Display device and figure skin color compensation method

Abstract

The invention provides a display device and a figure skin color compensation method, and the method comprises the steps: recognizing a partition boundary through a boundary pixel difference value, dividing a face into a preset number of partitions, and screening a to-be-compensated region based on the deviation between each partition and an original skin color pixel value. According to the method, a local area with abnormal chromatic aberration caused by the illumination condition in the video frame can be accurately positioned, unnecessary adjustment of a normal skin color area is avoided, and more targeted compensation operation can be executed on a target person. According to the method, the original skin color pixel value of a normal skin color area is reserved, targeted skin color compensation is executed by dividing a plurality of face subareas, and the skin color secondary distortion phenomenon caused by executing skin color compensation on the whole face area is effectively eliminated.

Description

Technical Field

[0001] The present application relates to the technical field of display devices, and in particular, to a display device and a method for compensating human skin color. Background Art

[0002] A display device is a terminal device for displaying a picture and an application program installed in the display device. The display device can output different display pictures. The display device can implement picture rendering and interaction functions through a built-in application program to output a display picture, or guide a user to input an operation instruction according to the output display picture, so as to interact with the display device.

[0003] Due to the dynamic change of the illumination conditions of the shooting scene, in a media video, there are regional skin color differences of the same person in a single frame of the picture. For example, in a strong side light environment, the skin color of the backlight area of the person's face will form an obvious color deviation from the original skin color of the person, resulting in skin color misalignment in the face of the person in the picture output by the display device, affecting the overall coordination of the person's image and also affecting the user experience when watching video content.

[0004] To solve the problem of skin color distortion of the human face, the display device can perform compensation adjustment on the face area. However, when there are local highlight or backlight areas on the human face, the display device may overcompensate the normal skin color area that is not affected by the illumination conditions, causing unnecessary chromaticity adjustment of the normal skin color pixels, resulting in a secondary distortion problem of the compensated skin color. Summary of the Invention

[0005] The present application provides a display device and a method for compensating human skin color to solve the problem of secondary skin color distortion that occurs when performing skin color compensation on the entire face area.

[0006] In a first aspect, some embodiments of the present application provide a display device, including a display and a controller. The display is configured to display a user interface; the controller is configured to:

[0007] In response to a skin color compensation instruction, during the playback of media data, identify a target person in the currently displayed video frame;

[0008] In the face area of the target person, identify a partition boundary formed by boundary pixel points, where the first pixel difference between the boundary pixel points and at least one adjacent pixel point is greater than or equal to a first pixel threshold;

[0009] According to the partition boundary, divide the face area into a preset number of face partitions;

[0010] Calculate a second pixel difference between the average pixel value of each face partition and the original skin color pixel value of the target person;

[0011] Mark the face sub - regions where the second pixel difference is greater than or equal to the second pixel threshold as the sub - regions to be compensated;

[0012] Perform skin - color compensation on the sub - regions to be compensated in the video frame by using the skin - color optimization parameters calculated based on the original skin - color pixel values.

[0013] The above - mentioned technical solution has the following beneficial effects or advantages: By identifying the facial region of the target person and dividing the face into sub - regions, the problem of secondary distortion caused by compensating the entire facial region in the traditional method is solved. First, the partition boundaries are identified through the boundary pixel differences, and the face is divided into a preset number of sub - regions. Then, the sub - regions to be compensated are selected based on the deviation between each sub - region and the original skin - color pixel values. Thus, the local regions with abnormal color differences caused by high - light or shadow are accurately located, avoiding unnecessary adjustments to the normal skin - color regions and solving the phenomenon of secondary skin - color distortion caused by full - region compensation.

[0014] In some embodiments, before the controller executes the step of calculating the second pixel difference between the average pixel value of each face sub - region and the original skin - color pixel value of the target person, it is further configured to:

[0015] Identify the facial features of the target person through a person recognition algorithm;

[0016] In the played video frames of the media data, identify the target person according to the facial features;

[0017] If the target person is identified, extract the original skin - color pixel values according to the target person in the played video frame.

[0018] The above - mentioned technical solution has the following beneficial effects or advantages: Through the person recognition algorithm, in the played video frames, perform person recognition on the target person, so as to extract the original skin - color pixel values of the target person in other video frames to determine the reference value of the target person's skin - color, making the subsequent partition compensation of the person's face have a comparison standard, and significantly improving the accuracy and stability of skin - color restoration.

[0019] In some embodiments, when the controller executes extracting the original skin - color pixel values according to the target person in the played video frame, it is specifically configured to:

[0020] In the played video frame, identify the first pixel value of the facial region of the target person and the second pixel value of the non - facial region; the first pixel value is the regional pixel value of the facial region, and the second pixel value is the regional pixel value of the non - facial region;

[0021] Perform a weighted average on the first pixel value and the second pixel value to obtain an average pixel value of the first pixel value and the second pixel value;

[0022] Match the original skin color pixel value in the human skin color pixel library according to the average pixel value, and the human skin color pixel library stores skin color pixel values extracted according to different skin color samples.

[0023] The above technical solution has the following beneficial effects or advantages: By fusing and calculating the pixel values of the human face / non-face area of the human body and matching with the skin color library, the extraction accuracy of the original skin color pixel value of the target person is improved. In this embodiment, by simultaneously analyzing the first pixel value of the face area and the second pixel value of non-face areas such as the hand and torso areas, calculating the average pixel value of the target person, and combining with a pre-built skin color pixel library for similarity matching, it can effectively overcome the influence of a single pixel value on judging the original skin color pixel value of the target person, and ensure the accuracy of the extracted original skin color value conforming to the true skin color characteristics of the person.

[0024] In some embodiments, before the controller executes the step of performing skin color compensation on the partition to be compensated in the video frame by using the skin color optimization parameter calculated based on the original skin color pixel value, the controller is further configured to:

[0025] Determine the type of illumination area to which the partition to be compensated belongs according to the relative position of the partition to be compensated in the face area;

[0026] Generate the skin color optimization parameter based on the original skin color pixel value of the target person and the type of illumination area.

[0027] The above technical solution has the following beneficial effects or advantages: By determining the optimization parameter according to the type of illumination area, the physical rationality of the compensation operation is improved. According to different illumination conditions in the video frame, determine the illumination type to which the partition to be compensated belongs in the face area, and thus determine the skin color optimization parameter for different partitions to be compensated according to the illumination type, so as to perform different degrees of skin color optimization on different partitions to be compensated.

[0028] In some embodiments, the type of illumination area includes a light-receiving area or a backlight area. When the controller executes the step of generating the skin color optimization parameter based on the original skin color pixel value of the target person and the type of illumination area, the controller is specifically configured to:

[0029] Generate a first skin color optimization parameter based on the original skin color pixel value of the target person and the light-receiving area, and the first skin color optimization parameter is used to indicate performing downward skin color compensation on the partition to be compensated corresponding to the light-receiving area;

[0030] Generate a second skin color optimization parameter based on the original skin color pixel values of the target person and the backlight area, where the second skin color optimization parameter is used to indicate upward skin color compensation for the partition to be compensated corresponding to the backlight area.

[0031] The above technical solution has the following beneficial effects or advantages: By differentiating the highlight and backlight areas to implement differential compensation, the problem of single compensation direction is solved. In this embodiment, downward compensation parameters are designed for the illuminated area, and upward compensation parameters are designed for the backlight area, which can handle both over-bright and over-dark areas at the same time. On the premise of maintaining the overall facial tone uniformity, the skin color layering in the high dynamic range scene is effectively restored.

[0032] In some embodiments, the step of the controller performing skin color compensation on the partition to be compensated in the video frame by using the skin color optimization parameter calculated based on the original skin color pixel values is specifically configured as:

[0033] Input the skin color optimization parameter into a skin color compensation model, so as to parse, through the skin color compensation model, a compensation item and a compensation value corresponding to the compensation item according to the skin color optimization parameter; the compensation item includes a contrast compensation item, a saturation compensation item, and a brightness compensation item;

[0034] Perform skin color compensation on the partition to be compensated according to the compensation value of the contrast compensation item, the compensation value of the saturation compensation item, and the compensation value of the brightness compensation item.

[0035] The above technical solution has the following beneficial effects or advantages: Multi-dimensional collaborative adjustment is realized through the skin color compensation model, and the naturalness of the compensation effect on the partition to be compensated is improved. In this embodiment, the optimization parameter is decomposed into three compensation items of contrast, saturation, and brightness and their quantization values, and the partition to be compensated is compensated through this multi-dimensional compensation mechanism, thereby improving the compensation effect.

[0036] In some embodiments, the step of the controller performing skin color compensation on the partition to be compensated in the video frame by using the skin color optimization parameter calculated based on the original skin color pixels is further configured as:

[0037] Identify non-human features in the facial area, where the non-human features are used to characterize the object features that block the facial area of the target person;

[0038] Mark the area corresponding to the non-human feature as a non-compensation area;

[0039] In the partition to be compensated, perform skin color compensation on the area other than the non-compensation area according to the skin color optimization parameter.

[0040] The above technical solution has the following beneficial effects or advantages: By excluding the interference areas of non-human features, the accuracy of the compensation operation is improved. In this application, by identifying the non-human features that block the facial area, the blocked area is marked as a non-compensation area, avoiding incorrect compensation of non-human features according to the skin color optimization parameters, and reducing the distortion problem of the pixel values of these non-human features themselves.

[0041] In some embodiments, after the controller executes the step of identifying the target person in the currently displayed video frame, it is further configured to:

[0042] Detect the facial orientation of the target person;

[0043] In the video frame, according to the human contour corresponding to the facial orientation, identify the facial contour pixel points of the target person;

[0044] Mark the area formed by the facial contour pixel points as the facial area of the target person.

[0045] The above technical solution has the following beneficial effects or advantages: By optimizing contour extraction through facial orientation recognition, the deflection angle of the person is detected in real time, and the facial contour recognition strategy is dynamically adjusted, so that the facial partition reference is always consistent with the current facial projection, ensuring the partition accuracy in multi-angle shooting scenarios such as top view and bottom view.

[0046] In some embodiments, the facial orientation is a front orientation or a side orientation. When the controller executes the step of identifying the facial contour pixel points of the target person according to the human contour corresponding to the facial orientation, it is specifically configured to:

[0047] When the facial orientation is the front orientation, identify the facial contour pixel points of the target person according to the first human contour area corresponding to the front orientation;

[0048] When the facial orientation is the side orientation, identify the facial contour pixel points of the target person according to the second human contour area corresponding to the side orientation.

[0049] The above technical solution has the following beneficial effects or advantages: By establishing contour recognition methods for different orientations, the accuracy of determining the facial area is improved. In this embodiment, by performing feature matching according to the real-time orientation during recognition, the problem of missed detection of the facial area caused by non-front angles is solved, ensuring the integrity of skin color compensation at various shooting angles.

[0050] In a second aspect, some embodiments of this application further provide a method for compensating the skin color of a person, which is applied to the display device described in the first aspect. The method includes:

[0051] In response to a skin color compensation instruction, during the playback of media data, identify the target person in the currently displayed video frame;

[0052] In the facial area of the target person, identify the partition boundary formed by boundary pixel points, where the first pixel difference between the boundary pixel points and at least one adjacent pixel point is greater than or equal to a first pixel threshold;

[0053] According to the partition boundary, divide the facial area into a preset number of facial partitions;

[0054] Calculate the second pixel difference between the average pixel value of each facial partition and the original skin color pixel value of the target person;

[0055] Mark the facial partitions with the second pixel difference greater than or equal to a second pixel threshold as partitions to be compensated;

[0056] Perform skin color compensation on the partitions to be compensated in the video frame through skin color optimization parameters calculated based on the original skin color pixel value.

[0057] As can be seen from the above technical solutions, the present application provides a display device and a method for compensating the skin color of a person. The method identifies the partition boundary through the boundary pixel difference, divides the face into a preset number of partitions, and then screens the areas to be compensated based on the deviation between each partition and the original skin color pixel value. This method can accurately locate the local areas with abnormal color differences caused by the lighting conditions in the video frame, and at the same time avoid unnecessary adjustments to the normal skin color areas, enabling more targeted compensation operations to be performed on the target person. This method not only retains the original skin color pixel value of the normal skin color area, but also divides multiple facial partitions and performs targeted skin color compensation, effectively eliminating the phenomenon of secondary skin color distortion caused by performing skin color compensation on the entire facial area. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0059] Figure 1 It is a schematic diagram of the operation scenario between the display device and the control device provided by some embodiments of the present application;

[0060] Figure 2 It is a schematic diagram of the hardware configuration of the display device provided by some embodiments of the present application;

[0061] Figure 3Schematic diagram of the software configuration of the display device provided by some embodiments of the present application;

[0062] Figure 4 Flowchart of the method for the display device to perform skin color compensation for a person provided by some embodiments of the present application;

[0063] Figure 5 Timing diagram of the method for the display device to perform skin color compensation for a person provided by some embodiments of the present application;

[0064] Figure 6 Flowchart of the display device for generating a partition boundary provided by some embodiments of the present application;

[0065] Figure 7 Schematic diagram of the facial area for the display device to obtain the front-facing direction of a person provided by some embodiments of the present application;

[0066] Figure 8 Schematic diagram of the facial area for the display device to obtain the side-facing direction of a person provided by some embodiments of the present application;

[0067] Figure 9 Flowchart of the display device for determining a partition to be compensated provided by some embodiments of the present application;

[0068] Figure 10 Flowchart of the display device for dividing multiple partitions to be compensated provided by some embodiments of the present application;

[0069] Figure 11 Flowchart of the display device for performing compensation on multiple partitions to be compensated provided by some embodiments of the present application;

[0070] Figure 12 Flowchart of the first embodiment of the display device for extracting the original skin color pixel value provided by some embodiments of the present application;

[0071] Figure 13 Flowchart of the second embodiment of the display device for extracting the original skin color pixel value provided by some embodiments of the present application;

[0072] Figure 14 Flowchart of the display device for performing skin color compensation provided by some embodiments of the present application. Detailed implementation manners

[0073] The embodiments will be described in detail below, and the examples are shown in the drawings. When the following description refers to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following embodiments do not represent all implementation manners consistent with the present application. They are only examples of the systems and methods consistent with some aspects of the present application detailed in the claims.

[0074] It should be noted that the brief description of terms in this application is only for the convenience of understanding the following-described embodiments, rather than intending to limit the embodiments of this application. Unless otherwise specified, these terms should be understood in their ordinary and usual meanings.

[0075] In this application, terms such as "first", "second", "third", etc. in the specification, claims, and the above-mentioned drawings are used to distinguish similar or like objects or entities, and do not necessarily imply limiting a specific order or sequence, unless otherwise noted. It should be understood that such terms can be interchanged under appropriate circumstances.

[0076] The terms "comprising" and "having" and any variations thereof are intended to cover but not be exclusive of inclusion. For example, a product or device comprising a series of components does not necessarily have to be limited to all the components clearly listed, but may include other components not clearly listed or inherent to these products or devices.

[0077] The term "module" refers to any known or later-developed hardware, software, firmware, artificial intelligence, fuzzy logic, or a combination of hardware or / and software code that can perform functions related to that element.

[0078] In the embodiments of this application, the display device 200 generally refers to a device having the capabilities of displaying images and processing data. For example, the display device 200 includes but is not limited to smart TVs, mobile terminals, computers, monitors, advertising screens, wearable devices, virtual reality devices, augmented reality devices, etc.

[0079] Figure 1 This is a schematic diagram of the operation scenario between the display device and the control device provided for some embodiments of this application. As Figure 1 shown, the user can operate the display device 200 through touch operations, the mobile terminal 300, and the control device 100. Among them, the control device 100 is used to receive the operation instructions input by the user and convert the operation instructions into control instructions that the display device 200 can recognize and respond to. For example, the control device 100 can be a remote control, a stylus, a gamepad, etc.

[0080] The mobile terminal 300 can be used as a control device to perform the human-computer interaction between the user and the display device 200. The mobile terminal 300 can also be used as a communication device to establish a communication connection with the display device 200 for data interaction. In some embodiments, software applications can be installed on the mobile terminal 300 and the display device 200, and the connection communication can be achieved through network communication protocols to achieve the purpose of one-to-one control operations and data communication. It is also possible to transmit the audio and video content displayed on the mobile terminal 300 to the display device 200 to achieve the synchronous display function.

[0081] In some embodiments, the mobile terminal 300 or other electronic devices can also simulate the functions of the control device 100 by running an application program that controls the display device 200.

[0082] As Figure 1 also shown in, the display device 200 also communicates with the server 400 through various communication methods for data communication. The display device 200 is allowed to communicate and connect through a local area network (LAN), a wireless local area network (WLAN), and other networks.

[0083] The display device 200 can provide a broadcast receiving television function, and can also additionally provide an intelligent network television function with computer support functions, including but not limited to, network television, smart television, Internet Protocol Television (IPTV), etc.

[0084] Figure 2 For some embodiments of this application Figure 1 is the hardware configuration block diagram of the display device 200 in

[0085] In some embodiments, the display device 200 may include at least one of a tuner demodulator 210, a communication device 220, a detector 230, a device interface 240, a controller 250, a display 260, an audio output device 270, a memory, a power supply, and a user input interface.

[0086] In some embodiments, the detector 230 is used to collect signals from the external environment or interact with the outside. For example, the detector 230 includes a light receiver, a sensor for collecting the intensity of environmental light; or, the detector 230 includes an image collector, such as a camera, which can be used to collect external environmental scenes, user attributes, or user interaction gestures. Or, the detector 230 includes a sound collector, such as a microphone, etc., for receiving external sounds.

[0087] In some embodiments, the display 260 includes a display function component for presenting a picture and a driving component for driving image display. The display 260 is used to receive an image signal output from the controller 250 for display. For example, the display 260 can be used to display video content, image content, components of a menu manipulation interface, and a user manipulation UI interface, etc.

[0088] In some embodiments, the communication device 220 is a component for communicating with external devices or the server 400 according to various communication protocol types. The display device 200 can be provided with multiple communication devices 220 according to different supported communication methods. For example, when the display device 200 supports wireless network communication, the display device 200 can be provided with a communication device 220 including a WiFi function. When the display device 200 supports Bluetooth connection communication, the display device 200 needs to be provided with a communication device 220 including a Bluetooth function.

[0089] The communication device 220 can enable the display device 200 to communicate with an external device or a server 400 through a wireless or wired connection. Among them, the wired connection can connect the display device 200 to the external device through components such as data lines and interfaces. The wireless connection can connect the display device 200 to the external device through wireless signals or a wireless network. The display device 200 can directly establish a connection relationship with the external device, or can indirectly establish a connection relationship through a gateway, a router, a connection device, etc.

[0090] In some embodiments, the controller 250 may include at least one of a central processing unit, a video processor, an audio processor, a graphics processor, and a power processor, and the first interface to the nth interface for input / output. The controller 250 controls the operation of the display device and responds to user operations through various software control programs stored in the memory. The controller 250 controls the overall operation of the display device 200.

[0091] In some embodiments, the controller 250 and the tuner demodulator 210 may be located in different split devices, that is, the tuner demodulator 210 may also be in an external device of the main device where the controller 250 is located, such as an external set-top box, etc.

[0092] In some embodiments, the user can input a user command on the graphical user interface (GUI) displayed on the display 260, and then the user input interface receives the user input command through the graphical user interface (GUI).

[0093] In some embodiments, the audio output device 270 can be the built-in speaker of the display device 200, or can be an external audio output device connected to the display device 200. Among them, for the external audio output device connected to the display device 200, the display device 200 can also be provided with an external audio output terminal, and the audio output device can be connected to the display device 200 through the external audio output terminal to output the sound of the display device 200.

[0094] In some embodiments, the user input interface 280 can be used to receive instructions from user input.

[0095] In order to perform user interaction, in some embodiments, the display device 200 can run an operating system. The operating system is a computer program for managing and controlling the hardware resources and software resources in the display device 200. The operating system can control the display device to provide a user interface. For example, the operating system can directly control the display device to provide a user interface, or can provide a user interface by running an application program. The operating system also allows the user to interact with the display device 200.

[0096] It should be noted that the operating system may be a native operating system based on a specific operating platform, or a third-party operating system deeply customized based on a specific operating platform, or an independent operating system specially developed for the display device.

[0097] The operating system can be divided into different modules or layers according to the functions implemented, such as Figure 3 As shown, in some embodiments, the system is divided into four layers, from top to bottom, namely, the application layer (Applications) layer (referred to as "application layer"), the application framework layer (Application Framework) layer (referred to as "framework layer"), the system library layer and the kernel layer.

[0098] In some embodiments, the application layer is used to provide services and interfaces for applications so that the display device 200 can run applications and interact with users based on the applications. At least one application can be run in the application layer, and these applications can be window programs, system settings programs, clock programs, etc. that come with the operating system; they can also be applications developed by third-party developers. In specific implementations, the application packages in the application layer are not limited to the above examples.

[0099] The framework layer provides application programming interfaces (APIs) and programming frameworks for applications. The application framework layer includes some predefined functions. The application framework layer is equivalent to a processing center that determines the actions that applications in the application layer take. Through the API interface, applications can access system resources and obtain system services during execution.

[0100] like Figure 3 As shown, Figure 3 A software configuration diagram of a display device provided for some embodiments of the present application. In some embodiments, the system of the display device 200 can be divided into three layers, namely, an application layer, a middleware layer, and a hardware layer from top to bottom.

[0101] The application layer mainly includes applications on the TV and the application framework. Among them, applications are mainly applications developed based on the browser, such as HTML5 APPs and native applications.

[0102] The Application Framework is a complete program model that has all the basic functions required by standard application software, such as file access, data exchange, etc., as well as the usage interfaces for these functions (toolbars, status bars, menus, dialog boxes).

[0103] Native APPs can support online or offline, message push or local resource access.

[0104] The middleware layer includes various middleware such as TV protocols, multimedia protocols, and system components. The middleware can use the basic services (functions) provided by the system software to connect various parts of the application system on the network or different applications, and can achieve the purpose of resource sharing and function sharing.

[0105] The hardware layer mainly includes the HAL interface, hardware, and drivers. Among them, the HAL interface is the unified interface for docking all TV chips, and the specific logic is implemented by each chip. The drivers mainly include: audio driver, display driver, Bluetooth driver, camera driver, WIFI driver, USB driver, HDMI driver, sensor drivers (such as fingerprint sensors, temperature sensors, pressure sensors, etc.), and power supply drivers, etc.

[0106] It should be noted that the above examples are only simple divisions of the functions of the operating system, and do not limit the specific form of the operating system of the display device 200 in the embodiments of the present application. According to factors such as the functions of the display device and the type of the operating system, the number of levels and the specific level types included in the operating system can be in other forms.

[0107] In some embodiments, the display device 200 can implement diversified function operations through built-in multi-type application programs, such as application scenarios like web browsing, music playing, and video playing. When the display device 200 executes the video playing function, the display device 200 will display the interactive interface of the multimedia resource. The interactive interface integrates several function control icons representing different media resources. The user can trigger the operation instruction by touching and selecting the target control, or move the focus option in the interactive interface through the control device 100 and click the "OK" button to trigger the operation instruction. After receiving the user instruction, the display device 200 will execute the process of decoding the corresponding media resource and playing the media resource interface, and display the corresponding media resource interface on the display 260.

[0108] To implement an efficient resource transmission mechanism, the display device 200 can be configured with a communication device 220. After receiving a user operation instruction, the display device 200 can obtain media asset data through the communication device. First, a secure data channel is established with the sending device of the media asset data through the communication device 220. The sending device can be other terminal devices, for example, a device that sends media asset data to the display device 200 through screen mirroring or Bluetooth transmission, or can also be a server side, such as a communication server, a cloud server, etc.

[0109] After the establishment of the secure data channel is completed, the display device 200 can send a data transmission request for specified media asset data to the sending device. After parsing and processing the request, the sending device can transmit the corresponding media asset data back to the display device 200 through the established secure data channel, so that the display device 200 can completely receive the data stream and start decoding and playing to complete the interaction of the media asset data.

[0110] In the media asset data, due to the dynamic change of the illumination conditions of the shooting scene, there will be regional skin color differences of the same person in a single frame of the picture. For example, in a strong side light environment, the illuminated area of the person's face is affected by the light in the environment, and the skin color of the person's face will change, resulting in an obvious color deviation from the original skin color of the person. This causes the skin color of the person's face in the video frame to be misaligned when the display device 200 plays the video frame corresponding to the media asset data, affecting the overall coordination of the person's image and the user's viewing experience at the same time.

[0111] To reduce the skin color distortion problem of the person's face caused by the illumination conditions in the video frame, the display device 200 can perform skin color compensation based on the entire face area of the person to restore the real skin color of the person. However, when only a local area of the person's face is affected by the illumination, during the skin color compensation process, the display device 200 may over-compensate the normal skin color area that is not affected by the illumination conditions, causing unnecessary chromaticity adjustment to the normal skin color area that was not originally affected by the illumination, resulting in a secondary distortion problem of the compensated skin color.

[0112] To solve the problem of secondary skin color distortion that occurs when performing skin color compensation on the entire face area, some embodiments of the present application provide a display device 200, including a controller 250 and a display 260, wherein the display 260 is configured to display a user interface. The display device 200 is also configured to execute a method for compensating the skin color of a person, and the execution subject of this method is the controller 250.

[0113] During the process of the controller 250 executing the human skin color compensation method, it can be implemented through an interaction framework formed between the hardware module in the underlying hardware layer and the upper application layer. Among them, the hardware layer may include a human recognition module and an image processor. The human recognition module can recognize the human in the media data and identify the skin color area. The image processor is configured to perform compensation and rendering on the facial area to be compensated, and send the compensated video frame to the application layer, and display the compensated video frame picture of the application layer through the display 260.

[0114] Figure 4 The flowchart of the human skin color compensation method executed by the display device provided by some embodiments of the present application. Figure 5 The timing diagram of the human skin color compensation method executed by the display device provided by some embodiments of the present application. The display device 200 executes the human skin color compensation method according to the Figure 5 shown timing relationship. Refer to Figure 4 and Figure 5 , the method includes:

[0115] S100: In response to the skin color compensation instruction, during the process of playing media data, identify the target person in the currently displayed video frame.

[0116] The user can input a skin color compensation instruction during the process of the display device 200 playing media data, so that the display device 200 responds to the skin color compensation instruction and enters the skin color compensation mode, thereby performing skin color compensation on the person in the video frame of the media data and reducing the influence of the lighting conditions on the skin color of the person. It should be noted that the lighting influence in this embodiment refers to the lighting conditions in the picture corresponding to the media data, rather than the lighting conditions in the environment where the display device 200 is located.

[0117] In the skin color compensation mode, the controller 250 can obtain the video frame data being displayed by the application layer through the human recognition module located in the hardware layer, and identify the target person in the currently displayed video frame to determine the person who needs to perform skin color compensation. The human recognition module can recognize the person in the currently played video frame of the media data through a human recognition algorithm and mark it in the video frame. The controller 250 can return the marked video frame to the application layer for display to prompt the user about the recognized person situation and determine the target person.

[0118] In some embodiments, a video frame may include multiple characters. In this case, the controller 250 may set a way to mark each character in the video frame through the character recognition module. For example, each character may be framed by a rectangular box to determine the number of characters by the number of marks. The user may perform an interaction with the display device 200 through a selection instruction to determine a target character in the video frame with marks. The target character is the character for which skin color compensation needs to be performed. Among them, the selection instruction may indicate to select one character from multiple characters as the target character, or may indicate to select multiple characters as the target characters. Therefore, the target character may be one or multiple. After determining the target character, the controller 250 may cancel the display of the marks to facilitate the user to continue watching the media data.

[0119] S200: In the facial region of the target character, identify the partition boundary formed by the boundary pixel points.

[0120] Figure 6 It is a flowchart for a display device provided by some embodiments of the present application to generate a partition boundary. Refer to Figure 6 , in each video frame, based on the dynamically changing lighting conditions, there may be a light-receiving area in the facial region of the target character, resulting in distortion of the skin color due to the influence of light. At this time, the facial region of the target character may include a distorted area, that is, an area where the skin color changes due to the influence of light, such as Figure 6 the area of the shadow box part in the interface shown. It also includes a non-distorted area, that is, an area where the skin color does not change due to the influence of light, such as Figure 6 the facial area in the interface shown that is not marked by the shadow box. The non-distorted area retains the original skin color of the target character.

[0121] To improve the accuracy of determining the skin color compensation area, the controller 250 may identify the partition boundary formed by the boundary pixel points in the facial region of the target character. Based on the local influence of light, in the video frame, there will be boundary pixel points in the facial region of the target character that separate the distorted area and the non-distorted area.

[0122] The controller 250 can set a first pixel threshold to determine boundary pixel points, where the first pixel difference between a boundary pixel point and at least one adjacent pixel point is greater than or equal to the first pixel threshold. Since there are obvious skin color differences between the pixels in the distortion area and the non-distortion area, there should be a large pixel value gap between a boundary pixel point and at least one adjacent pixel point. The controller 250 can traverse the pixel values of each pixel point in the face area and calculate the first pixel difference between this pixel point and the pixel values of each adjacent pixel point. When the first pixel difference between at least one adjacent pixel point of this pixel point is greater than or equal to the first pixel threshold, it indicates that this pixel point is located between the distortion area and the non-distortion area, and the controller 250 can mark this pixel point as a boundary pixel point. If the first pixel difference between this pixel point and all adjacent pixel points is less than the first pixel threshold, it indicates that this pixel point is located within the distortion area or the non-distortion area and is not a boundary pixel point. After determining all the boundary pixel points, the controller 250 can generate a partition boundary according to the trajectory formed by the boundary pixel points.

[0123] In some embodiments, the target person in the video frame may have different face orientations, and different face orientations correspond to different human silhouettes. Correspondingly, the face area of the target person is also different. The controller 250 can detect the face orientation of the target person. First, the controller 250 locates the target person in the video frame through an image recognition algorithm and determines the face orientation of the target person through a face orientation detection module. Among them, the face orientation can include a front orientation and a side orientation. For example, when the target person is facing the screen directly, the face orientation is the front orientation. When the target person is sideways or obliquely facing the screen, the face orientation is the side orientation.

[0124] The controller 250 selects a corresponding human silhouette recognition model according to the detected face orientation. For a target person with a front orientation, the controller 250 can adopt a front silhouette recognition model, which can recognize the facial feature points of the front silhouette, such as eyes, nose, mouth, etc., and determine the facial silhouette pixel points according to these feature points. For a target person with a side orientation, the controller 250 can adopt a side silhouette recognition model, which can recognize the facial feature points of the side silhouette, such as the side face silhouette, ears, etc., and determine the facial silhouette pixel points according to the feature points.

[0125] In some embodiments, such as Figure 7As shown, when the face orientation is the front orientation, the controller 250 can determine the first person contour area corresponding to the front orientation, and identify the area where facial feature points such as eyes, nose, and mouth are located in the first person contour area. After the identification is completed, the controller 250 can use the front contour recognition algorithm to perform feature extraction and matching in the first person contour area, and identify the facial contour pixel points when the target person is in the front orientation. For example, the controller 250 can use a machine learning algorithm to extract features from the first person contour area, such as edge features and texture features of the face, and then match these features with a pre-stored facial feature library to find the matching facial features, thereby determining the facial contour pixel points. The controller 250 can connect the identified facial contour pixel points to form a closed facial area formed by the dotted line in the interface as shown in Figure 7 The closed facial area formed by the dotted line in the shown interface, and this area is the facial area of the target person.

[0126] As Figure 8 shown, when the face orientation is the side orientation, the controller 250 can identify the facial contour pixel points of the target person according to the second person contour area corresponding to the side orientation. The controller 250 can determine the second person contour area corresponding to the side orientation, and this area usually includes areas where feature points such as the side face contour and ears are located. The controller 250 can use the side contour recognition algorithm to perform feature extraction and matching on the second person contour area, and identify the facial contour pixel points when the target person is in the side orientation. The controller 250 then connects the identified facial contour pixel points to form a closed facial area formed by the dotted line in the interface as shown in Figure 8 The closed facial area formed by the dotted line in the shown interface, that is, the facial area of the target person.

[0127] S300: According to the partition boundary, divide the facial area into a preset number of face partitions.

[0128] After determining the partition boundary, the controller 250 can divide the facial area of the target person into a preset number of face partitions according to the partition boundary. The number of face partitions can be determined according to the shape and number of the partition boundaries. For example, when the partition boundary is a trajectory passing through the facial area, the facial area can be divided into two face partitions. The partition boundary can also be a regular or irregular circular trajectory. At this time, the facial area can be divided into face partitions formed by each partition boundary, and, in addition to these face partitions in the facial area, the remaining area in the facial area forms a face partition.

[0129] S400: Calculate the second pixel difference between the average pixel value of each face partition and the original skin color pixel value of the target person.

[0130] The controller 250 needs to determine the face part partitions that need to perform skin color compensation in the divided face part partitions. To this end, the controller 250 needs to calculate the second pixel difference between the average pixel value of each face part partition and the original skin color pixel value of the target person.

[0131] The face part partition is a local facial area with uniform pixel values, but the pixel values of each pixel point in the face part partition are not the same. Therefore, the controller 250 can traverse the pixel values of all pixel points in the face part partition and calculate the average pixel value of all pixel points in the face part partition according to the traversed pixel values, that is, the average pixel value of the face part partition.

[0132] Since multiple face part partitions can be divided in the facial area, these face part partitions respectively correspond to an average pixel value. Among them, the average pixel values of two adjacent face part partitions are different. However, the average pixel values of two non-adjacent face part partitions can be the same. For example, in the facial area, there are face part partition A, face part partition B, and face part partition C. Among them, face part partition B is an adjacent area affected by light, and face part partition A and face part partition C are non-adjacent original skin color areas. Face part partition B separates face part partition A and face part partition C. At this time, face part partition A and face part partition C are two independent face part partitions, and both face part partition A and face part partition C are original skin color areas and are not affected by the lighting conditions. Therefore, the average pixel value of face part partition A is the same as the average pixel value of face part partition C, both of which are the original skin color pixel values. The average pixel value of face part partition A is different from the average pixel value of face part partition B, and the average pixel value of face part partition B is different from the average pixel value of face part partition C.

[0133] As Figure 9 shown, after determining the average pixel value of the face part partition, the controller 250 can calculate the second pixel difference between the average pixel value of each face part partition and the original skin color pixel of the target person to determine the partition to be compensated that needs to perform skin color compensation among multiple face part partitions.

[0134] S500: Mark the face part partitions with the second pixel difference greater than or equal to the second pixel threshold as the partitions to be compensated.

[0135] To improve the accuracy of determining the partition to be compensated according to the second pixel difference, the controller 250 can set the second pixel threshold. The second pixel threshold characterizes the degree of difference between the average pixel value of the face part partition and the original skin color pixel value of the target person. When the second pixel difference is less than the second pixel threshold, it means that the difference between the average pixel value of the face part partition and the original skin color pixel value of the target person is small, and the average pixel value of the face part partition relatively conforms to the original skin color pixel value of the target person. Therefore, this face part partition is a non-distorted area.

[0136] When the second pixel difference is greater than or equal to the second pixel threshold, it indicates that the difference between the average pixel value of this facial partial area and the original skin color pixel value of the target person is relatively large, and the average pixel value of this facial partial area does not match the original skin color pixel value of the target person. Therefore, this facial partial area is a non-distorted area, and facial compensation needs to be performed on this facial partial area. The controller 250 can mark this facial partial area as an area to be compensated.

[0137] S600: Perform skin color compensation on the area to be compensated in the video frame through the skin color optimization parameters calculated based on the original skin color pixels.

[0138] The controller 250 can perform skin color compensation on the area to be compensated in the video frame through the skin color optimization parameters, so that the pixel values of the pixel points in the area to be compensated are restored to have a second pixel difference less than the second pixel threshold from the original skin color pixel value, approaching the original skin color of the target person.

[0139] As can be seen from the above technical solutions, in the embodiments of the present application, the partition boundaries are identified through the boundary pixel differences, the facial area is divided into a preset number of partitions, and then the areas to be compensated are screened based on the deviation of each partition from the original skin color pixel value, so as to accurately locate the local areas with abnormal color differences caused by the influence of light in the video frame, and avoid unnecessary adjustments to the normal skin color areas.

[0140] In some embodiments, during the process of performing skin color compensation on the area to be compensated in the video frame, the controller 250 can send the skin color optimization parameters to the image processor. After receiving the skin color optimization parameters, the image processor can analyze the area to be compensated that needs to be optimized, re-render the pixel points of the area to be compensated according to the skin color optimization parameters, and send the re-rendered video frame to the controller 250. The controller 250 can send the re-rendered video frame to the application layer to control the display 260 to display the re-rendered video frame in the user interface.

[0141] In some embodiments, the lighting conditions may simultaneously have different skin color effects on multiple facial partial areas of the facial area. Therefore, the controller 250 can determine the relative position of the area to be compensated in the facial area, determine the lighting area type of the area to be compensated, and generate skin color optimization parameters based on the original skin color pixel value of the target person and the lighting area type.

[0142] The lighting area type can include the light-receiving area and the backlight area. Among them, the light-receiving area is used to characterize that the area to be compensated is the highlight area directly in contact with the light, and the backlight area is the shadow area formed when the facial organs in the facial area block the light and is not directly in contact with the light.

[0143] In some embodiments, such as Figure 10As shown, the controller 250 can also identify the light irradiation angle in the video frame, and determine the light irradiation area type of the area to be compensated according to the normal angle corresponding to the irradiation angle and the relative position of the area to be compensated in the face area. For example, when the image of the target person in the video frame is a frontal image, the light level irradiates the target person from left to right. The controller 250 can divide the face area into two areas to be compensated as shown in Figure 10 the interface shown, that is, divide the face area into a first area to be compensated, that is, the left face, and a second area to be compensated, that is, the right face. The left face of the target person is directly exposed to the light irradiation. Therefore, the first area to be compensated is the light-receiving area, and the right face is not directly exposed to the light. Therefore, the second area to be compensated is the backlight area.

[0144] In some embodiments, when calculating the skin color optimization parameter according to the original skin color pixel value of the target person and the light irradiation area type, the controller 250 can combine the area properties of different light irradiation area types. For example, for the light-receiving area, due to the influence of light, the skin color pixel value of the first area to be compensated should be greater than the original skin color pixel value. For the backlight area, due to the influence of shadow, the skin color pixel value of the second area to be compensated should be less than the original skin color pixel value. Therefore, for different light irradiation type areas, the controller 250 can generate different skin color optimization parameters to perform different degrees of skin color compensation for different light irradiation type areas and improve the display effect of the person after skin color compensation.

[0145] In some embodiments, the controller 250 can intercept the area to be compensated in the video frame and convert the area to be compensated from the RGB color space to the YCbCr color space for easy color adjustment calculation. The YCbCr color space includes a luminance component (Y), a blue difference component (Cb), and a red difference component (Cr). In the YCbCr color space, the controller 250 can independently adjust the color and luminance of the area to be compensated. The controller 250 can use the original skin color pixel value as the target pixel value for skin color compensation, and automatically adjust the luminance value and color value of the area to be compensated in the YCbCr color space. When the average pixel value of the area to be compensated is the same as the original skin color pixel value, calculate the skin color optimization parameter according to the recorded dynamic luminance value and dynamic color value during adjustment.

[0146] Based on different light irradiation area types, different degrees of skin color compensation need to be performed on the areas to be compensated belonging to different light irradiation area types. Therefore, the skin color optimization parameters calculated by the controller 250 in the YCbCr color space are also different. As shown in Figure 11As shown, for the first partition to be compensated in the light-receiving area, the controller 250 can automatically adjust the brightness value and color value of the first partition to be compensated downward in the YCbCr color space according to the original skin color pixel value of the target person. When the average pixel value of the first partition to be compensated is the same as the original skin color pixel value, calculate the first skin color optimization parameter according to the dynamic brightness value and dynamic color value recorded during the adjustment, and then perform skin color compensation on the first partition to be compensated according to the first skin color optimization parameter.

[0147] For the second partition to be compensated in the backlight area, the controller 250 can automatically adjust the dynamic brightness value and dynamic color value of the second partition to be compensated upward in the YCbCr color space according to the original skin color pixel value of the target person. When the average pixel value of the second partition to be compensated is the same as the original skin color pixel value, calculate the second skin color optimization parameter according to the dynamic brightness value and dynamic color value recorded during the adjustment, and then perform skin color compensation on the second partition to be compensated according to the second skin color optimization parameter.

[0148] The first skin color optimization parameter is used to instruct the image processor to perform downward skin color compensation on the first partition to be compensated corresponding to the light-receiving area, such as reducing the brightness value or neutralizing the overexposed area, so as to offset the skin color overbright distortion caused by the light-receiving illumination on the first partition to be compensated. The second skin color optimization parameter is used to instruct the image processor to perform upward skin color compensation on the second partition to be compensated corresponding to the backlight area, such as increasing the saturation or brightness, so as to offset the skin color overdark distortion caused by the backlight shadow on the second partition to be compensated.

[0149] In some embodiments, the controller 250 can calibrate the partition to be compensated in combination with the organ features of the human face. For example, for some organ feature characteristics, natural light and shadow features may be formed. For example, the zygomatic area is prone to light reflection to form a light-receiving area, and the nasal wing area is not easy to reflect light and is prone to form a shadow area. Therefore, the controller 250 can identify the facial features of the target person through a face recognition model and the person recognition algorithm, and calibrate the current partition to be compensated according to the organ feature characteristics corresponding to the facial features.

[0150] Among them, the facial features of the person may include light-receiving characteristic organs and backlight characteristic organs. The controller 250 can calibrate and increase the light-receiving area according to the light-receiving characteristic organs. For example, when the zygomatic area is not in the light-receiving area, mark the zygomatic area as the light-receiving area. The controller 250 calibrates and increases the backlight area according to the backlight characteristic organs. For example, when the nasal wing area is not in the light-receiving area, the nasal wing area can be marked as the backlight area.

[0151] In some embodiments, the target person appears in the played video frames of the media data and is less affected by the illumination, and the facial area maintains the display of the original skin color pixels. Therefore, as Figure 12As shown, the controller 250 can extract the original skin color pixel values of the target person from the played video frames. The controller 250 can obtain the playback progress of the media data and perform frame splitting on the media data segment before the playback progress. After completing the frame splitting, the controller 250 can identify the target person in the played video frames of the media data according to the facial features of the person.

[0152] After identifying the target person, the controller 250 can extract the original skin color pixel values according to the identified target person in the played video frame. To improve the accuracy of skin color extraction, the controller 250 can perform skin color extraction on the facial area of the target person in the played video frame through a skin color recognition model. The skin color recognition model can extract the facial features of all the people in the played video frame and compare them with the facial features of the target person to obtain the feature similarity. When the feature similarity is greater than or equal to the similarity threshold, it indicates that there is a target person in the played video frame, and the skin color recognition model can extract the original skin color pixel values from the facial area of the target person.

[0153] If the skin color of the target person in the played video frame has been distorted, the extracted original skin color pixel values are also the distorted original skin color pixel values, which will lead to subsequent skin color compensation according to the distorted original skin color pixel values. Therefore, in some embodiments, to improve the accuracy of extracting the original skin color pixel values, the controller 250 can also calculate the original skin color pixel values by way of weighted averaging the skin color pixel values of the non-facial area and the facial area of the target person.

[0154] In some embodiments, the controller 250 can also identify the first pixel values of the facial area and the second pixel values of the non-facial area of the target person in the played video frame through the skin color recognition model. Among them, the non-facial area refers to the area of the exposed skin of the target person outside the facial area, such as the hands, arms or legs, etc.

[0155] After the controller 250 identifies the target person, the skin color recognition model can identify the skin exposed area of the target person by detecting the human key points of the target person. Among them, the human key points are the feature points used to represent the human body posture, and can include limb key points, joint key points and torso key points, etc. After obtaining the human key points, the skin color recognition model can extract the skin area of the target person in the played video frame through the human key points and extract the second pixel values of the non-facial area according to the skin area.

[0156] Such as Figure 13As shown, after obtaining the first pixel value and the second pixel value, the controller 250 can calculate the average pixel value of the first pixel value and the second pixel value to avoid solely relying on the facial area to determine the original skin color pixel value of the target person. The controller 250 can match the original skin color pixel value in the person skin color material library according to the average pixel value. Among them, the person skin color pixel library stores skin color pixel values extracted according to different skin color samples. For example, based on different ethnic groups, the person skin color pixel library can include corresponding skin color pixel values, or set different ranges of skin color pixel values. When the average pixel value is the same as the skin color pixel value, the controller 250 can output the matched skin color pixel value as the original skin color pixel value of the target person. Or, when the average pixel value is within the range of the skin color pixel value, the controller 250 can output the mean value or key value in the skin color pixel value range as the original skin color pixel value of the target person.

[0157] In some embodiments, before the skin color recognition model executes the skin color extraction function in the above embodiments, the controller 250 also needs to perform a specific training process on the skin color recognition model. For this purpose, the controller 250 can obtain a preset number of training data, and the training data can be image data containing people with different skin colors. The controller 250 inputs the training data into the skin color recognition model, so that the skin color recognition model extracts the skin color pixel value according to the training data, compares the extracted skin color pixel value with the preset pixel value label, calculates the training loss, and iteratively updates the parameters in the skin color recognition model based on the training loss. When the training loss is less than or equal to the preset loss threshold, the controller 250 can obtain the trained skin color recognition model.

[0158] In some embodiments, after obtaining the skin color optimization parameter, the controller 250 can input the skin color optimization parameter into the skin color compensation model, and the skin color compensation model is a multi-dimensional compensation analysis model based on the convolutional neural network architecture. The skin color compensation model can parse the skin color optimization parameter into a compensation item and a compensation value corresponding to the compensation item. Among them, the compensation item can include a contrast compensation item, a saturation compensation item, and a brightness compensation item, so as to perform skin color compensation on the partition to be compensated from three aspects of contrast, saturation, and brightness.

[0159] When the controller 250 performs skin color compensation on the partition to be compensated, as Figure 14 shown, the compensation value of the contrast compensation item, the compensation value of the saturation compensation item, and the compensation value of the brightness compensation item can be mapped to the YCbCr color space to perform hierarchical compensation. For example, in the Y channel, the brightness of the partition to be compensated is compensated and adjusted by the compensation value of the brightness compensation item, and in the CbCr channel, the color of the partition to be compensated is compensated and adjusted by the compensation value of the contrast compensation item and the compensation value of the saturation compensation item.

[0160] It should be noted that this embodiment does not specifically limit the order of performing brightness compensation and color compensation. In other embodiments of this embodiment, the color of the partition to be compensated can also be compensated first through the compensation values of the contrast compensation item and the saturation compensation item, and then the brightness of the partition to be compensated can be compensated through the compensation value of the brightness compensation item. It is also possible to compensate the brightness and color of the partition to be compensated separately at the same time.

[0161] After completing the skin color compensation of the partition to be compensated, the controller 250 can convert the compensated video frame back to the RGB color space and update the pixel values of the partition to be compensated to make the compensation effective, and retain the original pixel data of the non-compensated partition.

[0162] In some embodiments, before performing skin color compensation on the partition to be compensated, the facial area may include non-human features, and the non-human features are used to characterize the object features that block the facial area of the target person, such as masks, glasses, etc. The non-human features have their own pixel values. When the controller 250 performs skin color compensation on the partition to be compensated, there is no need to perform compensation on the area corresponding to the non-human features. For this reason, the controller 250 can identify non-human features in the facial area and mark the area corresponding to the non-human features as a non-compensated area. In the partition to be compensated, skin color compensation is performed on the area other than the non-compensated area according to the skin color optimization parameters to avoid non-human features in the facial area and only compensate the skin area of the person in the partition to be compensated, thereby improving the accuracy of skin color compensation.

[0163] It should be noted that the above embodiments only illustrate the technical solutions for performing skin color compensation on one target person in the video frame. In the actual application process, it is also possible to perform partition compensation on the facial areas of multiple target persons in the video frame. During the process of performing skin color compensation on multiple target persons, the order of skin color compensation for each target person is not limited.

[0164] Some embodiments of the present application also provide a method for compensating the skin color of a person, which is applied to the display device 200. The display device 200 at least includes a controller 250 and a display 260. The display 260 is configured to display a user interface. The method includes:

[0165] S100: In response to a skin color compensation instruction, during the process of playing media data, identify the target person in the currently displayed video frame.

[0166] S200: In the facial area of the target person, identify the partition boundary formed by the boundary pixel points.

[0167] Wherein, the first pixel difference between the boundary pixel point and at least one adjacent pixel point is greater than or equal to the first pixel threshold.

[0168] S300: Divide the facial area into a preset number of facial sub - areas according to the partition boundary.

[0169] S400: Calculate the second pixel difference between the average pixel value of each facial sub - area and the original skin - color pixel value of the target person.

[0170] S500: Mark the facial sub - areas where the second pixel difference is greater than or equal to the second pixel threshold as the sub - areas to be compensated.

[0171] S600: Perform skin - color compensation on the sub - areas to be compensated in the video frame through the skin - color optimization parameters calculated based on the original skin - color pixels.

[0172] As can be seen from the above technical solutions, the present application provides a display device and a method for compensating the skin color of a person. The method identifies the partition boundary through the boundary pixel difference, divides the face into a preset number of partitions, and then screens the areas to be compensated based on the deviation between each partition and the original skin - color pixel value. This method can accurately locate the local areas with abnormal color differences caused by the lighting conditions in the video frame, and at the same time avoid unnecessary adjustments to the normal skin - color areas, enabling more targeted compensation operations for the target person. This method not only retains the original skin - color pixel values of the normal skin - color areas, but also divides multiple facial sub - areas and performs targeted skin - color compensation, effectively eliminating the phenomenon of secondary skin - color distortion caused by performing skin - color compensation on the entire facial area.

[0173] For the same and similar parts among the various embodiments in this specification, reference can be made to each other and will not be repeated here.

[0174] Those skilled in the art can clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus a necessary general - purpose hardware platform. Based on such an understanding, the technical solutions in the embodiments of the present invention, in essence, or the part that makes contributions to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disc, etc., and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods in various embodiments or some parts of the embodiments of the present invention.

[0175] Finally, it should be noted that: the above - mentioned embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the various embodiments of the present application.

[0176] For ease of explanation, the above description has been presented in connection with specific embodiments. However, the foregoing exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Numerous modifications and variations are possible in light of the above teachings. The selection and description of the above embodiments were made to better explain the principles and practical applications, so that those skilled in the art can better use the embodiments and various different variations of the embodiments suitable for specific use considerations.

Claims

1. A display device, characterized in that, Including: A display configured to display a user interface; A controller configured to: In response to a skin color compensation instruction, during the playback of media data, identify a target person in the currently displayed video frame; In the facial area of the target person, identify a partition boundary formed by boundary pixel points, where the first pixel difference between the boundary pixel points and at least one adjacent pixel point is greater than or equal to a first pixel threshold; According to the partition boundary, divide the facial area into a preset number of face partitions; Calculate the second pixel difference between the average pixel value of each face partition and the original skin color pixel value of the target person; Mark the face partitions with the second pixel difference greater than or equal to a second pixel threshold as partitions to be compensated; Perform skin color compensation on the partitions to be compensated in the video frame through skin color optimization parameters calculated based on the original skin color pixel value.

2. The display device according to claim 1, wherein Before the controller executes the step of calculating the second pixel difference between the average pixel value of each face partition and the original skin color pixel value of the target person, it is further configured to: Identify the facial features of the target person through a person recognition algorithm; In the played video frames of the media data, identify the target person according to the facial features; If the target person is identified, extract the original skin color pixel value according to the target person in the played video frame.

3. The display device according to claim 2, wherein When the controller executes extracting the original skin color pixel value according to the target person in the played video frame, it is specifically configured to: In the played video frame, identify the first pixel value of the facial area and the second pixel value of the non-facial area of the target person; the first pixel value is the area pixel value of the facial area, and the second pixel value is the area pixel value of the non-facial area; Perform weighted averaging on the first pixel value and the second pixel value to obtain the average pixel value of the first pixel value and the second pixel value; Match the original skin color pixel value in the person skin color pixel library according to the average pixel value, and the person skin color pixel library stores skin color pixel values extracted according to different skin color samples.

4. The display device according to claim 1, characterized in that, Before the controller executes the step of performing skin color compensation on the partitions to be compensated in the video frame through skin color optimization parameters calculated based on the original skin color pixel value, it is further configured to: Determine the type of illumination area to which the partition to be compensated belongs according to the relative position of the partition to be compensated in the facial area; Generate the skin color optimization parameter based on the original skin color pixel value of the target person and the type of illumination area.

5. The display device according to claim 4, wherein The type of illumination area includes a light-receiving area or a backlight area. When the controller executes the step of generating the skin color optimization parameter based on the original skin color pixel value of the target person and the type of illumination area, it is specifically configured to: Generate a first skin color optimization parameter based on the original skin color pixel value of the target person and the light-receiving area, and the first skin color optimization parameter is used to indicate performing downward skin color compensation on the partition to be compensated corresponding to the light-receiving area; Generate a second skin color optimization parameter based on the original skin color pixel values of the target person and the backlight area, where the second skin color optimization parameter is used to indicate upward skin color compensation for the partition to be compensated corresponding to the backlight area.

6. The display device according to claim 1, wherein The step of the controller performing skin color compensation on the partition to be compensated in the video frame by using the skin color optimization parameter calculated based on the original skin color pixel values is specifically configured as: Input the skin color optimization parameter into a skin color compensation model, so as to parse, through the skin color compensation model, a compensation item and a compensation value corresponding to the compensation item according to the skin color optimization parameter; the compensation item includes a contrast compensation item, a saturation compensation item, and a brightness compensation item; Perform skin color compensation on the partition to be compensated according to the compensation value of the contrast compensation item, the compensation value of the saturation compensation item, and the compensation value of the brightness compensation item.

7. The display device according to claim 1, wherein The step of the controller performing skin color compensation on the partition to be compensated in the video frame by using the skin color optimization parameter calculated based on the original skin color pixels is further configured as: Identify non-human features in the facial area, where the non-human features are used to characterize the object features that block the facial area of the target person; Mark the area corresponding to the non-human features as a non-compensation area; In the partition to be compensated, perform skin color compensation on the area other than the non-compensation area according to the skin color optimization parameter.

8. The display device according to claim 1, characterized in that After the controller performs the step of identifying the target person in the currently displayed video frame, it is further configured as: Detect the facial orientation of the target person; In the video frame, identify the facial contour pixel points of the target person according to the human contour corresponding to the facial orientation; Mark the area formed by the facial contour pixel points as the facial area of the target person.

9. The display device according to claim 8, wherein, The facial orientation is a front orientation or a side orientation. The step of the controller identifying the facial contour pixel points of the target person according to the human contour corresponding to the facial orientation is specifically configured as: When the facial orientation is the front orientation, identify the facial contour pixel points of the target person according to the first human contour area corresponding to the front orientation; When the facial orientation is the side orientation, identify the facial contour pixel points of the target person according to the second human contour area corresponding to the side orientation.

10. A method for compensating human skin color, characterized in that, Applied to a display device, the display device includes a display and a controller, the display is configured to display a user interface, and the method includes: In response to a skin color compensation instruction, identify the target person in the currently displayed video frame during the process of playing media data; In the facial area of the target person, identify a partition boundary formed by boundary pixel points, where the first pixel difference between the boundary pixel points and at least one adjacent pixel point is greater than or equal to a first pixel threshold; According to the partition boundary, divide the facial area into a preset number of facial partitions; Calculate the second pixel difference between the average pixel value of each facial partition and the original skin color pixel value of the target person; Mark the facial partition whose second pixel difference is greater than or equal to a second pixel threshold as a partition to be compensated; Perform skin color compensation on the partition to be compensated in the video frame by using the skin color optimization parameter calculated based on the original skin color pixel value.

Images