Method and device for processing picture in video call, electronic equipment and storage medium

Abstract

The embodiment of the invention relates to the field of communication, in particular to a picture processing method and device in a video call, electronic equipment and a storage medium. The method comprises the following steps: acquiring a current video image displayed in a video call; recognizing a face area in the current video image, analyzing the image quality of the face area, and judging whether a preset image quality requirement is met or not; when it is judged that the image quality of the face area does not meet the image quality requirement, display parameters of a screen are adjusted; and optimizing and displaying subsequent video images in the video call based on the adjusted display parameters. According to the scheme, the video image display effect of the central control screen under the screen-to-screen talkback function can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of communications, and in particular to a method, device, electronic device and storage medium for processing images in a video call. Background Art

[0002] At present, many central control screens on the market have a screen-to-screen intercom function, which can display video images on the screen of the central control screen during the intercom process. However, when the intercom process takes place at night or in a dimly lit environment, the picture captured by the central control screen will be darker, making the video image presented on the central control screen unclear, affecting the video call effect and causing a poor user experience. Summary of the invention

[0003] The purpose of the embodiments of the present invention is to provide a method, device, electronic device and storage medium for processing images in a video call, so as to improve the video image display effect of the central control screen under the screen-to-screen intercom function and enhance the user experience.

[0004] In order to solve the above technical problems, an embodiment of the present invention provides a method for processing a picture in a video call, comprising:

[0005] Get the current video image displayed in the video call;

[0006] Identify a face region in the current video image, and analyze the image quality of the face region to determine whether it meets a preset image quality requirement;

[0007] If it is determined that the image quality of the face area does not meet the image quality requirement, adjusting the display parameters of the screen;

[0008] The subsequent video images in the video call are displayed in an optimized manner based on the adjusted display parameters.

[0009] The embodiment of the present invention further provides a device for processing a picture in a video call, comprising:

[0010] An acquisition module, used to acquire the current video image displayed in the video call;

[0011] A recognition module, used to recognize a face region in the current video image, and analyze the image quality of the face region to determine whether it meets a preset image quality requirement;

[0012] An adjustment module, configured to adjust display parameters of the screen when it is determined that the image quality of the face area does not meet the image quality requirement;

[0013] The display module is used to optimize the display of subsequent video images in the video call based on the adjusted display parameters.

[0014] An embodiment of the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for processing the screen in a video call in the above-mentioned embodiment.

[0015] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the method for processing images in a video call in the above embodiment is implemented.

[0016] An embodiment of the present invention further provides a computer program product. When the computer program product is executed on a terminal device, the electronic device executes any one of the above methods.

[0017] In an embodiment of the present invention, during an intercom call in the form of a video call on the central control screen, the current video image displayed in the video call is obtained; the face area in the current video image is identified, and the image quality of the face area is analyzed to determine whether it meets the preset image quality requirements; if the image quality of the face area does not meet the preset image quality requirements, the display parameters of the screen can be adjusted, and subsequent video images in the video call can be optimized based on the adjusted display parameters, so as to achieve image quality optimization of the face area, improve the video image display effect and thus improve the user experience.

[0018] In some embodiments, the obtaining of the current video image displayed in the video call includes: obtaining the current video image in the initial stage of the video call when it is confirmed that the current device executing the video call has turned on the automatic fill light function. This process can enter the video image quality optimization process early; by setting the automatic fill light function startup item in the device, it can be flexibly set whether the image quality optimization process is enabled.

[0019] In some embodiments, analyzing the image quality of the face region to determine whether it meets the preset image quality requirements includes: analyzing the face definition of the face region to determine whether the proportion of the region where the face definition does not meet the preset standard definition in the face region is greater than a preset value; if the proportion is greater than the preset value, it is determined that the image quality of the face region does not meet the preset image quality requirements. By quantifying the face definition ratio of the face region, accurate confirmation of the image quality requirements of the face region is achieved.

[0020] In some embodiments, when it is determined that the image quality of the face area does not meet the image quality requirements, adjusting the display parameters of the screen includes: when it is determined that the clarity of the face area does not meet the standard clarity, calculating the difference between the clarity of the face area and the standard clarity, and adjusting the display parameters of the screen based on the difference, so that the clarity of the adjusted face area meets the standard requirements.

[0021] In some embodiments, after optimizing and displaying subsequent video images in the video call based on the adjusted display parameters, the method further includes: acquiring the subsequent video images displayed in the video call; identifying the face area in the subsequent video image, and analyzing the image quality of the face area to determine whether it meets the preset optimization requirements; if it is determined that the image quality of the face area does not meet the optimization requirements, continuously adjusting the display parameters of the screen until a subsequent video image in the video call is displayed based on the adjusted display parameters, and if the image quality of the face area meets the optimization requirements, the subsequent video images in the video call are displayed while maintaining the display parameters unchanged.

[0022] In some embodiments, after obtaining the current video image displayed in the video call, the method further includes: identifying the color and brightness of each area block in the current video image, and analyzing the color and brightness of each area block to determine whether the preset image quality requirements are met; when it is determined that there is at least one area block whose color and / or brightness do not meet the image quality requirements, setting a color block and / or brightness block for top display on the picture layer corresponding to each area block in the at least one area block; optimizing the display of the subsequent video image in the video call based on the added color block and / or brightness block for top display. By performing color and brightness analysis on the overall video image according to different area blocks, and performing regional display adjustment in the form of additional top display of color blocks and / or brightness blocks, accurate optimization of the picture can be achieved.

[0023] In some embodiments, after obtaining the current video image displayed in the video call, the method further includes: identifying whether the intercom screen in the current video image is located in a designated area of ​​the screen; if it is determined that the intercom screen is not located in the designated area of ​​the screen, moving the intercom screen into the designated area in the subsequent video image displayed. By adjusting the position of the intercom screen in the video image, the comfort and visibility of the video image are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] One or more embodiments are exemplarily described by the pictures in the corresponding drawings, and these exemplary descriptions do not constitute limitations on the embodiments.

[0025] Figure 1 is a flowchart illustrating a method for processing a picture in a video call according to an embodiment of the present application;

[0026] Figure 2 is a flowchart illustrating another method for processing a picture in a video call according to an embodiment of the present application;

[0027] Figure 3 is a flowchart illustrating another method for processing a picture in a video call according to an embodiment of the present application;

[0028] Figure 4 is a flowchart illustrating another method for processing a picture in a video call according to an embodiment of the present application;

[0029] Figure 5 is a flowchart illustrating another method for processing a picture in a video call according to an embodiment of the present application;

[0030] Figure 6 is a schematic diagram illustrating the effect of a video image to be optimized and optimized display parameters according to an embodiment of the present application;

[0031] Figure 7 is a schematic diagram illustrating the structure of a device for processing a picture in a video call according to an embodiment of the present application;

[0032] Figure 8 It is a hardware block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to make the purpose, technical scheme and advantages of the embodiments of the present invention clearer, the following will be described in detail with reference to the accompanying drawings. However, it will be appreciated by those skilled in the art that in the various embodiments of the present invention, many technical details are provided in order to enable the reader to better understand the present application. However, even without these technical details and various changes and modifications based on the following embodiments, the technical scheme claimed in the present application can be implemented.

[0034] One embodiment of the present invention relates to a method for processing a screen in a video call. The execution subject of the method can be an electronic product itself with a video call function and a video intercom function, such as but not limited to a mobile terminal, a central control screen, etc. When the electronic product itself is used as the execution subject of the present solution, it can not only display the video images of both users of the call in real time during the call, but also has the ability to process the video images, and can complete the whole process of the method for processing the screen in the video call in the embodiment of the present application by itself. Of course, this requires a relatively high performance of the electronic product itself. Alternatively, the execution subject of the present method can be a server connected to the above-mentioned electronic product with a video call function and a video intercom function through a network or the like. The server has the ability to process the video image, and the electronic product only needs to upload the video image collected by itself to the server for processing, and receive the control instructions or configuration parameters fed back by the processor to respond and execute. In this embodiment, the connection method between the latter execution subject and the above-mentioned electronic product is not limited. In this application, the server is used as the execution subject and the central control screen is used as an electronic product that can make video calls, and the exemplary description of the method for processing the screen in the video call provided in the embodiment of the present application is provided.

[0035] like Figure 1 As shown, the method for processing images in a video call provided in this embodiment includes the following steps.

[0036] Step 101: Acquire the current video image displayed in the video call.

[0037] During a video call on the central control screen, both central control screens can use their own image acquisition devices, such as cameras, to capture video content of the caller and his / her surroundings and transmit it to the other party's video call device for display, which is usually called the "main video screen". At the same time, the captured video content will also be embedded or displayed on the main video screen in the form of a small window on the video call interface of the party, also known as the "intercom screen". That is, the main video screen and the intercom screen are displayed simultaneously in the interface of each party's central control screen, and the video content of the two can be flexibly switched between by the user.

[0038] Specifically, during a video call on the central control screen, the central control screen can capture the current video image displayed in its own video call, and then upload the video image to the server for the server to perform image processing.

[0039] In some embodiments, this step may specifically include: in the initial stage of the video call, and when it has been confirmed that the current device executing the video call has turned on the automatic fill light function, obtaining the current video image in the initial stage of the video call.

[0040] Specifically, in order to ensure that the video image played by the central control screen can maintain good image quality in the face area from beginning to end during the video call, it can be preferred to start obtaining the current video image and uploading it to the server at the initial stage of the video call, and the server will perform relevant image processing. In addition, in order to reflect the operational flexibility of the overall solution, the central control screen, that is, the current device that performs the video call, can have an automatic fill light function built in. Only if the user has enabled this function in advance, the central control screen will obtain the current video image and upload it to the server at the initial stage of each video call.

[0041] Step 102: Identify the face area in the current video image, and analyze the image quality of the face area to determine whether it meets the preset image quality requirements.

[0042] During a video call, the most direct requirement of users for the quality of the video image is to clearly see the other party's face, so as to observe the other party's expression at any time and facilitate emotional communication. Therefore, after receiving the video image uploaded by the central control screen, the server can perform facial feature recognition on the video image, determine the face area, and further analyze the image quality in the face area. In addition, before the server performs facial feature recognition on the video image, it can also first detect whether the overall light brightness of the video image meets the preset brightness requirements. If it is detected that the light is too bright or too dark, the facial feature recognition step is started, so that this step is implemented only when image quality optimization is actually needed to avoid unnecessary operations.

[0043] Indicators used to evaluate and analyze image quality in this embodiment may include, but are not limited to, image clarity, noise, dynamic range, color accuracy, brightness uniformity, color uniformity, lateral chromatic aberration, glare, etc. In order to more accurately quantify the image quality in the face area, the index type to be analyzed may be pre-set, and then a suitable index value may be set for each index type as a boundary value for measuring good image quality. These index values ​​are integrated together to form the image quality requirements for judging whether the image quality is good or not.

[0044] The server may analyze the image quality in the face area by using the indicator value of at least one indicator type mentioned above, so as to determine whether the image quality in the face area meets the preset image quality requirement.

[0045] In some embodiments, the type of indicator that users are most concerned about can be selected as the quality requirement for evaluating the good quality of the face area. For example, users are usually more concerned about the clarity of the face of the target object in the video. Therefore, in this step, the process of analyzing the image quality of the face area and determining whether it meets the preset image quality requirements can include the following steps (step a to step b).

[0046] Step a: Analyze the face definition of the face area to determine whether the proportion of the area where the face definition does not reach the preset standard definition in the face area is greater than a preset value.

[0047] For example, the face area can be divided into blocks, and then the definition of each block can be calculated using a preset algorithm to determine whether it reaches the preset standard definition. If it reaches the standard definition, it means that the image quality of the block meets the image quality requirements. Otherwise, if it does not reach the standard definition, it means that the image quality of the block does not meet the image quality requirements. Then, it is counted whether the area of ​​all blocks that do not reach the standard definition accounts for a larger proportion of the area of ​​the face area than the preset value.

[0048] Step b: When the proportion is greater than the preset value, it is determined that the image quality of the face area does not meet the preset image quality requirements.

[0049] For example, after step a, when the overall area of ​​the blocks that do not meet the image quality requirements accounts for a proportion of the total area of ​​the face area that exceeds the preset value, it is considered that the face in the face area is unclear, and the face area as a whole does not meet the image quality requirements and needs to be optimized and adjusted.

[0050] The preset value for determining whether the face in the face area is unclear, that is, the upper limit of the proportion of the overall area of ​​the blocks that do not meet the image quality requirements to the total area of ​​the face area, can be set based on user experience, for example, but not limited to 5%.

[0051] Step 103: When it is determined that the image quality of the face area does not meet the image quality requirements, adjust the display parameters of the screen.

[0052] Specifically, when the server determines that the image quality of the face area does not meet the indicator value of a certain indicator type that has been set above, it is necessary to adjust the display parameters of the central control screen through "post-production" so that the face area meets the indicator value of the corresponding indicator type, thereby improving the image quality. The specific adjustment of the display parameters of the screen may include the adjusted area and the adjusted parameter type and parameter value, where the parameter type may include but is not limited to brightness, color, contrast, etc.

[0053] For example, in some embodiments, when the above-mentioned face clarity is used as the specific indicator type for measuring the image quality requirements of the face area, when it is determined that the image quality of the face area does not meet the image quality requirements, adjusting the display parameters of the screen may specifically include: when it is determined that the clarity of the face area does not meet the standard clarity, calculating the difference between the clarity of the face area and the standard clarity, and adjusting the display parameters of the screen based on the difference.

[0054] For example, according to the aforementioned method of determining the clarity of the face area by blocks, the difference between the clarity of the face area and the standard clarity can be calculated for each block one by one, and then the display parameters can be adjusted based on the size of the difference. After determining the difference in clarity corresponding to each block, the display parameters can be adjusted in a partial block or all blocks as a whole to improve the adjustment efficiency. In this embodiment, a target for the image quality optimization result of the face area after adjusting the display parameters can be set, and the value of the display parameter to be adjusted can be calculated based on the target. For example, the desired optimization target can be, but is not limited to, when the video image is displayed by the adjusted display parameters, 95% of the face area can meet the preset image quality requirements.

[0055] Step 104: Optimize display of subsequent video images in the video call based on the adjusted display parameters.

[0056] Specifically, after the server calculates the display parameters of the central control screen for adjusting the image quality of the face area based on the preset image quality optimization adjustment target, the server sends the adjusted display parameters to the central control screen to control the central control screen to optimize the display of subsequent video images in the video call based on the received display parameters, thereby improving and optimizing the image quality in the face area.

[0057] In the present embodiment, during an intercom call via video call on the central control screen, the current video image displayed in the video call is obtained; the face area in the current video image is identified, and the image quality of the face area is analyzed to determine whether it meets the preset image quality requirements; if the image quality of the face area does not meet the preset image quality requirements, the display parameters of the screen are adjusted, and subsequent video images in the video call are displayed in an optimized manner based on the adjusted display parameters, so as to achieve image quality optimization of the face area, improve the video image display effect and thus improve the user experience.

[0058] Another embodiment of the present invention relates to another method for processing a video call image. Figure 1 A supplement to the method shown.

[0059] exist Figure 1 Based on the method shown in FIG. 1 , specifically after step 104, as Figure 2 As shown, the following method steps can also be performed.

[0060] Step 105: Acquire subsequent video images displayed in the video call.

[0061] This step may refer to the content of step 101, except that the video image acquired in this step is a subsequent video image located after the current video image and optimized for display by the central control screen during the video call based on the adjusted display parameters after step 104.

[0062] Step 106, identifying the face area in the subsequent video image, and analyzing the image quality of the face area to determine whether it meets the preset optimization requirements.

[0063] Specifically, the image quality analysis of the face area in this step is the same as the index used in the above step 102 to analyze the image quality, including but not limited to the image clarity, noise, dynamic range, color accuracy, brightness uniformity, color uniformity, lateral chromatic aberration, glare, etc., but the analysis objectives are different. Step 102 is to analyze whether the index values ​​of the above indexes meet the image quality requirements. If not, it is necessary to adjust the display parameters through steps 103 to 104 to optimize the display of the video image, while step 106 is to analyze whether the video image optimized after the display parameter adjustment has met the optimization goal, that is, the optimization requirement, and the optimization requirement is mainly the expectation of the degree of optimization. For example, after the display parameters are adjusted to optimize the display of the face area in the subsequent video image, it can be judged whether the optimization requirement has been met by comparing the index values ​​of various image quality evaluations after the analysis of the subsequent video image with the index values ​​before the optimized display, or the area of ​​the image that has been optimized to meet the requirements accounts for the area ratio of the original image to be optimized. For example, when the area that has been optimized and meets the image quality requirements accounts for more than 95% of the area of ​​the image to be optimized, it is considered that the optimization requirements are met. The specific content of the optimization requirements is not limited in this embodiment, and those skilled in the art can customize them according to actual needs.

[0064] Step 107, when it is determined that the image quality of the face area does not meet the optimization requirements, continuously adjust the display parameters of the screen until the subsequent video images in the video call are displayed based on the adjusted display parameters in an optimized manner. When the image quality of the face area meets the optimization requirements, the subsequent video images in the video call are displayed while maintaining the display parameters unchanged.

[0065] Specifically, each time the display parameters are adjusted, the subsequent video images must be optimized based on the adjusted display parameters, and the optimization results can only be detected by analyzing the image quality of the subsequent video images, and the "adjustment + detection" verification process may require multiple rounds of operations. Therefore, when the server determines that the image quality of the face area does not meet the optimization requirements, it is likely that it will be necessary to continuously adjust the screen display parameters, and then optimize the display of subsequent video images in the video call based on the display parameters after each round of adjustment, until the image quality of the face area meets the optimization requirements, the display parameter adjustment process will be terminated, and the subsequent video images in the video call will be displayed while maintaining the current display parameters unchanged.

[0066] like Figure 3As shown, the example row provides an example method of processing the picture in a video call in multiple rounds of adjusting display parameters, including the following steps (step 1 to step 4).

[0067] Step 1: Turn on the automatic fill light function on the central control screen and upload the video image in the video call to the server.

[0068] When the user turns on the automatic fill light function of the central control screen, when the central control screen is triggered to make a new round of video call (intercom call), the central control screen will first upload the first 3 seconds (the duration can be set by the user) of the video image in the video call to the server.

[0069] Step 2: The server identifies and analyzes the facial area in the video image, determines the display parameters that need to be adjusted, and sends them to the central control screen.

[0070] The server analyzes the uploaded video image, and in the case of poor light (too bright or too dark), counts the portrait features of the face area (such as the image quality of the portrait features, more specifically, various indicators of image quality, such as clarity, etc.), and then calculates the best adjusted display parameters based on the analysis results, and sends the display parameters to the central control screen. Here, the portrait features include human appearance features and movement habit features, etc. The portrait features of the face area mentioned in this embodiment include, for example, facial features, facial contour features, etc.

[0071] Step 3: The central control screen displays subsequent video images according to the received display parameters, and uploads the subsequent video images to the server.

[0072] The central control screen displays subsequent video images according to the received display parameters to achieve a fill light effect, and uploads the latest video image 3 seconds after the fill light to the server.

[0073] Step 4: The server determines whether the face area in the subsequent video image is optimized and whether the optimization reaches 95%; if so, the operation ends, otherwise returns to step 2.

[0074] After receiving the candidate video image after fill-in, the server will continue to determine whether the face area in the subsequent video image is optimized and whether the area of ​​the optimized area accounts for 95% of the area to be optimized. If yes, the optimization process ends, otherwise it returns to step 2 and continues to optimize the subsequent video images according to the received video image.

[0075] The method for processing the video call picture provided in this embodiment is to Figure 1The solution of the method embodiment shown is supplemented by analyzing the subsequent video images displayed based on the adjusted display parameters at least once to verify the adjustment solution of the display parameters and the optimization results of the video image, and evaluate whether the optimization process meets the optimization requirements, so as to ensure that the image quality of the face area in the finally optimized displayed video image meets the expected image quality requirements, thereby improving the satisfaction of both parties in the video call with the video image.

[0076] Another embodiment of the present invention relates to another method for processing a video call image. Figure 1 A complement to the methods shown.

[0077] exist Figure 1 Based on the method shown in FIG. 1 , specifically after step 101, as Figure 4 As shown, the following method steps can also be performed.

[0078] Step 108: Identify the color and brightness of each area block in the current video image, and analyze the color and brightness of each area block to determine whether it meets the preset image quality requirements.

[0079] Specifically, the image quality requirements in this embodiment add requirements on color and brightness in the video image, that is, the color and brightness need to be within a reasonable range. In order to accurately adjust the color and brightness of the video image, the server in this embodiment divides the acquired current video image into multiple area blocks, and identifies the color and brightness of each area block separately to determine whether the preset image quality requirements on color and brightness are met.

[0080] Step 109, when it is determined that there is at least one area block whose color and / or brightness do not meet the image quality requirements, a color block and / or brightness block is added to the top display on the picture layer corresponding to each area block in the at least one area block.

[0081] For example, when it is determined that the color of a certain area block of the video image does not meet the image quality requirements, a color block is set to be added to the top display on the picture layer corresponding to the area block to adjust the color of the area block, and / or when it is determined that the brightness of a certain area block does not meet the image quality requirements, a brightness block is set to be added to the top display on the picture layer corresponding to the area block to adjust the brightness of the area block. The specific operation is that the server sends an instruction to add a color block or a brightness block to the central control screen, and the instruction includes: the area block that needs to be set and the corresponding color and brightness parameters. The central control screen configures the picture layer of the corresponding area block based on the received instruction.

[0082] Step 110: Optimize the display of subsequent video images in the video call based on the added color block and / or brightness block displayed on top.

[0083] Specifically, the server can send an instruction to add a color block and / or a brightness block to the central control screen, and at the same time instruct the central control screen to optimize the display of subsequent video images in the video call based on the added color block and / or brightness block displayed on top. Based on the parameter configuration and display instructions received from the server, the central control screen synchronously displays the corresponding color block and / or brightness block on top in the designated area block when displaying subsequent video images in the video call, thereby improving and optimizing the color and brightness of the overall video image and improving the image quality.

[0084] In this embodiment, during an intercom call via video call on the central control screen, the color and brightness of the area blocks in the video image that do not meet the image quality requirements are synchronously configured in units of area blocks, and the subsequent video images in the video call are optimized based on the top displayed color blocks and / or brightness blocks, thereby improving the video image display effect and thus improving the user experience.

[0085] Another embodiment of the present invention relates to another method for processing a video call image. Figure 1 A supplement to the method shown.

[0086] exist Figure 1 Based on the method shown in FIG. 1 , specifically after step 101, as Figure 5 As shown, the following method steps can also be performed.

[0087] Step 111, identifying whether the intercom picture in the current video image is located in a designated area of ​​the screen.

[0088] Specifically, when the intercom screen in the video image blocks the key image content of the main video screen, such as when the face area is blocked, it is easy to interfere with the corresponding caller's viewing of the video image. In this case, it is best to control the intercom screen to be displayed in a specified area of ​​the screen, which usually does not affect the face area, such as the upper right corner of the video image. Therefore, after acquiring the video image, the server can identify whether the intercom screen in the current video image is located in the specified area of ​​the screen, so as to adjust the position of the intercom screen at any time based on the identification result.

[0089] Step 112, when it is determined that the intercom picture is not located in the designated area of ​​the screen, the intercom picture is moved into the designated area in the subsequent video image displayed.

[0090] Specifically, when it is determined that the intercom screen is not located in the designated area of ​​the screen, the intercom screen is likely to block key image content in the video image, such as the face area. At this time, the server will send an instruction to the central control screen, instructing the central control screen to move the intercom screen to the designated area in the subsequent video image displayed to avoid blocking key image content in the subsequent video image.

[0091] In this embodiment, during an intercom call in the form of a video call on the central control screen, the position of the intercom screen in the video image is identified and determined, and if it is determined that the intercom screen is not located in a designated area of ​​the screen, the intercom screen is moved to the designated area in the subsequent video image displayed, thereby reducing the probability of key image content in the video image being blocked, improving the video image display effect and thus improving the user experience.

[0092] Based on the above method embodiments, Figure 6 The figure shows the video image to be optimized on the central control screen, and a schematic diagram of the effect of optimizing the corresponding display parameters on the image.

[0093] Among them, (a) and (b) are the first group of schematic diagrams. In Figure (a), the intercom screen at the beginning of the video image is in the middle; the light on the left side of the face in the face area showing the other party of the call is dark and the clarity is poor. After the server obtains the video image, it needs to add some light sources to the left side of the face to increase the brightness in order to improve the clarity of the face recognition features; at the same time, it is also necessary to move the intercom screen to the designated area to avoid interference with the face image. Therefore, the server will calculate the display parameters that need to be optimized for display on the central control screen, and send the calculated display parameters to the central control screen for optimized display. As shown in Figure (b), the display parameters of the central control screen calculated by the server may include which positions need to display what color and shape of graphics, and how many parameters to adjust the screen brightness, and adjust the display position of the intercom screen to a specified position (such as the upper right corner) to achieve the effect of improving the clarity of the face recognition features and avoiding the intercom screen blocking the face area.

[0094] Among them, (c) and (d) are schematic diagrams of the second group. In Figure (c), the video image shows that the light on the lower left and upper right sides of the face area of ​​the other party in the call is dark and the clarity is poor. After the server obtains the video image, it needs to add some light sources to the lower left and upper right sides of the face to increase the brightness, so as to improve the clarity of the facial recognition features. Therefore, the server will calculate the display parameters that need to be optimized for display on the central control screen, and send the calculated display parameters to the central control screen for optimized display. As shown in Figure (d), the display parameters of the central control screen calculated by the server may include which positions need to display what color and shape of graphics, and adjust the screen brightness to a certain parameter to achieve the effect of improving the clarity of facial recognition features.

[0095] Another embodiment of the present invention relates to a device for processing images in a video call, such as Figure 7 As shown, including:

[0096] The acquisition module 201 is used to acquire the current video image displayed in the video call;

[0097] The recognition module 202 is used to recognize the face area in the current video image and analyze the image quality of the face area to determine whether it meets the preset image quality requirements;

[0098] An adjustment module 203, configured to adjust display parameters of the screen when it is determined that the image quality of the face area does not meet the image quality requirement;

[0099] The display module 204 is configured to optimize the display of subsequent video images in the video call based on the adjusted display parameters.

[0100] In some embodiments, the acquisition module 201 is specifically used to acquire the current video image at the initial stage of the video call when it is confirmed that the automatic fill light function has been turned on in the current device executing the video call.

[0101] In some embodiments, the recognition module 202 is specifically used to analyze the facial clarity of the facial area to determine whether the proportion of the area where the facial clarity does not reach the preset standard clarity in the facial area is greater than a preset value; when the proportion is greater than the preset value, it is determined that the image quality of the facial area does not meet the preset image quality requirements.

[0102] In some embodiments, the adjustment module 203 is specifically used to calculate the difference between the clarity of the face area and the standard clarity when it is determined that the clarity of the face area does not meet the standard clarity, and adjust the display parameters of the screen based on the difference.

[0103] In some embodiments, the acquisition module 201 is also used to acquire the subsequent video images displayed in the video call; the recognition module 202 is also used to identify the face area in the subsequent video image, and analyze the image quality of the face area to determine whether it meets the preset optimization requirements; the adjustment module 203 is also used to continuously adjust the display parameters of the screen when it is determined that the image quality of the face area does not meet the optimization requirements, until the display module 204 optimizes and displays the subsequent video images in the video call based on the adjusted display parameters, and when the image quality of the face area meets the optimization requirements, the display module 204 maintains the display parameters unchanged to display the subsequent video images in the video call.

[0104] In some embodiments, the identification module 202 is also used to identify the color and brightness of each area block in the current video image, and analyze the color and brightness of each area block to determine whether the preset image quality requirements are met; the adjustment module 203 is also used to set a color block and / or brightness block for top display on the picture layer corresponding to each area block in the at least one area block when it is determined that there is at least one area block whose color and / or brightness does not meet the image quality requirements; the display module 204 is also used to optimize the display of the subsequent video images in the video call based on the added color block and / or brightness block for top display.

[0105] In some embodiments, the identification module 202 is also used to identify whether the intercom screen in the current video image is located in a specified area of ​​the screen; the adjustment module 203 is also used to trigger the display module 204 to move the intercom screen into the specified area in the displayed subsequent video image when it is determined that the intercom screen is not located in the specified area of ​​the screen.

[0106] Another embodiment of the present invention relates to an electronic device, such as Figure 8 As shown, it includes at least one processor 302; and a memory 301 that is communicatively connected to the at least one processor 302; wherein the memory 301 stores instructions that can be executed by the at least one processor 302, and the instructions are executed by the at least one processor 302 so that the at least one processor 302 can execute any of the above method embodiments.

[0107] The memory 301 and the processor 302 are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 302 and the memory 301 together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor 302 is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor 302.

[0108] The processor 302 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 301 can be used to store data used by the processor 302 when performing operations.

[0109] Another embodiment of the present invention relates to a computer-readable storage medium storing a computer program, which implements any of the above method embodiments when executed by a processor.

[0110] Another embodiment of the present invention relates to a computer program product. When the computer program product is run on a terminal device, the electronic device executes any one of the method embodiments described above.

[0111] That is, those skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0112] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0113] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0114] Those skilled in the art will appreciate that the above-mentioned embodiments are specific examples for implementing the present invention, and in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A method for processing images in a video call, characterized in that: include: Get the current video image displayed in the video call; Identify a face region in the current video image, and analyze the image quality of the face region to determine whether it meets a preset image quality requirement; If it is determined that the image quality of the face area does not meet the image quality requirement, adjusting the display parameters of the screen; The subsequent video images in the video call are displayed in an optimized manner based on the adjusted display parameters.

2. The method for processing images during a video call according to claim 1, characterized in that: The obtaining of the current video image displayed in the video call includes: In the initial stage of the video call, and if it has been confirmed that the current device executing the video call has turned on the automatic fill light function, the current video image in the initial stage of the video call is obtained.

3. The method for processing images during a video call according to claim 1, characterized in that: Analyze the image quality of the face area to determine whether it meets the preset image quality requirements, including: Analyze the face definition of the face area to determine whether the proportion of the area where the face definition does not reach the preset standard definition in the face area is greater than a preset value; When the proportion is greater than the preset value, it is determined that the image quality of the face area does not meet the preset image quality requirement.

4. The method for processing images during a video call according to claim 3, characterized in that: When it is determined that the image quality of the face area does not meet the image quality requirement, adjusting the display parameters of the screen includes: When it is determined that the definition of the face region does not meet the standard definition, a difference between the definition of the face region and the standard definition is calculated, and a display parameter of the screen is adjusted based on the difference.

5. The method for processing images during a video call according to claim 1, characterized in that: After optimizing the display of subsequent video images in the video call based on the adjusted display parameters, the method further includes: Acquire the subsequent video image displayed in the video call; Identifying a face region in the subsequent video image, and analyzing the image quality of the face region to determine whether it meets a preset optimization requirement; When it is determined that the image quality of the face area does not meet the optimization requirements, the display parameters of the screen are continuously adjusted until subsequent video images in the video call are displayed in an optimized manner based on the adjusted display parameters. When the image quality of the face area meets the optimization requirements, the display parameters are maintained unchanged to display subsequent video images in the video call.

6. The method for processing images during a video call according to any one of claims 1 to 5, characterized in that: After obtaining the current video image displayed in the video call, the method further includes: Identify the color and brightness of each area block in the current video image, and analyze the color and brightness of each area block to determine whether the preset image quality requirements are met; When it is determined that there is at least one area block whose color and / or brightness do not meet the image quality requirement, a color block and / or brightness block is added to be displayed on top on the picture layer corresponding to each area block in the at least one area block; The subsequent video image in the video call is displayed in an optimized manner based on an increased color block and / or brightness block displayed on top.

7. The method for processing images during a video call according to any one of claims 1 to 5, characterized in that: After obtaining the current video image displayed in the video call, the method further includes: Identify whether the intercom picture in the current video image is located in a designated area of ​​the screen; When it is determined that the intercom picture is not located in the designated area of ​​the screen, the intercom picture is moved into the designated area in the displayed subsequent video image.

8. A device for processing images in a video call, characterized in that: include: An acquisition module, used to acquire the current video image displayed in the video call; A recognition module, used to recognize a face region in the current video image, and analyze the image quality of the face region to determine whether it meets a preset image quality requirement; An adjustment module, configured to adjust display parameters of the screen when it is determined that the image quality of the face area does not meet the image quality requirement; The display module is used to optimize the display of subsequent video images in the video call based on the adjusted display parameters.

9. An electronic device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for processing images in a video call as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for processing images in a video call described in any one of claims 1 to 7 is implemented.

Images