module (176)). The data may include, for example, input data or output data for software (e.g., program (140)) and related commands. The memory (130) may include volatile memory (132) or non-volatile memory (134).

[0036] The program (140) may be stored as software in memory (130) and may include, for example, an operating system (142), middleware (144), or an application (146).

[0037] The input module (150) can receive commands or data to be used for a component of the electronic device (101) (e.g., processor (120)) from outside the electronic device (101) (e.g., user). The input module (150) may include, for example, a microphone, a mouse, a keyboard, a key (e.g., a button), or a digital pen (e.g., a stylus pen).

[0038] The sound output module (155) can output a sound signal to the outside of the electronic device (101). The sound output module (155) may include, for example, a speaker or a receiver. The speaker may be used for general purposes, such as multimedia playback or recording playback. The receiver may be used to receive incoming calls. According to one embodiment, the receiver may be implemented separately from the speaker or as part thereof.

[0039] The display module (160) can visually provide information to an external (e.g., 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 said 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 the force generated by said touch.

[0040] The audio module (170) can convert sound into an electrical signal or, conversely, convert an electrical signal into sound. According to one embodiment, the audio module (170) can acquire sound through the input module (150) or output sound through the sound output module (155) or an external electronic device (e.g., electronic device (102)) (e.g., speaker or headphones) connected directly or wirelessly to the electronic device (101).

[0041] The sensor module (176) can detect the operating state of the electronic device (101) (e.g., power or temperature) or the external environmental state (e.g., user state) and generate an electrical signal or data value corresponding to the detected state. According to one embodiment, the sensor module (176) may include, for example, a gesture sensor, a gyroscope sensor, a barometric pressure sensor, a magnetic sensor, an accelerometer sensor, a grip sensor, a proximity sensor, a color sensor, an IR (infrared) sensor, a biosensor, a temperature sensor, a humidity sensor, or an illuminance sensor.

[0042] The interface (177) may support one or more specified protocols that can be used for the electronic device (101) to be connected directly or wirelessly to an external electronic device (e.g., electronic device (102)). According to one embodiment, the interface (177) may include, for example, a high definition multimedia interface (HDMI), a universal serial bus (USB) interface, an SD card interface, or an audio interface.

[0043] The connection terminal (178) may include a connector through which the electronic device (101) can 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).

[0044] The haptic module (179) can convert an electrical signal into a mechanical stimulus (e.g., vibration or movement) or an electrical stimulus that the user can perceive through tactile or kinesthetic senses. According to one embodiment, the haptic module (179) may include, for example, a motor, a piezoelectric element, or an electric stimulation device.

[0045] The camera module (180) can capture still images and video. According to one embodiment, the camera module (180) may include one or more lenses, image sensors, image signal processors, or flashes.

[0046] The power management module (188) can manage the power supplied to the electronic device (101). According to one embodiment, the power management module (188) can be implemented, for example, as at least part of a power management integrated circuit (PMIC).

[0047] The battery (189) can supply power to at least one component of the electronic device (101). According to one embodiment, the battery (189) may include, for example, a non-rechargeable primary battery, a rechargeable secondary battery, or a fuel cell.

[0048] The communication module (190) can support the establishment of a direct (e.g., wired) communication channel or a wireless communication channel between an 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 include one or more communication processors that operate independently of the processor (120) (e.g., application processor) and 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., cellular communication module, short-range wireless communication module, or GNSS (global navigation satellite system) communication module) or a wired communication module (194) (e.g., LAN (local area network) communication module, or power line communication module). The corresponding communication module among these communication modules can communicate with an external electronic device (104) through a first network (198) (e.g., a short-range communication network such as Bluetooth, WiFi (wireless fidelity) direct, or IrDA (infrared data association)) or a second network (199) (e.g., 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 may 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 identify or authenticate the electronic device (101) within a communication network such as the first network (198) or the second network (199) using subscriber information (e.g., International Mobile Subscriber Identifier (IMSI)) stored in the subscriber identification module (196).

[0049] The wireless communication module (192) can support 5G networks and next-generation communication technologies following 4G networks, for example, new radio access technology. NR access technology can support high-speed transmission of high-capacity data (enhanced mobile broadband (eMBB)), minimization of terminal power and connection of multiple terminals (massive machine type communications (mMTC)), or high reliability and low latency (ultra-reliable and low-latency communications (URLLC)). The wireless communication module (192) can support a high-frequency band (e.g., mmWave band) to achieve a high data transmission rate, for example. The wireless communication module (192) can support various technologies for securing performance in the high-frequency band, such as beamforming, massive MIMO (multiple-input and multiple-output), 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), external electronic device (e.g., electronic device (104)), or network system (e.g., 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 realizing eMBB, loss coverage (e.g., 164 dB or less) for realizing mMTC, or U-plane latency (e.g., downlink (DL) and uplink (UL) each 0.5 ms or less, or round trip 1 ms or less) for realizing URLLC.

[0050] An antenna module (197) can transmit a signal or power to or from an external source (e.g., an external electronic device). According to one embodiment, the antenna module (197) may include an antenna comprising a radiator made of a conductor or a conductive pattern formed on a substrate (e.g., a PCB). According to 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 a first network (198) or a second network (199), may be selected from the plurality of antennas, for example, by a communication module (190). A signal or power may be transmitted or received between the communication module (190) and an external electronic device through the selected at least one antenna. According to some embodiments, in addition to the radiator, other components (e.g., a radio frequency integrated circuit (RFIC)) may be additionally created as part of the antenna module (197).

[0051] According to one embodiment, the antenna module (197) can create a mmWave antenna module. According to one embodiment, the mmWave antenna module may include a printed circuit board, an RFIC disposed on or adjacent to a first surface (e.g., bottom surface) of the printed circuit board and capable of supporting a specified high frequency band (e.g., mmWave band), and a plurality of antennas (e.g., array antennas) disposed on or adjacent to a second surface (e.g., top surface or side surface) of the printed circuit board and capable of transmitting or receiving a signal of the specified high frequency band.

[0052] At least some of the above components can be connected to each other via a communication method between peripheral devices (e.g., bus, GPIO (general purpose input and output), SPI (serial peripheral interface), or MIPI (mobile industry processor interface)) and exchange signals (e.g., commands or data) with each other.

[0053] According to one embodiment, commands or data may be transmitted or received between an electronic device (101) and an external electronic device (104) through 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 performed on the electronic device (101) may be performed on one or more of the external electronic devices (102, 104, or 108). For example, if the electronic device (101) needs to perform a function or service automatically or in response to a request from a user or another device, the electronic device (101) may request one or more external electronic devices to perform at least part of the function or service instead of performing the function or service itself or additionally. One or more external electronic devices that receive the above request may execute at least part of the requested function or service, or 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 provide the result as is or additionally processed as at least part of the response to the request. For this purpose, for example, cloud computing, distributed computing, mobile edge computing (MEC), or client-server computing technology may be used. The electronic device (101) may provide ultra-low latency services using, for example, distributed computing or mobile edge computing. In one embodiment, the external electronic device (104) may include an Internet of Things (IoT) device. The server (108) may be an intelligent server using machine learning and / or neural networks. According to one embodiment, the external electronic device (104) or the server (108) may be included within a 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.

[0054] FIG. 2 is a diagram illustrating the operation of an electronic device according to one embodiment acquiring a second image in which at least one pixel value among a plurality of pixel values ​​of a first image has been changed.

[0055] Referring to FIG. 2(a), according to one embodiment, an electronic device (501) (e.g., the electronic device (501) of FIG. 5) may perform a function to change at least one pixel value among a plurality of pixel values ​​of a first image (201). For example, the electronic device (501) may perform a function to edit the first image (201) to obtain a second image (202) in which the brightness distribution (or brightness contrast) is improved compared to the first image (201). According to one embodiment, the electronic device (501) may adjust the histogram of the first image (201) to improve the brightness distribution (or brightness contrast) of the first image (201). For example, if the electronic device (201) has more than a specified number (or specified distribution) of pixels clustered at a specific brightness value of the histogram of the first image (201), it can distribute (adjust) the distribution of pixels having a specific brightness value by using a histogram equalization (HE) operation (or method). The above function may represent a function of performing a histogram equalization (HE) operation (or method) on the histogram of the first image (201) so that the brightness values ​​of the pixels constituting the histogram of the first image (201) are distributed (dispersed) uniformly overall.

[0056] Referring to FIG. 2(b), according to one embodiment, an electronic device (501) can equalize the histogram of a first image (201) based on performing the above function. According to one embodiment, the electronic device (501) can obtain a second image (202) in which the brightness distribution of the first image (201) has been altered based on performing a histogram equalization (HE) operation (or method) on the histogram of the first image (201). The histogram after the histogram equalization (HE) method has been performed (e.g., the histogram of the second image (202)) may have brightness values ​​distributed more uniformly overall than the existing histogram (e.g., the histogram of the first image (201)). Through this, the electronic device (501) can obtain a second image (202) with improved brightness contrast of the first image (201).

[0057] For example, a histogram equalization (HE) method may include an operation (or method) of adjusting a histogram using a contrast-limited adaptive histogram equalization (CLAHE) algorithm or a rescale algorithm. For example, the operation of adjusting a histogram using a CLAHE algorithm or a rescale algorithm may include an operation of adjusting (e.g., equalizing) the values ​​(or distribution) of pixels exceeding a threshold or a specified value in the histogram using the corresponding algorithm (e.g., CLAHE algorithm or rescale algorithm), and an operation of redistributing (or readjusting) the equalized histogram using the corresponding algorithm.

[0058] According to one embodiment, the electronic device (501) can change pixel values ​​of the first image (201) using a parameter set obtained based on at least one of a contrast limited adaptive histogram equalization (CLAHE) algorithm or a rescale algorithm. The parameter set may include at least one parameter for changing pixel values ​​of the first image (201) by adjusting the histogram using at least one of the contrast limited adaptive histogram equalization (CLAHE) algorithm or the rescale algorithm of the first image (201).

[0059] For example, at least one parameter may include at least one of the number of multiple regions of the first image (e.g., tile size), a specified distribution of pixel values ​​of a histogram corresponding to each of the multiple regions (e.g., clip limit value), or a specified ratio for adjusting pixel values ​​of a histogram corresponding to each of the multiple regions (e.g., rescale value).

[0060] For example, the tile size can represent the width and height of each of the multiple regions when the first image is divided into multiple regions.

[0061] For example, the clip limit value may represent a height or vertical axis value (e.g., a value corresponding to the number of pixels) specified to adjust the distribution of the histogram. For example, the electronic device (501) may smooth the histogram to be lower than the clip limit value and readjust the distribution of the histogram.

[0062] For example, the rescale value may represent a value for readjusting the distribution of the histogram. For example, the electronic device (501) may redistribute pixel values ​​in the histogram that exceed the rescale value, taking into account the distribution of the histogram.

[0063] According to one embodiment, the CLAHE (contrast limited adaptive histogram equalization) algorithm is described in detail in FIG. 3, and the rescale algorithm is described in detail in FIG. 4.

[0064] FIG. 3 is a diagram illustrating the operation of an electronic device adjusting a histogram based on the CLAHE (contrast limited adaptive histogram equalization) algorithm according to one embodiment.

[0065] According to one embodiment, an electronic device (501) (e.g., the electronic device (501) of FIG. 5) can adjust the histogram of each of a plurality of regions of a first image (201) (e.g., the first image (201) of FIG. 2) based on a CLAHE (contrast limited adaptive histogram equalization) algorithm. For convenience of explanation, the operation of adjusting the first histogram (301) corresponding to a specific region among the plurality of regions of the first image (201) will be described. However, the operation of adjusting the first histogram (301) based on a CLAHE (contrast limited adaptive histogram equalization) algorithm can be applied in the same way to the operation of adjusting the histograms corresponding to the remaining regions among the plurality of regions of the first image (201) based on a CLAHE (contrast limited adaptive histogram equalization) algorithm. According to one embodiment, the first histogram (301) may be a graph representing the distribution of brightness values ​​included in a specific region among a plurality of regions of the first image (201). The horizontal axis of the first histogram (301) may represent brightness values, and the vertical axis may represent a value corresponding to the number of pixels having those brightness values. That is, the vertical axis may indicate how many pixels of the first image (201) have a specific brightness value exist.

[0066] Referring to FIG. 3 (a) and (b), according to one embodiment, a histogram (303) with adjusted pixel values ​​can be obtained by using an offset corresponding to an area (320) that is the same as the area of ​​a plurality of first pixel values ​​(e.g., brightness values) that exceed a specified threshold value (e.g., clip limit value) among the pixel values ​​(e.g., brightness values) of the first histogram (301).

[0067] According to one embodiment, the electronic device (501) can identify a region (310) of a plurality of first pixel values ​​(e.g., brightness values) that exceed a specified threshold value (e.g., clip limit value) among the pixel values ​​(e.g., brightness values) of the first histogram (301). The electronic device (501) can obtain an adjusted histogram (303) by adding (compensating) an offset corresponding to a region (320) having the same area as the area of ​​the corresponding region (310) to the histogram (302) from which the corresponding region (310) is excluded (or smoothed) from the first histogram (301).

[0068] According to one embodiment, the horizontal length of the region (320) may represent a length corresponding to the range of total brightness values ​​representing the horizontal axis of the adjusted histogram (302). The vertical length of the region (320) may be determined based on the horizontal length.

[0069] Through this, the electronic device (501) can obtain a second image (202) (e.g., the second image (202) of FIG. 2) in which at least one pixel value among a plurality of pixel values ​​of the first image (201) is changed based on the first histogram (301) adjusted based on the CLAHE (contrast limited adaptive histogram equalization) algorithm.

[0070] For example, the electronic device (501) can integrate the adjusted histogram based on the first histogram (301) adjusted according to the CLAHE (contrast limited adaptive histogram equalization) algorithm, and obtain a cumulative distribution function (CDF) as the result of the integration. The electronic device (501) can obtain a pixel change function that can change the pixels of an image using the cumulative distribution function (CDF). For example, the electronic device (501) can obtain a second image (202) in which at least one pixel value among a plurality of pixel values ​​of the first image (201) is changed using the pixel change function.

[0071] FIG. 4 is a diagram illustrating the operation of an electronic device adjusting a histogram based on a rescale algorithm according to one embodiment.

[0072] According to one embodiment, an electronic device (501) (e.g., the electronic device (501) of FIG. 5) can adjust the histogram of each of a plurality of regions of a first image (201) (e.g., the first image (201) of FIG. 2) based on a rescale algorithm. For convenience of explanation, the operation of adjusting a second histogram (401) corresponding to a specific region among the plurality of regions of the first image (201) will be described. However, the operation of adjusting the second histogram (401) can be applied in the same way to the operation of adjusting histograms corresponding to the remaining regions among the plurality of regions of the first image (201). According to one embodiment, the second histogram (401) may be a graph representing the distribution of brightness values ​​included in a specific region of the first image (201). The horizontal axis of the second histogram (401) may represent brightness values, and the vertical axis may represent the distribution of pixels having the corresponding brightness values ​​(values ​​corresponding to the number of pixels).

[0073] Referring to FIG. 4(a) and (b), according to one embodiment, the distribution of pixels of a second histogram (401) corresponding to a specific region among a plurality of regions of a first image (201) (e.g., the first image (201) of FIG. 2) (e.g., a value corresponding to the number of pixels) can be adjusted using a specified value (e.g., a rescale value). The adjusted histogram (402) shown in FIG. 4(b) may represent a histogram in which the second histogram (401) is adjusted (or smoothed) (e.g., reduced) according to a specified ratio so that the distribution of pixels having brightness values ​​of the second histogram (401) (e.g., a value corresponding to the number of pixels) does not exceed a specified value (e.g., a rescale value).

[0074] Referring to FIG. 4(c), according to one embodiment, an electronic device (501) can obtain an adjusted histogram (403) using an offset (420) that corresponds to an area equal to the area (410) that exceeds the distribution of pixels of the adjusted histogram (402) (e.g., a value corresponding to the number of pixels) among the distribution of pixels (e.g., brightness values) of the second histogram (401).

[0075] According to one embodiment, the electronic device (501) can obtain an adjusted histogram (403) by compensating (adding) to the adjusted histogram (402) shown in FIG. 4 (b) an offset corresponding to an area equal to the area (410) that exceeds the distribution of pixels of the adjusted histogram (402) among the pixels (e.g., brightness values) of the second histogram (401) (e.g., brightness values).

[0076] According to one embodiment, the horizontal length of the area (420) corresponding to the offset may represent a length corresponding to a range of brightness values ​​representing the horizontal axis of the adjusted histogram (402). The vertical length of the area (420) corresponding to the offset may be determined based on the horizontal length.

[0077] According to one embodiment, the electronic device (501) can obtain a second image (202) (e.g., the second image (202) of FIG. 2) in which at least one pixel value among a plurality of pixel values ​​of the first image (201) is changed based on the second histogram (401) being adjusted based on a rescale algorithm.

[0078] The electronic device was able to acquire a set of parameters to be used in a histogram equalization (HE) method for adjusting (e.g., normalization) the histogram of the first image at the time of adjusting (e.g., normalization). The electronic device was able to acquire the corresponding parameter set at the time each adjustment operation was performed while performing N adjustment operations of the histogram of the first image. For example, the electronic device could acquire a first set of parameters for performing a first histogram equalization (HE) method based on the first image. Additionally, after performing the first histogram equalization (HE) method using the first set of parameters, the electronic device could acquire a second set of parameters for performing a second histogram equalization (HE) method based on an image obtained from the first image (e.g., a normalized image). However, acquiring multiple sets of parameters for performing the histogram equalization (HE) method on multiple histograms might require a significant amount of time. In other words, since it takes a considerable amount of time to acquire the corresponding parameter set, a significant amount of time was required to smooth the histogram of the first image multiple times. As the electronic device requires a significant amount of time to acquire the second image obtained by smoothing the first image multiple times, a problem of reduced usability of the electronic device may occur.

[0079] The set of parameters to be used in the histogram equalization (HE) method may differ from image to image. The electronic device defines a formula for determining a specific set of parameters using camera setting information set when acquiring images. Defining a formula for each image and acquiring the set of parameters according to the formula may result in lower accuracy and take a long time. An electronic device according to one embodiment (e.g., the electronic device (501) of FIG. 5) can acquire N sets of parameters in advance before performing the histogram equalization (HE) method to adjust the histogram of the first image N times (e.g., perform the histogram equalization (HE) method) using a first artificial intelligence model (731) (e.g., the first artificial intelligence model (731) of FIG. 7a), thereby reducing the time required to acquire the final image with the changed brightness distribution. Additionally, the electronic device (501) can acquire N sets of parameters faster than before by using the first artificial intelligence model (731). The electronic device (501) according to one embodiment can select parameters by utilizing the semantic meaning represented by the object when using the first artificial intelligence model (731). Furthermore, the electronic device (501) according to one embodiment can acquire more image scenes and parameter sets by determining values ​​with a complex network rather than a simple formula, thereby making it possible to select more optimized parameter values.

[0080] FIG. 5 is a schematic block diagram of an electronic device according to one embodiment.

[0081] Referring to FIG. 5, according to one embodiment, an electronic device (501) (e.g., electronic device (101) of FIG. 1) may include a processor (520) (e.g., processor (120) of FIG. 1), a memory (530) (e.g., memory (130) of FIG. 1), and a display (560) (e.g., display (160) of FIG. 1).

[0082] According to one embodiment, the processor (520) can control the overall operation of the electronic device (201). For example, the processor (520) may be composed of one or more processing circuits. According to one embodiment, one or more processors (520) may include a hardware accelerator for executing a neural network model. For example, the hardware accelerator may include, but is not limited to, a neural processing unit (NPU), a tensor processing unit (TPU), or an artificial intelligence engine.

[0083] According to one embodiment, the processor (520) may control a function or a series of operations to change at least one pixel value among a plurality of pixel values ​​of the first image (201). For example, the processor (520) may execute a function to edit the first image (201) and perform operations to improve the brightness distribution (or brightness contrast) of the first image (201). For example, the processor (520) may perform an operation to equalize the histogram of the first image N times (N is a natural number greater than or equal to 1) to improve the brightness distribution (or brightness contrast) of the first image (201). According to one embodiment, the processor (520) may obtain N sets of parameters to perform N histogram equalization operations on the histogram of the first image using a first artificial intelligence model (731) (e.g., the first artificial intelligence model (731) of FIG. 7a). For example, the processor (520) can obtain N sets of parameters at once by using a first artificial intelligence model (731) stored in memory (530) or an external device (e.g., a server). At this time, the processor (520) can obtain N sets of parameters before performing N histogram equalization operations on the histogram of the first image in response to user input to adjust the brightness distribution (or brightness contrast) of the first image. Subsequently, the processor (520) can perform N histogram equalization operations on the histogram of the first image using the previously obtained N sets of parameters. For example, N may be a natural number greater than or equal to 1.

[0084] In the following, a series of operations that perform a histogram equalization operation on a histogram may be described as a histogram equalization operation.

[0085] According to one embodiment, the processor (520) may execute a function to change at least one pixel value among a plurality of pixel values ​​of the first image. The function may represent a function to equalize the histogram of the first image so that the brightness values ​​of the pixels constituting the histogram of the first image are distributed uniformly (e.g., normalization, equalization).

[0086] According to one embodiment, the processor (520) may provide the first image to a second artificial intelligence model (732) (e.g., the first artificial intelligence model (732) of FIG. 7b) in response to executing a function to change at least one pixel value among a plurality of pixel values ​​of the first image. According to one embodiment, the processor (520) may obtain information about the first image from the second artificial intelligence model (732) based on providing the first image to the second artificial intelligence model (732). The second artificial intelligence model (732) may be implemented as a semantic artificial intelligence model. Depending on the implementation, according to one embodiment, the processor (520) may obtain information about the first image through a separate algorithm stored in memory (530).

[0087] For example, information about the first image may include information about the histogram of the first image. For example, information about the histogram may include standard deviation of intensity image histogram, kurtosis of intensity image histogram, and / or skewness of intensity image histogram.

[0088] For example, information about the first image may further include information about at least one object (e.g., person, animal, text, sky, or landscape) included in the first image.

[0089] For example, information regarding the first image may include information related to image quality. For example, information related to image quality may include a statistical naturalness measure (SNM), a measure of enhancement (EME), and / or a global contrast factor (GCF).

[0090] For example, information regarding the first image may include information related to the image texture. For example, information related to the image texture may include a vector of local binary patterns (LBP) rotationally invariant features, entropy of gray-level co-occurrence matrix, inertia of gray-level co-occurrence matrix, energy of gray-level co-occurrence matrix, correlation of gray-level co-occurrence matrix, homogeneity of gray-level co-occurrence matrix, FFT energy, FFT entropy, FFT inertia, and / or FFT homogeneity.

[0091] According to one embodiment, the processor (520) may determine N times, which represents the number of times the histogram of the first image is smoothed to change at least one pixel value of the first image. For example, N times may be automatically set by the processor (520) or set by the user.

[0092] According to one embodiment, the processor (520) may obtain N sets of parameters from the first artificial intelligence model (731) to equalize the histogram of the first image N times based on providing information about the first image and N times to the first artificial intelligence model (731). Here, N may represent a natural number greater than or equal to 1. The second artificial intelligence model (732) and the first artificial intelligence model (731) may be different from each other.

[0093] According to one embodiment, the processor (520) may obtain N sets of parameters from the first artificial intelligence model (731) to equalize the histogram of the first image N times based on providing information about the first image to the first artificial intelligence model (731). For example, the first artificial intelligence model (731) may analyze information about the first image to determine an appropriate number of times (e.g., N times) to perform equalization operations on the histogram of the first image, and determine a set of parameters corresponding to that number.

[0094] According to one embodiment, the processor (520) may obtain N sets of parameters to equalize the histogram of the first image N times from the first artificial intelligence model (731) based on providing the first image to the first artificial intelligence model (731).

[0095] According to one embodiment, the processor (520) may obtain N sets of parameters to equalize the histogram of the first image N times from the first artificial intelligence model (731) based on providing information about the first image N times and the first image to the first artificial intelligence model (731).

[0096] According to one embodiment, each of the N sets of parameters may include at least one parameter for equalizing the histogram of each of the plurality of regions of the first image. The at least one parameter may include at least one of the number of the plurality of regions of the first image (e.g., tile size), a specified threshold value for the pixel values ​​of each of the plurality of histograms corresponding to each of the plurality of regions (e.g., clip limit value), or a specified ratio for adjusting the pixel values ​​of each of the plurality of histograms (e.g., rescale value). For example, the value of the at least one parameter may vary depending on information regarding at least one object (e.g., person, animal, text, sky, or landscape) included in the first image. For example, the at least one parameter may vary depending on information regarding an object (e.g., person, animal, text, sky, or landscape) included in each of the plurality of regions included in the first image.

[0097] According to one embodiment, the processor (520) can sequentially smooth the histogram of the first image N times using N sets of parameters. According to one embodiment, the operation of the processor (520) to sequentially smooth the histogram of the first image N times using N sets of parameters may include the operation of sequentially smoothing the histogram of each of a plurality of regions of the first image N times using N sets of parameters. For example, the processor (520) may obtain a first set of parameters corresponding to a first order and a second set of parameters corresponding to a second order following the first set of parameters from the first artificial intelligence model (731) to smooth the histogram of the first image twice. Based on the smoothing of the histogram of the first image using the first set of parameters, the processor (520) may obtain a third image in which at least one first pixel value of the first image has been changed. The processor (520) can obtain a second image in which at least one second pixel value of the third image has been changed based on smoothing the histogram of the third image using a second parameter set. Through this, the processor (520) can sequentially smooth the histogram of the first image.

[0098] According to one embodiment, the processor (520) can equalize the histogram of the first image N times based on at least one of the CLAHE (contrast limited adaptive histogram equalization) algorithm or the rescale algorithm using N sets of parameters.

[0099] According to one embodiment, the processor (520) can obtain a second image based on smoothing the histogram of the first image N times using N sets of parameters. According to one embodiment, the second image may represent an image in which the value of at least one pixel among a plurality of pixels of the first image has been changed. For example, the second image may represent an image in which the brightness distribution of the first image has been changed. The second image may represent an image in which the contrast of the first image has been improved.

[0100] The operations of the electronic device (501) described in the drawings below may be performed by a processor (520). However, for the sake of convenience of explanation, the operations performed by the processor (520) will be described as being performed by the electronic device (501).

[0101] FIG. 6a is a diagram illustrating an operation in which an electronic device, according to one embodiment, performs a histogram equalization operation N times on a histogram of a first image to obtain a second image.

[0102] Referring to FIG. 6a, according to one embodiment, an electronic device (501) (e.g., the electronic device (501) of FIG. 5) may obtain N sets of parameters in advance before performing the equalization operation, so as to perform a histogram equalization (HE) method N times on a histogram of a first image using a first artificial intelligence model (731) (e.g., the first artificial intelligence model (731) of FIG. 7a).

[0103] According to one embodiment, the electronic device (501) can sequentially perform histogram equalization (HE) operations on the histogram of the first image N times using N sets of parameters.

[0104] According to one embodiment, the electronic device (501) can obtain a first image that has been equalized once by performing a histogram equalization (HE) operation on the histogram of the first image using a first parameter set corresponding to a first order.

[0105] According to one embodiment, the electronic device (501) can obtain a first image that has been smoothed twice based on performing a histogram equalization (HE) operation on a histogram of a first image that has been smoothed once using a second parameter set corresponding to a second order.

[0106] According to one embodiment, the electronic device (501) can obtain a first image that has been smoothed three times based on performing a histogram equalization (HE) operation on a histogram of a first image that has been smoothed twice using a third parameter set corresponding to a third order.

[0107] According to one embodiment, the electronic device (501) can obtain a first image that has been smoothed N times by performing a histogram equalization (HE) operation on a histogram of a first image that has been smoothed N-1 times using an N-1 parameter set corresponding to an N-1 order. In this case, N may be a natural number greater than or equal to 4.

[0108] According to one embodiment, the electronic device (501) can acquire a first image smoothed N times as a second image.

[0109] For convenience of explanation, the histogram equalization (HE) operation for the histograms of the first image is omitted multiple times between the third parameter set corresponding to the third order and the N-1 order, but the electronic device (501) can perform the histogram equalization (HE) operation for the histograms of the omitted images in the same way.

[0110] Meanwhile, the number of times the first image in FIG. 6a is smoothed is exemplary, and the technical features of the present disclosure may not be limited thereto.

[0111] FIG. 6b is a diagram illustrating an operation in which an electronic device, according to one embodiment, performs a histogram equalization operation N times on a histogram of a first image to obtain a second image.

[0112] Referring to FIG. 6b, according to one embodiment, an electronic device (501) (e.g., the electronic device (501) of FIG. 5) may obtain each of N sets of parameters before performing a histogram equalization (HE) operation on each image, so as to perform a histogram equalization (HE) operation N times on the histogram of the first image using a first artificial intelligence model (731) (e.g., the first artificial intelligence model (731) of FIG. 7a).

[0113] According to one embodiment, the electronic device (501) may obtain a first parameter set corresponding to a first order immediately before performing a histogram equalization (HE) operation on the histogram of the first image. According to one embodiment, the electronic device (501) may obtain a first image that has been equalized once based on performing a histogram equalization (HE) operation on the histogram of the first image using the first parameter set.

[0114] According to one embodiment, the electronic device (501) may acquire a second parameter set corresponding to a second order immediately before performing a histogram equalization (HE) operation on the histogram of the first image that has been equalized once. According to one embodiment, the electronic device (501) may acquire a first image that has been equalized twice based on performing a histogram equalization (HE) operation on the histogram of the second image using the second parameter set.

[0115] According to one embodiment, the electronic device (501) can obtain a first image that has been smoothed three times based on performing a histogram equalization (HE) operation on the histogram of the first image that has been smoothed twice using a third parameter set corresponding to a third order. For example, the electronic device (501) can obtain the third parameter set immediately before performing the histogram equalization (HE) operation on the histogram of the first image that has been smoothed twice.

[0116] For convenience of explanation, the histogram equalization (HE) operation on the histograms of the first image is omitted multiple times between the third parameter set corresponding to the third order and the N-1 order, but the electronic device (501) can perform the histogram equalization (HE) operation on the histograms of the omitted images in the same way. At this time, N may be a natural number greater than or equal to 4.

[0117] According to one embodiment, the electronic device (501) can acquire a first image that has been smoothed N times as a second image. Meanwhile, the number of times the first image is smoothed in FIG. 6b is exemplary and the technical features of the present disclosure may not be limited thereto.

[0118] FIG. 7a is a diagram illustrating the operation of an artificial intelligence model acquiring N sets of parameters according to one embodiment.

[0119] Referring to FIG. 7a, according to one embodiment, information indicating a first image and the number of times the first image is to be smoothed (e.g., N times) may be provided (or input) to the first artificial intelligence model (731). According to one embodiment, the first artificial intelligence model (731) may acquire (or output) N sets of parameters. Here, N may represent a natural number greater than or equal to 1. According to one embodiment, each of the N sets of parameters may include at least one parameter for equalizing the histogram of each of the plurality of regions of the first image. Depending on the implementation, N sets of parameters may be acquired (or output) even if only the first image is provided to the first artificial intelligence model (731).

[0120] According to one embodiment, each of the N parameter sets may include a parameter set for each of the plurality of regions included in the first image. For example, the number of the plurality of regions included in the first image may be M (e.g., M is a natural number greater than or equal to 1). For example, the first parameter set corresponding to the first may include a parameter set for each of the M regions. For example, the second parameter set corresponding to the second may include a parameter set for each of the M regions.

[0121] According to one embodiment, the first artificial intelligence model (731) may be stored in memory (530) (e.g., memory (530) of FIG. 5) or stored on a separate server or external device. For example, the first artificial intelligence model (731) may learn training data through a deep learning algorithm. The training data may consist of pairs of data and labels (ground truth values ​​of the data). The first artificial intelligence model (731) may be configured to predict an improved image from a degraded image by learning training data consisting of pairs of a ground truth image and a degraded image (data) that is degraded compared to the ground truth image. According to one embodiment, the first artificial intelligence model (731) may include a model learned using a loss function.

[0122] For example, the artificial intelligence model (731) can be trained using a loss function so that the values ​​of the parameters included in the parameter set output from the first artificial intelligence model (731) correspond (match) each of the specified values.

[0123] For example, the first artificial intelligence model (731) can be trained using a loss function based on a specified image and a final image (e.g., the Nth image of FIG. 6a) obtained using the Nth parameter set (e.g., the Nth parameter set of FIG. 6) output from the first artificial intelligence model (731), so that the brightness distribution of the histogram of the final image and the brightness distribution of the histogram of the specified image correspond (match) to each other.

[0124] For example, the first artificial intelligence model (731) can be trained using a loss function based on each image obtained using each of the N parameter sets output from the first artificial intelligence model (731) and each of the specified images, such that the brightness distribution of the histogram of each image obtained using each of the N parameter sets corresponds (matches) with the brightness distribution of the histogram of each of the specified images.

[0125] FIG. 7b is a diagram illustrating the operation of an artificial intelligence model acquiring N sets of parameters according to one embodiment.

[0126] Referring to FIG. 7b, according to one embodiment, a first image may be provided (or input) to a second artificial intelligence model (732). According to one embodiment, the second artificial intelligence model (732) may acquire (or output) information about the first image. For example, the information about the first image may include information about the histogram of the first image. The second artificial intelligence model (732) may be implemented as a semantic artificial intelligence model. According to one embodiment, the second artificial intelligence model (732) may be stored in a memory (530) (e.g., the memory (530) of FIG. 5) or stored on a separate server or external device.

[0127] According to one embodiment, N times, representing information about the first image and the number of times the first image is smoothed, may be provided (or input) to the first artificial intelligence model (731). According to one embodiment, the first artificial intelligence model (731) may acquire (or output) N sets of parameters. The second artificial intelligence model (732) and the first artificial intelligence model (731) may be different from each other.

[0128] FIG. 7c is a diagram illustrating the operation of an artificial intelligence model acquiring N sets of parameters according to one embodiment.

[0129] Referring to FIG. 7c, according to one embodiment, a first image may be provided (or input) to a second artificial intelligence model (732). According to one embodiment, the second artificial intelligence model (732) may acquire (or output) information about the first image (e.g., features of the first image). For example, the information about the first image may include information about the histogram of the first image. The second artificial intelligence model (732) may be implemented as a semantic artificial intelligence model. According to one embodiment, the second artificial intelligence model (732) may be stored in memory (530) (e.g., memory (530) of FIG. 5) or stored on a separate server or external device.

[0130] According to one embodiment, a first image, information about the first image, and information indicating the number of times to smooth the first image (e.g., N times) may be provided (or input) to the first artificial intelligence model (731). According to one embodiment, the first artificial intelligence model (731) may obtain (or output) N sets of parameters based on the first image, information about the first image, and information indicating the number of times to smooth the first image (e.g., N times). The second artificial intelligence model (732) and the first artificial intelligence model (731) may be different from each other.

[0131] FIG. 8 is a flowchart illustrating the operation of an electronic device acquiring a second image in which the pixel values ​​of a first image have been changed, according to one embodiment.

[0132] Referring to FIG. 8, according to one embodiment, in operation 811, an electronic device (501) (e.g., the electronic device (501) of FIG. 5) may perform a function to change at least one pixel value among a plurality of pixel values ​​of a first image. For example, the electronic device (501) may perform operations to improve the brightness distribution (or brightness contrast) of the first image by performing a function to edit the first image. The function may represent a function to equalize the histogram of the first image so that the brightness values ​​of the pixels constituting the histogram of the first image are distributed uniformly (e.g., normalization, equalization).

[0133] According to one embodiment, in operation 813, the electronic device (501) may obtain N sets of parameters based on providing information about the first image to the first artificial intelligence model (731) (e.g., the first artificial intelligence model (731) of FIG. 7a). According to one embodiment, N may represent a natural number greater than or equal to 1.

[0134] According to one embodiment, the electronic device (501) may obtain information about the first image from the second artificial intelligence model (732) based on providing the first image to the second artificial intelligence model (732) (e.g., the second artificial intelligence model (732) of FIG. 7b) in response to executing the above function. According to one embodiment, the electronic device (501) may also obtain information about the first image through a separate algorithm.

[0135] For example, information about the first image may include information about the histogram of the first image. For example, information about the histogram may include standard deviation of intensity image histogram, kurtosis of intensity image histogram, and / or skewness of intensity image histogram.

[0136] For example, information about the first image may further include information about at least one object (e.g., person, animal, text, sky, or landscape) included in the first image.

[0137] For example, information regarding the first image may include information related to image quality. For example, information related to image quality may include a statistical naturalness measure (SNM), a measure of enhancement (EME), and / or a global contrast factor (GCF).

[0138] For example, information regarding the first image may include information related to the image texture. For example, information related to the image texture may include a vector of local binary patterns (LBP) rotationally invariant features, entropy of gray-level co-occurrence matrix, inertia of gray-level co-occurrence matrix, energy of gray-level co-occurrence matrix, correlation of gray-level co-occurrence matrix, homogeneity of gray-level co-occurrence matrix, FFT energy, FFT entropy, FFT inertia, and / or FFT homogeneity. According to one embodiment, the electronic device (501) may determine N times, which represents the number of times the histogram of the first image is smoothed to change at least one pixel value of the first image. For example, N times may be automatically set by the electronic device (501) or set by the user. According to one embodiment, the electronic device (501) may obtain N sets of parameters in advance before performing the operation of equalizing the histogram of the first image, based on providing information about the first image and N times to the first artificial intelligence model (731). According to one embodiment, each of the N sets of parameters may include at least one parameter for equalizing the histogram of each of the plurality of regions of the first image.At least one parameter may include at least one of the number of regions of the first image (e.g., tile size), a specified threshold value for each pixel value of a plurality of histograms corresponding to each of the plurality of regions (e.g., clip limit value), or a specified ratio for adjusting the pixel values ​​of the plurality of histograms (e.g., rescale value).

[0139] According to one embodiment, in operation 815, the electronic device (501) can sequentially smooth the histogram of the first image N times using N sets of parameters. According to one embodiment, the electronic device (501) can smooth the histogram of the first image N times based on at least one of the CLAHE (contrast limited adaptive histogram equalization) algorithm or the rescale algorithm using N sets of parameters.

[0140] According to one embodiment, in operation 817, the electronic device (501) can obtain a second image in which at least one pixel value among a plurality of pixel values ​​of the first image is changed based on sequentially smoothing the histogram of the first image N times using N sets of parameters. For example, the second image may represent an image in which the brightness distribution of the first image is changed. The second image may represent an image in which the brightness contrast of the first image is improved.

[0141] FIG. 9a is a flowchart illustrating the operation of an electronic device, according to a comparative embodiment, to acquire a second image from a first image using a set of parameters acquired to equalize the histogram of the first image twice.

[0142] Referring to FIG. 9a, according to a comparative embodiment, in operation 911, the electronic device can obtain a first set of parameters based on a first image. For example, according to a comparative embodiment, the electronic device can obtain a first set of parameters for changing at least one pixel value among a plurality of pixel values ​​of the first image based on the first image.

[0143] According to a comparative embodiment, in operation 913, the electronic device can obtain a second image in which at least one first pixel value of the first image is changed using a first parameter set. For example, the electronic device can obtain a second image in which at least one first pixel value of the first image is changed based on performing a histogram equalization operation on the histogram of the first image using a first parameter set.

[0144] According to a comparative embodiment, in operation 915, the electronic device can obtain a second parameter set based on the second image. For example, according to a comparative embodiment, the electronic device can obtain a second parameter set for changing at least one pixel value among a plurality of pixel values ​​of the second image based on the second image.

[0145] According to a comparative embodiment, in operation 917, the electronic device can obtain a third image in which at least one second pixel value of the second image is changed using a second parameter set. For example, the electronic device can obtain a third image in which at least one second pixel value of the first image is changed based on performing a histogram equalization operation on the histogram of the second image using a second parameter set.

[0146] The electronic device according to the comparative embodiment can acquire a set of parameters for equalization at the time of equalizing the histogram of the first image. That is, when performing N equalization operations on the histogram of the first image, the electronic device according to the comparative embodiment can acquire the corresponding set of parameters at the time when the histogram equalization operation is performed on the corresponding histogram. The electronic device according to the comparative embodiment may require a significant amount of time to acquire multiple sets of parameters for performing histogram equalization operations on multiple histograms. In other words, since a significant amount of time is required to acquire the corresponding set of parameters, a significant amount of time is required to equalize the histogram of the first image multiple times.

[0147] For example, an electronic device according to a comparative embodiment can obtain a second image by checking a first image stored in the memory of the electronic device, obtaining a first parameter set from the first image, and performing a histogram equalization operation using the first parameter set. An electronic device according to a comparative embodiment can store the second image in memory. An electronic device according to a comparative embodiment can obtain a third image by checking the second image stored in memory, obtaining a second parameter set from the second image, and performing a histogram equalization operation using the second parameter set. That is, in order to obtain a final image in which the pixel values ​​of the first image are changed, the electronic device according to the comparative embodiment must perform each operation of obtaining a parameter set every time, so a lot of time is required and memory usage may increase. An electronic device according to one embodiment (e.g., the electronic device (501) of FIG. 5) can acquire N sets of parameters in advance before performing a histogram equalization (HE) method to adjust the histogram of a first image N times (e.g., perform a histogram equalization (HE) method), thereby reducing the time to acquire a final image with a changed brightness distribution.

[0148] FIG. 9b is a flowchart illustrating the operation of an electronic device, according to one embodiment, to acquire a second image from a first image using a set of parameters acquired to equalize the histogram of a first image twice.

[0149] Referring to FIG. 9b, according to one embodiment, in operation 931, an electronic device (501) (e.g., the electronic device (501) of FIG. 5) may obtain a first parameter set and a second parameter set to perform a histogram equalization operation twice on a histogram of a first image. According to one embodiment, the electronic device (501) may obtain a first parameter set corresponding to a first order and a second parameter set corresponding to a second order after the first order from a first artificial intelligence model (731) (e.g., the first artificial intelligence model (731) of FIG. 7a).

[0150] According to one embodiment, in operation 935, the electronic device (501) can obtain a second image in which at least one first pixel value of the first image has been changed based on performing a histogram equalization operation on the histogram of the first image using a first parameter set.

[0151] According to one embodiment, in operation 939, the electronic device (501) can obtain a third image in which at least one second pixel value of the second image has been changed based on performing a histogram equalization operation on the histogram of the second image using a second parameter set. According to one embodiment, the third image may represent an image in which the brightness distribution of the first image has been changed.

[0152] For the sake of convenience of explanation, the operation of obtaining two sets of parameters to equalize the histogram twice has been described, but the description of the operation of obtaining two sets of parameters to equalize the histogram twice can be applied equally to the operation of obtaining N sets of parameters to perform histogram equalization on the histogram N times (N is a natural number greater than or equal to 1).

[0153] An electronic device (501) according to one embodiment can acquire N sets of parameters in advance before performing an equalization operation to equalize the histogram of a first image N times using a first artificial intelligence model (731), thereby reducing the time required to acquire a final image with a changed brightness distribution. Additionally, the electronic device (501) can acquire N sets of parameters faster than before using the first artificial intelligence model (731).

[0154] FIGS. 10a and FIGS. 10b are drawings for explaining the operation of an electronic device, according to one embodiment, to equalize the histogram of a first image using a first parameter set corresponding to a first order among parameter sets obtained to equalize the histogram of a first image twice. FIGS. 10c is a drawing for explaining the operation of an electronic device, according to one embodiment, to equalize the histogram corresponding to a first region among a plurality of regions of a first image.

[0155] Referring to FIG. 10a and FIG. 10b, according to one embodiment, an electronic device (501) can perform a histogram equalization operation on a histogram of a first image (201) using a first parameter set (1010) corresponding to a first order. For example, the electronic device (501) can perform a histogram equalization operation on each of a plurality of histograms corresponding to each of a plurality of regions (1011, 1012, 1013, 1014) of the first image (201).

[0156] According to one embodiment, the first parameter set (1010) may include the number of a plurality of regions (1011, 1012, 1013, 1014), a threshold value (e.g., clip limit) related to the distribution (or number) of pixels of each of a plurality of histograms corresponding to each of the plurality of regions (1011, 1012, 1013, 1014), and / or a value (e.g., rescale value) specified to rescale the distribution of the plurality of histograms corresponding to each of the plurality of regions (1011, 1012, 1013, 1014).

[0157] Referring to FIG. 10c, according to one embodiment, an electronic device (501) can perform a histogram equalization operation on a histogram (1020) corresponding to a first region (1011) of a first image (201) based on performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified clip limit (e.g., 0.1) for a first region (1011) of a first image (201), and / or performing a rescale algorithm using a specified rescale value (e.g., 0.9).

[0158] According to one embodiment, an electronic device (501) can obtain a histogram (1030) based on performing a contrast limited adaptive histogram equalization (CLAHE) algorithm on a histogram (1020) corresponding to a first region (1011) using a specified clip limit (e.g., 0.1). For example, the electronic device (501) can obtain a histogram (1030) by excluding from the histogram (1020) a region corresponding to a portion of the histogram (1020) that exceeds the specified clip limit, and compensating for the region of the histogram (1020) that exceeds the specified clip limit as an offset (1031).

[0159] Alternatively, according to one embodiment, the electronic device (501) may obtain a histogram (1040) based on performing a rescale algorithm on a histogram (1020) corresponding to a first region (1011) using a specified rescale value (e.g., 0.9). For example, the electronic device (501) may obtain a histogram (1040) by adjusting the histogram (1020) based on the specified rescale value and compensating the portion between the histogram adjusted based on the specified rescale value and the histogram (1020) as an offset (1041).

[0160] Alternatively, although not illustrated, according to one embodiment, the electronic device (501) may obtain an adjusted histogram by performing a CLAHE (contrast limited adaptive histogram equalization) algorithm and a rescale algorithm on a histogram (1020) corresponding to a first region (1011) using a specified clip limit (e.g., 0.1). For example, the electronic device (501) may perform the rescale algorithm after performing the CLAHE (contrast limited adaptive histogram equalization) algorithm, or may perform the CLAHE (contrast limited adaptive histogram equalization) algorithm after performing the rescale algorithm. The order of execution of the algorithms may be set by the user or automatically set by the electronic device (501).

[0161] For convenience of explanation, FIG. 10c only shows the histogram (1020) corresponding to the first region (1011) and the histograms (1030, 1040) obtained as a result of performing a histogram equalization operation on the histogram (1020) corresponding to the first region (1011).

[0162] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the second region (1012) of the first image by performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.2) for the second region (1012) of the first image (201) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.95).

[0163] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the third region (1013) of the first image by performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.3) for the third region (1013) of the first image (201) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.97).

[0164] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the fourth region (1014) of the first image by performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.4) for the fourth region (1014) of the first image (201) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.95).

[0165] According to one embodiment, the electronic device (501) can perform a histogram equalization operation on a histogram (1020) corresponding to a first region (1011) of a first image, a histogram equalization operation on a histogram corresponding to a second region (1012) of a first image, and a histogram equalization operation on a histogram corresponding to a third region (1013) of a first image. Based on performing a histogram equalization operation on a histogram corresponding to a fourth region (1014) of a first image, a third image (1101) (e.g., the third image (1101) of FIG. 11a) in which at least one pixel among a plurality of pixels of the first image is changed can be obtained.

[0166] FIGS. 11a and 11b are drawings for explaining the operation of an electronic device, according to one embodiment, to equalize the histogram of a third image using a second parameter set corresponding to a second order among parameter sets obtained to equalize the histogram of a first image twice. FIG. 11c is a drawing for explaining the operation of an electronic device, according to one embodiment, to equalize the histogram corresponding to a first region among a plurality of regions of a third image.

[0167] Referring to FIG. 11a and FIG. 11b, according to one embodiment, an electronic device (501) can perform a histogram equalization operation on a histogram of a third image (1101) using a second parameter set (1105) corresponding to a second order after a first order. For example, the electronic device (501) can perform a histogram equalization operation on each of a plurality of histograms corresponding to each of a plurality of regions (1111, 1112, 1113, 1114, 1115, 1116, 1117, 1118, 1119) of the third image (1101).

[0168] According to one embodiment, the second parameter set (1105) may include the number of a plurality of regions (1111, 1112, 1113, 1114, 1115, 1116, 1117, 1118, 1119), a specified distribution value (e.g., clip limit) of pixel values ​​of each of a plurality of histograms corresponding to each of the plurality of regions (1111, 1112, 1113, 1114, 1115, 1116, 1117, 1118, 1119), and / or a specified ratio value (e.g., rescale) for adjusting pixel values ​​of each of the plurality of histograms corresponding to each of the plurality of regions (1111, 1112, 1113, 1114, 1115, 1116, 1117, 1118, 1119).

[0169] Referring to FIG. 11c, according to one embodiment, an electronic device (501) may perform a histogram equalization operation on a histogram (1110) corresponding to a first region (1111) of a third image (1101) based on performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified value (e.g., 0.05) for a first region (1111) of a third image (1101). According to one embodiment, the electronic device (501) may obtain a histogram (1120) based on performing a histogram equalization operation on a histogram (1110) corresponding to a first region (1111) of a third image (1101). For example, the electronic device (501) can obtain a histogram (1120) by excluding from the histogram (1110) an area corresponding to a portion of the histogram (1110) that exceeds a specified threshold, and compensating for the area corresponding to a portion of the histogram (1110) that exceeds a specified threshold as an offset (1121).

[0170] Alternatively, according to one embodiment, the electronic device (501) may perform a histogram equalization operation on a histogram (1110) corresponding to the first region (1111) of the third image (1101) based on performing a rescale algorithm using a specified ratio value (e.g., 0.9) for the first region (1111) of the third image (1101). According to one embodiment, the electronic device (501) may obtain a histogram (1140) based on performing a histogram equalization operation on a histogram (1110) corresponding to the first region (1111) of the third image (1101). For example, the electronic device (501) can obtain a histogram (1140) by adjusting the histogram (1110) based on a specified ratio value and compensating the portion between the histogram adjusted based on the specified ratio value and the histogram (1110) as an offset (1141).

[0171] For convenience of explanation, FIG. 11c only shows the histogram (1110) corresponding to the first region (1111) of the third image (1101) and the histogram (1120, 1140) obtained as a result of performing a histogram equalization operation on the histogram (1110) corresponding to the first region (1111) of the third image (1101).

[0172] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the second region (1112) of the third image (1101) based on performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.1) for the second region (1112) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.99).

[0173] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the third region (1113) of the third image (1101) based on performing a contrast-limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.2) for the third region (1113) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.95).

[0174] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the fourth region (1114) of the third image (1101) based on performing a contrast-limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.2) for the fourth region (1114) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.97).

[0175] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the fifth region (1115) of the third image (1101) based on performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.3) for the fifth region (1115) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.99).

[0176] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the sixth region (1116) of the third image (1101) based on performing a contrast-limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.4) for the sixth region (1116) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.95).

[0177] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the seventh region (1117) of the third image (1101) based on performing a contrast-limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.1) for the seventh region (1117) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.95).

[0178] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the eighth region (1118) of the third image (1101) based on performing a contrast-limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.1) for the eighth region (1118) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.99).

[0179] According to one embodiment, the electronic device (501) can adjust the histogram corresponding to the ninth region (1119) of the third image (1101) based on performing a contrast limited adaptive histogram equalization (CLAHE) algorithm using a specified distribution value (e.g., 0.02) for the ninth region (1119) of the third image (1101) and / or performing a rescale algorithm using a specified ratio value (e.g., 0.89).

[0180] According to one embodiment, the electronic device (501) smooths a histogram (1120) corresponding to a first region (1111) of the third image (1101), a histogram corresponding to a second region (1112) of the third image (1101), a histogram corresponding to a third region (1113) of the third image (1101), a histogram corresponding to a fourth region (1114) of the third image (1101), a histogram corresponding to a fifth region (1115) of the third image (1101), a histogram corresponding to a sixth region (1116) of the third image (1101), a histogram corresponding to a seventh region (1117) of the third image (1101), a histogram corresponding to an eighth region (1118) of the third image (1101), and a histogram corresponding to a ninth region (1119) of the third image (1101). Based on this, a second image (202) (e.g., the second image (202) of FIG. 2) can be obtained in which at least one pixel among the plurality of pixels of the third image (1101) is changed. The second image (202) may represent an image in which the brightness distribution of the first image (201) is changed.

[0181] The technical problems to be solved in this disclosure are not limited to those mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art to which this disclosure pertains.

[0182] According to one embodiment, the electronic device (501) may include at least one processor (520) and a memory (530) for storing instructions.

[0183] According to one embodiment, the instructions may be configured to cause the electronic device (501) to perform a function to change at least one pixel value among a plurality of pixel values ​​of a first image when executed by the at least one processor (520).

[0184] According to one embodiment, the instructions may be configured such that when executed by the at least one processor (520), the electronic device (501) obtains N sets of parameters for changing the at least one pixel value among the plurality of pixel values ​​of the first image using the histogram of the first image from the first artificial intelligence (AI) model (731) in response to executing the function, based on providing information about the first image to the first artificial intelligence model, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters includes at least one parameter associated with the histogram of each of the plurality of regions of the first image, and the at least one pixel value of the first image is changed N times using the histogram of each of the plurality of regions of the first image using the N sets of parameters.

[0185] According to one embodiment, the instructions may be configured to change the value of at least one pixel of the first image based on performing a histogram equalization (HE) operation sequentially on the histogram of each of the plurality of regions of the first image N times using the N parameter sets, wherein the N parameter sets include a set of parameters for performing a histogram equalization operation on the histogram of the first image.

[0186] According to one embodiment, the instructions may be configured such that when executed by the at least one processor (520), the electronic device (501) obtains a first parameter set corresponding to a first order and a second parameter set corresponding to a second order after the first parameter set from the first artificial intelligence model to perform the histogram equalization operation twice on the histogram of the first image, and uses the first parameter set and the second parameter set to sequentially perform the histogram equalization operation twice on the histogram.

[0187] According to one embodiment, the instructions may be configured such that, when executed by the at least one processor (520), the electronic device (501) acquires a third image in which at least one first pixel value of the first image is changed based on performing a histogram equalization operation on the histogram of the first image using the first parameter set, and acquires a second image in which at least one second pixel value of the third image is changed based on performing a histogram equalization operation on the histogram of the third image using the second parameter set.

[0188] According to one embodiment, the instructions may be configured to obtain the N sets of parameters from the first artificial intelligence model based on the number of times the electronic device (501) performs the histogram equalization operation on the histogram of the first image to change the at least one pixel value based on executing the function, and providing the N times representing the number of times the histogram equalization operation on the histogram of the first image is performed to the first artificial intelligence model.

[0189] According to one embodiment, the instructions are configured such that when executed by the at least one processor (520), the electronic device (501) obtains information about the first image from the second artificial intelligence (AI) model (732) based on providing the first image to the second artificial intelligence (AI) model (732), and the second artificial intelligence model (732) may be different from the first artificial intelligence model.

[0190] According to one embodiment, information regarding the first image may include information regarding the histogram of the first image.

[0191] According to one embodiment, the instructions may be configured to acquire the second image based on the electronic device (501) performing the operation of sequentially performing histogram equalization on each of the plurality of regions N times using the N sets of parameters when executed by the at least one processor (520).

[0192] According to one embodiment, the instructions may be configured such that, when executed by the at least one processor (520), the electronic device (501) includes a clip limit value representing a threshold value related to the number of the plurality of regions and the distribution of pixels in the plurality of histograms corresponding to the plurality of regions, and when executed by the at least one processor, the electronic device may be configured to smooth the distribution of pixels exceeding the threshold value in a first histogram corresponding to a first region among the plurality of regions, and to adjust the smoothed first histogram using values ​​corresponding to the distribution of pixels exceeding the threshold value in the first histogram.

[0193] According to one embodiment, the instructions may be configured such that when executed by the at least one processor (520), the electronic device (501) is configured such that the at least one parameter includes a number of the plurality of regions and a specified value for adjusting the plurality of histograms corresponding to the plurality of regions, the first histogram corresponding to the first region among the plurality of regions is adjusted according to a specified ratio so that the first histogram does not exceed the specified value, and the adjusted first histogram is readjusted using values ​​corresponding to the difference in area between the first histogram and the adjusted first histogram.

[0194] According to one embodiment, the instructions may be configured such that when executed by the at least one processor (520), the electronic device (501) acquires the second image in which the brightness distribution of the first image is changed based on changing the at least one pixel value using the histogram of the first image N times using the N sets of parameters.

[0195] According to one embodiment, a method of operation of an electronic device (501) may include: an operation of executing a function to change at least one pixel value among a plurality of pixel values ​​of a first image; an operation of obtaining N sets of parameters for changing the at least one pixel value using a histogram of the first image from the first artificial intelligence (AI) model (731) based on providing information about the first image in response to executing the function; wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters includes at least one parameter associated with a histogram of each of the plurality of regions of the first image, and based on changing the at least one pixel value of the first image sequentially using the histogram of each of the plurality of regions of the first image N times using the N sets of parameters, thereby obtaining a second image in which the at least one pixel value among the plurality of pixel values ​​of the first image has been changed.

[0196] According to one embodiment, the method of operation of the electronic device (501) may include an operation of changing the value of at least one pixel of the first image based on performing a histogram equalization operation on each of the plurality of regions of the first image sequentially N times using the N parameter sets, wherein the N parameter sets include a set of parameters for performing a histogram equalization operation on the histogram of the first image.

[0197] According to one embodiment, the method of operation of an electronic device (501) may include the operation of obtaining a first parameter set corresponding to a first order and a second parameter set corresponding to a second order after the first parameter set from the first artificial intelligence model to perform the operation of histogram equalization twice on the histogram of the first image, and the operation of sequentially performing the histogram equalization twice on the histogram using the first parameter set and the second parameter set.

[0198] According to one embodiment, the method of operation of the electronic device (501) may include the operation of obtaining a third image in which at least one first pixel value of the first image is changed based on performing the operation of histogram equalization on the histogram of the first image using the first parameter set, and the operation of obtaining a second image in which at least one second pixel value of the third image is changed based on performing the operation of histogram equalization on the histogram of the third image using the second parameter set.

[0199] According to one embodiment, the method of operation of an electronic device (501) may include, based on executing the function, an operation of confirming the number of times the operation of histogram equalization is performed on the histogram of the first image to change the value of at least one pixel as N times, and an operation of obtaining the N sets of parameters from the first artificial intelligence model based on providing the N times representing the number of times the operation of histogram equalization is performed on the histogram of the first image to the first artificial intelligence model.

[0200] According to one embodiment, the method of operation of the electronic device (501) may include the operation of acquiring the second image based on performing the operation of sequentially performing the histogram equalization on each of the plurality of regions N times using the N sets of parameters.

[0201] According to one embodiment, the method of operation of an electronic device (501) may include, wherein the at least one parameter includes a clip limit value representing a threshold value related to the number of the plurality of regions and the distribution of pixels of the plurality of histograms corresponding to the plurality of regions, an operation of smoothing the distribution of pixels exceeding the threshold value in a first histogram corresponding to a first region among the plurality of regions, and an operation of adjusting the smoothed first histogram using values ​​corresponding to the distribution of pixels exceeding the threshold value in the first histogram.

[0202] According to one embodiment, the method of operation of an electronic device (501) may include, wherein the at least one parameter includes a number of regions and a specified value for adjusting a plurality of histograms corresponding to the plurality of regions, an operation of adjusting a first histogram according to a specified ratio such that a first histogram corresponding to a first region among the plurality of regions does not exceed the specified value, and an operation of readjusting the adjusted first histogram using values ​​corresponding to the difference in area between the first histogram and the adjusted first histogram.

[0203] According to one embodiment, in a non-transient storage medium for storing computer-readable instructions, the instructions cause the electronic device (501) to perform at least one operation when executed by at least one processor (520) of the electronic device (501), and the at least one operation is an operation to perform a function to change at least one pixel value among a plurality of pixel values ​​of a first image, and an operation to obtain N sets of parameters for changing the at least one pixel value using a histogram of the first image from the first artificial intelligence (AI) model (731) based on providing information about the first image in response to the execution of the function, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters includes at least one parameter associated with a histogram of each of the plurality of regions of the first image, and based on changing the at least one pixel value of the first image sequentially N times using the histogram of each of the plurality of regions of the first image using the N sets of parameters. The method may include the operation of obtaining a second image in which at least one pixel value among the plurality of pixel values ​​of the first image is changed.

[0204] The effects obtainable from the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by those skilled in the art to which the present disclosure belongs.

[0205] The electronic device according to the various embodiments disclosed in this document may be of various forms. The electronic device may include, for example, a portable communication device (e.g., a smartphone), a computer device, a portable multimedia device, a portable medical device, a camera, a wearable device, or a consumer electronics device. The electronic device according to the embodiments of this document is not limited to the devices described above.

[0206] The various embodiments of this document and the terms used therein are not intended to limit the technical features described in this document to specific embodiments, and should be understood to include various modifications, equivalents, or substitutions of said 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 said items unless the relevant context clearly indicates otherwise. In this document, each of phrases such as "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" may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. Terms such as “first,” “second,” or “first” or “second” may be used simply to distinguish a component from another component and do not limit the components in any other aspect (e.g., importance or order). Where any (e.g., first) component is referred to as “coupled” or “connected” to another (e.g., second) component, with or without the terms “functionally” or “communicationally,” it means that said component may be connected to said other component directly (e.g., via a wire), wirelessly, or through a third component.

[0207] The term “module” as used in the 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, for example. A module may be a component formed integrally, or a minimum unit of said component or a part thereof 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).

[0208] Various embodiments of this document may be implemented as software (e.g., program (140)) comprising one or more instructions stored in a storage medium (e.g., internal memory (136) or external memory (138)) readable by a machine (e.g., electronic device (101, 501)). For example, a processor (e.g., processor (120, 520)) of the machine (e.g., electronic device (101, 501)) may call at least one of the one or more instructions stored from the storage medium and execute it. This enables the machine to be operated 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 that can be executed by an interpreter. The storage medium readable by the machine may be provided in the form of a non-transitory storage medium. Here, 'non-transitory' is a device in which the storage medium is tangible, and It merely means that it does not contain a signal (e.g., electromagnetic waves), and this term does not distinguish between cases where data is stored semi-permanently and cases where it is stored temporarily on a storage medium.

[0209] According to one embodiment, the method according to the various embodiments disclosed herein may be provided by being included in a computer program product. The computer program product may be traded between a seller and a buyer 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 distributed online (e.g., download or upload) through an application store (e.g., Play Store™) or directly between two user devices (e.g., smartphones). In the case of online distribution, at least a portion of the computer program product may be temporarily stored or temporarily created on a device-readable storage medium, such as the memory of a manufacturer's server, an application store's server, or a relay server.

[0210] According to various embodiments, each component (e.g., module or program) of the components described above may include a singular or multiple entities, and some of the multiple entities may be separated and placed in other components. According to various embodiments, one or more of the components or operations of the aforementioned components may be omitted, or one or more other components or operations may be added. Generally or additionally, multiple components (e.g., module or program) may be integrated into a single component. In this case, the integrated component may perform one or more functions of each of the multiple components in the same or similar manner as those performed by the corresponding component among the multiple components prior to integration. According to various embodiments, operations performed by the module, program, or other components may be executed sequentially, in parallel, iteratively, or heuristically, or one or more of the operations may be executed in a different order, omitted, or one or more other operations may be added.

Claims

1. In an electronic device (501), At least one processor (520); and It includes a memory (530) for storing instructions, When the above instructions are executed by the at least one processor, the electronic device, Executing a function to change at least one pixel value among a plurality of pixel values ​​of a first image, and Based on providing information about the first image to the first artificial intelligence (AI) model (731) in response to executing the above function, N sets of parameters for changing the at least one pixel value using the histogram of the first image are obtained from the first artificial intelligence model, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters includes at least one parameter associated with the histogram of each of the plurality of regions of the first image. An electronic device configured to acquire a second image in which the at least one pixel value among the plurality of pixel values ​​of the first image is changed, based on sequentially changing the at least one pixel value of the first image N times using the histogram of each of the plurality of regions of the first image using the above N sets of parameters.

2. In Paragraph 1, When the above instructions are executed by the at least one processor, the electronic device, The above N sets of parameters include sets of parameters for performing a histogram equalization operation on the histogram of the first image, and An electronic device configured to change the value of at least one pixel of the first image based on performing a histogram equalization (HE) operation sequentially on the histogram of each of the plurality of regions of the first image N times using the above N sets of parameters.

3. In any one of paragraphs 1 to 2, the instructions, when executed by the at least one processor, cause the electronic device, Obtaining a first parameter set corresponding to a first order and a second parameter set corresponding to a second order following the first parameter set from the first artificial intelligence model to perform the histogram equalization operation twice on the histogram of the first image, An electronic device configured to perform the operation of sequentially performing histogram equalization on the histogram twice using the first parameter set and the second parameter set.

4. In any one of paragraphs 1 through 3, When the above instructions are executed by the at least one processor, the electronic device, Based on performing a histogram equalization operation on the histogram of the first image using the first parameter set, a third image is obtained in which at least one first pixel value of the first image is changed, and An electronic device configured to acquire the second image in which at least one second pixel value of the third image has been changed, based on performing a histogram equalization operation on the histogram of the third image using the second parameter set.

5. In any one of paragraphs 1 through 4, When the above instructions are executed by the at least one processor, the electronic device, Based on executing the above function, the number of times the histogram equalization operation is performed on the histogram of the first image to change the at least one pixel value is determined to be N times, and An electronic device configured to obtain the N sets of parameters from the first artificial intelligence model based on providing the first artificial intelligence model with the N times representing the number of times the histogram equalization operation is performed on the histogram of the first image.

6. In any one of paragraphs 1 through 5, When the above instructions are executed by the at least one processor, the electronic device, Based on providing the first image to the second artificial intelligence (AI) model (732), information about the first image is obtained from the second artificial intelligence model, and The above second artificial intelligence model is an electronic device different from the above first artificial intelligence model.

7. In any one of paragraphs 1 through 6, An electronic device comprising information regarding the first image, including information regarding the histogram of the first image.

8. In any one of paragraphs 1 through 7, When the above instructions are executed by the at least one processor, the electronic device, An electronic device configured to acquire the second image based on performing the histogram equalization operation sequentially on the histograms of each of the plurality of regions N times using the above N sets of parameters.

9. In any one of paragraphs 1 through 8, The above at least one parameter includes a clip limit value representing a threshold value related to the number of the plurality of regions and the distribution of pixels of the plurality of histograms corresponding to the plurality of regions, and When the above instructions are executed by the at least one processor, the electronic device, Smoothing the distribution of pixels exceeding the threshold value in a first histogram corresponding to a first region among the plurality of regions, and An electronic device configured to adjust the first histogram using values ​​corresponding to the distribution of pixels exceeding the threshold value in the first histogram.

10. In any one of paragraphs 1 through 9, The above at least one parameter includes a specified value for adjusting the number of the plurality of regions and the plurality of histograms corresponding to the plurality of regions, and When the above instructions are executed by the at least one processor, the electronic device, The first histogram corresponding to the first region among the plurality of regions is adjusted according to a specified ratio so that the first histogram does not exceed the specified value, and An electronic device configured to readjust the adjusted first histogram using values ​​corresponding to the difference in area between the first histogram and the adjusted first histogram.

11. In any one of paragraphs 1 through 10, When the above instructions are executed by the at least one processor, the electronic device, An electronic device configured to acquire a second image in which the brightness distribution of the first image is changed based on changing the value of at least one pixel N times using the histogram of the first image using the above N sets of parameters.

12. In the method of operating the electronic device (501), An operation to execute a function for changing at least one pixel value among a plurality of pixel values ​​of a first image; Based on providing information about the first image to a first artificial intelligence (AI) model (731) in response to executing the above function, the operation of obtaining N sets of parameters for changing the at least one pixel value using a histogram of the first image from the first artificial intelligence model, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters includes at least one parameter associated with the histogram of each of the plurality of regions of the first image; and A method of operation of an electronic device comprising the operation of acquiring a second image in which the at least one pixel value among the plurality of pixel values ​​of the first image is changed, based on sequentially changing the at least one pixel value of the first image N times using the histogram of each of the plurality of regions of the first image using the above N sets of parameters.

13. In Paragraph 12, The above N sets of parameters include sets of parameters for performing a histogram equalization operation on the histogram of the first image, and A method of operation of an electronic device further comprising an operation of changing the value of at least one pixel of the first image based on performing a histogram equalization (HE) operation sequentially on the histogram of each of the plurality of regions of the first image N times using the above N sets of parameters.

14. In any one of claims 12 to 13, the operation of obtaining a first parameter set corresponding to a first order and a second parameter set corresponding to a second order following the first parameter set from the first artificial intelligence model to perform the operation of histogram equalization twice on the histogram of the first image; and A method of operating an electronic device further comprising the operation of sequentially performing histogram equalization on the histogram twice using the first parameter set and the second parameter set.

15. In a non-transient storage medium for storing computer-readable instructions, said instructions cause said electronic device (501) to perform at least one operation when executed by at least one processor (520) of said electronic device, said at least one operation is: An operation to execute a function for changing at least one pixel value among a plurality of pixel values ​​of a first image; Based on providing information about the first image to a first artificial intelligence (AI) model (731) in response to executing the above function, the operation of obtaining N sets of parameters for changing the at least one pixel value using a histogram of the first image from the first artificial intelligence model, wherein N is a natural number greater than or equal to 1, and each of the N sets of parameters includes at least one parameter associated with the histogram of each of the plurality of regions of the first image; and A storage medium comprising the operation of acquiring a second image in which the at least one pixel value among the plurality of pixel values ​​of the first image is changed, based on sequentially changing the at least one pixel value of the first image N times using the histogram of each of the plurality of regions of the first image using the above N parameter sets.

Images