A screen brightness compensation coefficient determination method, a compensation method and a product

Abstract

A screen brightness compensation coefficient determination method, a compensation method and a product, relate to the technical field of display screens, and the screen brightness compensation coefficient determination method comprises: acquiring a target image photographed for a target screen (S101); dividing the target image into a plurality of image regions corresponding to different screen regions of the target screen (S102); calculating the brightness average of each image region in the target image (S103); inputting the brightness average of each image region in the target image into a pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient of each screen region of the target screen, and the brightness compensation coefficient prediction network is obtained by training a neural network with a sample image photographed for a sample screen as a training sample and with standard brightness compensation coefficients of each screen region corresponding to the sample image as labels (S104).

Description

A method for determining screen brightness compensation coefficient, a compensation method, and a product. Technical Field

[0001] This application relates to the field of display screen technology, and in particular to a method for determining screen brightness compensation coefficient, a compensation method, and a product. Background Technology

[0002] Due to high refresh rates or reversed charging polarity, liquid crystal molecules in LCD screens are prone to differences in charging rates, leading to variations in brightness at the same gray level, i.e., uneven screen brightness and issues such as fine lines. Currently, addressing this uneven screen brightness requires repeated manual adjustments to each area of ​​every screen, a complex, time-consuming, and costly process. Summary of the Invention

[0003] In view of the above problems, this application provides a method for determining the screen brightness compensation coefficient, a compensation method, and a product to improve the compensation efficiency of screen brightness compensation.

[0004] A first aspect of this application provides a method for determining a screen brightness compensation coefficient, including:

[0005] Acquire a target image captured from the target screen;

[0006] The target image is divided into multiple image regions corresponding to different screen regions of the target screen;

[0007] Calculate the average brightness of each image region in the target image;

[0008] The average brightness of each image region in the target image is input into a pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient for each screen region of the target screen. The brightness compensation coefficient prediction network is trained by using sample images taken for the sample screen as training samples and the standard brightness compensation coefficients of each screen region corresponding to the sample images as labels.

[0009] In one possible implementation, the brightness compensation coefficient prediction network is trained through the following steps:

[0010] Obtain the sample image captured for the sample screen, and the standard brightness compensation coefficient for each screen area corresponding to the sample image;

[0011] The sample image is divided into multiple sample image regions corresponding to different screen regions of the sample screen;

[0012] Calculate the mean sample brightness of each sample image region in the sample image;

[0013] The average brightness of the samples is input into the neural network to be trained to obtain the sample brightness compensation coefficient for each screen area of ​​the sample screen.

[0014] The loss function value is calculated based on the sample brightness compensation coefficient and the standard brightness compensation coefficient;

[0015] Repeat the above steps until the preset number of training iterations or the loss function value converges, then end the training and obtain the brightness compensation coefficient prediction network.

[0016] In one possible implementation, the method further includes:

[0017] The predicted brightness compensation coefficient is written into the memory of the target screen so that the target screen can use the predicted brightness compensation coefficient to perform brightness compensation for the target screen.

[0018] In one possible implementation, the method further includes:

[0019] Acquire a standard image corresponding to the target screen, wherein the standard image corresponding to the target screen is: an image taken of the target screen after brightness compensation;

[0020] The effectiveness of the predicted brightness compensation coefficient is verified using a standard image corresponding to the target screen.

[0021] If the predicted brightness compensation coefficient passes verification, the predicted brightness compensation coefficient is written into the memory of the target screen.

[0022] In one possible implementation, the effectiveness of the predicted brightness compensation coefficient is verified using a standard image corresponding to the target screen, including:

[0023] The predicted brightness compensation coefficient for each screen area of ​​the target screen is sent to the screen processor of the target screen;

[0024] In response to the screen processor performing brightness compensation using the predicted brightness compensation coefficient, a brightness-compensated image of the target screen is acquired.

[0025] The brightness of the brightness-compensated image is compared with the brightness of the standard image corresponding to the target screen.

[0026] If the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is less than the target threshold, the predicted brightness compensation coefficient is determined to have passed the verification.

[0027] If the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is not less than the target threshold, the predicted brightness compensation coefficient is determined to fail verification.

[0028] In one possible implementation, the method further includes:

[0029] If the predicted brightness compensation coefficient fails the verification, a new target image is captured for the target screen, and a new predicted brightness compensation coefficient for each screen area of ​​the target screen is obtained through the compensation coefficient prediction network to re-verify the effectiveness of the new predicted brightness compensation coefficient.

[0030] In one possible implementation, the method further includes:

[0031] If at least one verification fails, record the predicted brightness compensation coefficient used for each brightness compensation, and / or output a manual brightness compensation prompt for the target screen.

[0032] A second aspect of this application also provides a screen brightness compensation method, the method comprising:

[0033] Based on the screen area corresponding to each pixel in the target image captured for the target screen, the pre-stored brightness compensation information is queried to determine the predicted brightness compensation coefficient corresponding to each pixel in the target image. The brightness compensation information includes the predicted brightness compensation coefficient for each screen area of ​​the target screen. The predicted brightness compensation information is determined by the screen brightness compensation coefficient determination method described in the first aspect of the embodiments of this application.

[0034] The target screen is brightness compensated according to the predicted brightness compensation coefficient corresponding to each pixel in the target image.

[0035] In one possible implementation, the method further includes:

[0036] Obtain the precharge value corresponding to each pixel in the target image;

[0037] Based on the pre-charge value corresponding to each pixel in the target image, determine the compensation value corresponding to each pixel in the target image;

[0038] Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image, including:

[0039] Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient and compensation value corresponding to each pixel in the target image.

[0040] A third aspect of this application also provides a screen brightness compensation system, the system comprising at least: a host computer, a camera, and a screen;

[0041] The host computer includes a first processor, which is used to execute the screen brightness compensation coefficient determination method described in the first aspect of the embodiments of this application;

[0042] The screen includes: a screen memory and a screen processor, wherein the screen processor is used for the screen brightness compensation method described in the second aspect of the embodiments of this application.

[0043] The camera is used to capture images of the screen.

[0044] A fourth aspect of this application also provides a screen brightness compensation coefficient determination device, used to perform the screen brightness compensation coefficient determination method described in the first aspect of this application, the device comprising:

[0045] The image acquisition module is used to acquire a target image captured from the target screen.

[0046] An image region segmentation module is used to divide the target image into multiple image regions corresponding to different screen regions of the target screen;

[0047] The average brightness calculation module is used to calculate the average brightness of each image region in the target image;

[0048] The brightness compensation coefficient determination module is used to input the average brightness of each image region in the target image into a pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient for each screen region of the target screen. The brightness compensation coefficient prediction network is trained by using sample images taken for the sample screen as training samples and the standard brightness compensation coefficients of each screen region corresponding to the sample images as labels.

[0049] A fifth aspect of this application also provides a screen brightness compensation device, applied to the screen brightness compensation method described in the second aspect of this application, the device comprising:

[0050] The information query module is used to query pre-stored brightness compensation information based on the screen area corresponding to each pixel in the target image captured for the target screen, and determine the predicted brightness compensation coefficient corresponding to each pixel in the target image. The brightness compensation information includes the predicted brightness compensation coefficient of each screen area of ​​the target screen. The predicted brightness compensation information is determined by the screen brightness compensation coefficient determination method described in the first aspect of the embodiments of this application.

[0051] The brightness compensation module is used to perform brightness compensation on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image.

[0052] A sixth aspect of this application provides an electronic device, including a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the screen brightness compensation coefficient determination method described in the first aspect of this application, or the steps of the screen brightness compensation method described in the second aspect of this application.

[0053] A seventh aspect of this application provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program implements the steps of the screen brightness compensation coefficient determination method described in the first aspect of this application, or the steps of the screen brightness compensation method described in the second aspect of this application.

[0054] An eighth aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the screen brightness compensation coefficient determination method as described in the first aspect of this application, or the steps of the screen brightness compensation method as described in the second aspect of this application.

[0055] This application provides a method for determining screen brightness compensation coefficients. The method includes: acquiring a target image captured for a target screen; dividing the target image into multiple image regions corresponding to different screen areas of the target screen; calculating the average brightness of each image region in the target image; inputting the average brightness of each image region in the target image into a pre-trained brightness compensation coefficient prediction network to obtain a predicted brightness compensation coefficient for each screen area of ​​the target screen. The brightness compensation coefficient prediction network is trained by using sample images captured for a sample screen as training samples and the standard brightness compensation coefficients of each screen area corresponding to the sample images as labels.

[0056] The specific beneficial effects are as follows: This application utilizes sample images (the average brightness of each image region of the sample image) captured on a sample screen as training samples, and uses empirically tuned screen parameters (i.e., the standard brightness compensation coefficients for each screen region corresponding to the sample image) as training sample labels to train a neural network (i.e., a brightness compensation coefficient prediction network). This enables the neural network to predict the corresponding brightness compensation coefficient based on the average brightness of each image region of the screen image. In the actual process of brightness compensation for the target screen, the average brightness of each image region in the target image captured on the target screen is input into the pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient. This allows the target screen to perform brightness compensation based on the predicted brightness compensation coefficient, solving the problem of uneven screen brightness and improving the efficiency of screen brightness compensation. Attached Figure Description

[0057] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 is a flowchart of a method for determining screen brightness compensation coefficient provided in an embodiment of this application;

[0059] Figure 2 is a schematic diagram of a brightness compensation system provided in an embodiment of this application;

[0060] Figure 3 is a schematic diagram of a brightness compensation process provided in an embodiment of this application;

[0061] Figure 4 is a schematic diagram of the structure of a brightness compensation coefficient prediction network provided in an embodiment of this application;

[0062] Figure 5 is a schematic diagram of the training process of a brightness compensation coefficient prediction network provided in an embodiment of this application;

[0063] Figure 6 is a schematic flowchart of a screen brightness compensation verification provided in an embodiment of this application;

[0064] Figure 7 is a flowchart of a screen brightness compensation method provided in an embodiment of this application;

[0065] Figure 8 is a logical schematic diagram of brightness compensation for a target screen provided in an embodiment of this application;

[0066] Figure 9 is a schematic diagram of another screen brightness compensation system provided in an embodiment of this application;

[0067] Figure 10 is a schematic diagram of a screen brightness compensation coefficient determination device provided in an embodiment of this application;

[0068] Figure 11 is a schematic diagram of a screen brightness compensation device provided in an embodiment of this application;

[0069] Figure 12 is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Specific Implementation

[0070] Exemplary embodiments of this application will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of this application are shown in the drawings, it should be understood that this application may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided to enable a more thorough understanding of this application and to fully convey the scope of this application to those skilled in the art.

[0071] Due to high refresh rates or charging polarity reversals, liquid crystal molecules in LCD screens are prone to differences in charging rates. This leads to regular differences in brightness at the same gray level among the liquid crystal molecules, resulting in fine lines on the screen. Specifically, LCD screens using a dual-gate structure employ a line-by-line scanning method, scanning half a row of pixels at a time or outputting two rows at a time to achieve a high refresh rate. However, the screen's luminous efficiency is affected by charging time. In this architecture, the charging time of screen pixels is influenced by the data signal from the previous scan. If the signal changes abruptly, the charging time is insufficient, resulting in inadequate pixel brightness and causing horizontal and vertical lines on the screen, severely impacting image quality.

[0072] Currently, addressing the aforementioned issue of uneven screen brightness requires manual adjustments to the brightness compensation values ​​for each area of ​​every screen. This presents three main problems: first, the adjustment process is lengthy and cannot be quantified; second, the unevenness within the screen necessitates repeated adjustments to the compensation coefficients in different areas; and third, significant differences exist between screens, requiring piecemeal adjustments.

[0073] In view of the above problems, this application proposes a method for determining screen brightness compensation coefficient, a compensation method, and a product to improve the efficiency of screen brightness compensation. The following, in conjunction with the accompanying drawings, provides a detailed description of the method for determining screen brightness compensation coefficient, the compensation method, and the product provided by this application through some embodiments and application scenarios.

[0074] The first aspect of this application provides a method for determining the screen brightness compensation coefficient. The method for determining the screen brightness compensation coefficient of the first aspect will be described below through sections 1.1, 1.2, 1.3 and 1.4.

[0075] 1.1 A brief overview of the method for determining the screen brightness compensation coefficient:

[0076] Referring to Figure 1, Figure 1 shows a flowchart of a method for determining a screen brightness compensation coefficient. As shown in Figure 1, the method includes:

[0077] Step S101: Acquire a target image captured from the target screen.

[0078] Specifically, the target screen can be a Liquid Crystal Display (LCD) screen with a Dual-gate structure, employing either Hardware Super Resolution (HSR) or Dual Line Gate (DLG) frequency multiplication. The target screen can be the screen after applying an initial compensation value. Applying the initial compensation value means that the screen has undergone preliminary brightness compensation using common brightness compensation methods, bringing the brightness differences within a certain threshold range.

[0079] In this embodiment, an industrial camera can be used to photograph the target screen. Referring to Figure 2, Figure 2 shows a schematic diagram of a brightness compensation system. As shown in Figure 2, the brightness compensation system includes: a host computer, a darkroom mechanism (the screen is placed in the darkroom mechanism to facilitate the camera to capture screen images), a pattern generator (PG), a camera, and a target screen. The host computer is equipped with host computer software to execute the screen brightness compensation coefficient determination method proposed in the first aspect of this application. The camera can be a high-resolution, low-noise industrial camera. Specifically, the target image capture process includes: the screen is displayed on the screen, then the host computer software controls the PG to light up the target screen, controls the camera to capture images of the target screen, and processes the captured images to obtain the target image.

[0080] Step S102: Divide the target image into multiple image regions corresponding to different screen regions of the target screen.

[0081] Specifically, the target screen is divided into multiple screen regions. The target image captured in step S101 is divided according to the different screen regions to obtain multiple image regions, each image region corresponding one-to-one with a screen region. For example, if the target screen is divided into M*N screen regions, the target image can be correspondingly divided into M*N image regions.

[0082] Step S103: Calculate the average brightness of each image region in the target image.

[0083] Referring to Figure 3, which shows a schematic diagram of a brightness compensation process, after capturing the target image, the target image is divided into multiple image regions. Then, the average brightness of each image region is calculated. The average brightness is calculated by averaging the brightness values ​​of each pixel in the image region.

[0084] Step S104: Input the average brightness of each image region in the target image into a pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient for each screen region of the target screen. The brightness compensation coefficient prediction network is trained by using sample images taken for the sample screen as training samples and the standard brightness compensation coefficients of each screen region corresponding to the sample images as labels.

[0085] As shown in Figure 3, the average brightness value of each image region is input into the brightness compensation coefficient prediction network to obtain the corresponding predicted brightness compensation coefficients output by the network. The brightness compensation coefficient prediction network is trained in advance using training samples (average brightness values ​​of each image region of a sample image taken from a sample screen) and sample labels (standard brightness compensation coefficients for each screen region corresponding to the sample image). The sample screen can be an LCD screen from the same batch as the target screen. The neural network used for training can be CNN, GAN, or Transformer. The predicted brightness compensation coefficients can be output in tabular form according to the position of the corresponding screen region. Referring to Figure 4, a schematic diagram of a brightness compensation coefficient prediction network is shown. As shown in Figure 4, a CNN is used as the brightness compensation coefficient prediction network, mainly composed of an input layer, hidden layers, and an output layer. For example, dividing the target screen into M*N screen regions corresponds to dividing the target image into M*N image regions, obtaining M*N average brightness values, and causing the brightness compensation coefficient prediction network to output a table of predicted brightness compensation coefficients in M ​​rows and N columns. In this embodiment, since adjacent screen areas may have the same predicted brightness compensation coefficient, elements with the same value in the table can be merged to reduce the amount of data that needs to be stored. After obtaining the predicted brightness compensation coefficient, the screen performs brightness compensation based on the predicted brightness compensation coefficient.

[0086] This application utilizes sample images as training samples and pre-tuned screen parameters as training sample labels to train a neural network (i.e., a brightness compensation coefficient prediction network). This network can predict the corresponding brightness compensation coefficient based on the average brightness of each image region of the screen image. During actual brightness compensation of the target screen, the average brightness of each image region in the target image is input into the pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient. This allows the target screen to perform brightness compensation based on the predicted coefficient, resolving the problem of uneven screen brightness and improving the efficiency of brightness compensation.

[0087] 1.2: Explanation of the training process for the brightness compensation coefficient prediction network:

[0088] In one possible implementation, the brightness compensation coefficient prediction network is trained through the following steps:

[0089] Step S201: Obtain the sample image captured for the sample screen, and the standard brightness compensation coefficients for each screen area corresponding to the sample image. Specifically, referring to Figure 5, which illustrates a training process of a brightness compensation coefficient prediction network, the first step is to acquire the sample image. The sample screen can be a product manufactured in the same batch as the target screen. The sample image is a screen image captured after applying an initial compensation value to the sample screen. The standard brightness compensation coefficient refers to the brightness compensation coefficient used empirically to complete the brightness compensation of the sample screen, ensuring that the sample screen has no fine lines and uniform screen brightness after brightness compensation.

[0090] Step S202 involves dividing the sample image into multiple sample image regions corresponding to different screen areas of the sample screen. Specifically, the sample screen is divided into multiple screen areas (e.g., M*N screen areas), and the sample image is divided according to the different screen areas to obtain multiple sample image regions.

[0091] Step S203: Calculate the average sample brightness of each sample image region in the sample image.

[0092] Step S204: Input the average sample brightness value into the neural network to be trained to obtain the sample brightness compensation coefficient for each screen region of the sample screen. As shown in Figure 5, for each sample image region, after calculating the corresponding average sample brightness value, it is input into the neural network to obtain the sample brightness compensation coefficient.

[0093] Step S205: Calculate the loss function value based on the sample brightness compensation coefficient and the standard brightness compensation coefficient. Specifically, the loss function value is calculated with the goal of making the neural network output (sample brightness compensation coefficient) as close as possible to the label (standard brightness compensation coefficient). Optionally, the loss function can be the following formula:

[0094] Where M*N represents the number of screen regions (i.e., the number of sample image regions) into which the sample screen is divided, meaning that the sample screen consists of M rows and N columns of screen regions; i Indicates the sample brightness compensation coefficient; This represents the standard brightness compensation coefficient. As shown in Figure 5, after calculating the loss function value, gradient backpropagation is performed on the neural network to update the relevant parameters.

[0095] Step S206: Repeat the above steps until the preset number of training iterations is reached or the loss function value converges, then end the training to obtain the brightness compensation coefficient prediction network. Specifically, reselect training samples (i.e., sample images), and iteratively train the neural network by repeating steps S201-S205 until the preset number of training iterations is reached, or the loss function value converges (the loss function value gradually decreases with iterative training until it stabilizes within a certain numerical range), then end the training and use the trained neural network as the brightness compensation coefficient prediction network.

[0096] This embodiment of the application, through the above steps (steps S201-S206), uses sample images (the average brightness of each image region of the sample image) captured on a sample screen as training samples, and uses screen parameters (i.e., the standard brightness compensation coefficients corresponding to each screen region of the sample image) that have been empirically adjusted as training sample labels to train a neural network (i.e., a brightness compensation coefficient prediction network). This enables the neural network to predict the corresponding brightness compensation coefficient based on the average brightness of each image region of the screen image. Thus, the neural network automatically determines the brightness compensation coefficient based on the captured screen image, solving the problem of uneven screen brightness and improving the efficiency of screen brightness compensation.

[0097] 1.3: Store the predicted brightness compensation coefficients:

[0098] In one possible implementation, the method further includes:

[0099] The predicted brightness compensation coefficient is written into the memory of the target screen so that the target screen can use the predicted brightness compensation coefficient to perform brightness compensation for the target screen.

[0100] Specifically, as shown in Figure 3, after obtaining the predicted brightness compensation coefficient, it is written into the target screen's memory (e.g., the PCB flash shown in Figure 3), enabling the target screen to perform its own brightness compensation based on this parameter (predicted brightness compensation coefficient). (As shown in Figure 3, during the use of the screen IP, the corresponding predicted brightness compensation coefficient is obtained by calling the compensation IP, and then brightness compensation is performed on the target screen.) The specific storage method can be as shown in Figure 2, utilizing the PG control and signal writing function of the host computer software. By controlling the PG, the obtained predicted brightness compensation coefficient is written into the timing controller (Tcon) chip, and then burned into the printed circuit board (PCB) cache of the target screen.

[0101] 1.4: Verification of the predicted brightness compensation coefficient:

[0102] In one possible implementation, the method further includes:

[0103] Step S105: Obtain the standard image corresponding to the target screen. The standard image corresponding to the target screen is: an image taken of the target screen after brightness compensation.

[0104] Step S106: The effectiveness of the predicted brightness compensation coefficient is verified using the standard image corresponding to the target screen.

[0105] Step S107: If the predicted brightness compensation coefficient is verified to be valid, the predicted brightness compensation coefficient is written into the memory of the target screen.

[0106] To further improve the screen brightness compensation effect, this embodiment proposes to verify the predicted brightness compensation coefficient after obtaining it, and then write it to the target screen's memory after successful verification. Specifically, referring to Figure 6, which shows a schematic flowchart of screen brightness compensation verification, the target screen is displayed, and the graphics signal generator PG is controlled to light up the target screen and complete position calibration (as shown in "Lighting Calibration" in Figure 6). Step S101 is executed, and the camera is controlled to take a picture of the target screen. The captured image is processed to obtain the target image (as shown in "Screen Capture" in Figure 6). Steps S102-S104 are executed to obtain the predicted brightness compensation coefficient (as shown in "Algorithm Processing" in Figure 6). Then, the predicted brightness compensation coefficient is sent to the target screen (as shown in "Data Sending" in Figure 6). Through automatic image detection, it is compared with a standard image (i.e., an image taken of the target screen after manual brightness adjustment) to determine whether the compensation based on the predicted brightness compensation coefficient is complete (as shown in "Compensation Effect Evaluation" in Figure 6). If the verification is successful, the predicted brightness compensation coefficients are then burned into the PCB flash memory, i.e., written into the memory of the target screen (as shown in "burning" in Figure 6). Finally, the target screen is manually confirmed to have completed brightness compensation. After confirming that the brightness compensation is complete, the target screen is removed from the display. In this embodiment, after obtaining the predicted brightness compensation coefficients, the predicted brightness compensation coefficients based on the network output are verified to detect whether they can achieve the expected brightness compensation effect (complete brightness compensation for the target screen), further improving the screen brightness compensation effect.

[0107] 1.4.1: Specific verification method:

[0108] In one possible implementation, step S106 verifies the effectiveness of the predicted brightness compensation coefficient using a standard image corresponding to the target screen, including:

[0109] Step S1061: Send the predicted brightness compensation coefficient of each screen area of ​​the target screen to the screen processor of the target screen.

[0110] Step S1062: In response to the screen processor performing brightness compensation using the predicted brightness compensation coefficient, a brightness-compensated image of the target screen is acquired.

[0111] Step S1063: Compare the brightness of the brightness-compensated image with the standard image corresponding to the target screen.

[0112] Step S1064: If the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is less than the target threshold, the predicted brightness compensation coefficient is determined to have passed verification.

[0113] Step S1065: If the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is not less than the target threshold, it is determined that the predicted brightness compensation coefficient verification fails.

[0114] In this embodiment, after executing steps S101-S104 to obtain the predicted brightness compensation coefficient, the predicted brightness compensation coefficient is sent to the screen processor of the target screen. The screen processor uses the predicted brightness compensation coefficient to perform brightness compensation on the target screen, and then takes a picture of the target screen to obtain a brightness-compensated image. The brightness-compensated image is compared with a standard image (i.e., an image taken of the target screen after manual brightness adjustment). If the brightness difference between the two is less than a target threshold, it indicates that the brightness compensation is complete and the predicted brightness compensation coefficient has passed verification. If the brightness difference is greater than or equal to the target threshold, it indicates that the brightness-compensated image still has uneven brightness, and the predicted brightness compensation coefficient has failed verification.

[0115] 1.4.2: Specific methods when verification fails:

[0116] In one possible implementation, the method further includes:

[0117] If the predicted brightness compensation coefficient fails the verification, a new target image is captured for the target screen, and a new predicted brightness compensation coefficient for each screen area of ​​the target screen is obtained through the compensation coefficient prediction network to re-verify the effectiveness of the new predicted brightness compensation coefficient.

[0118] Specifically, as shown in Figure 6, if the verification fails, the target screen is recalibrated (the target screen is lit up and the position calibration is completed), and the above process is repeated: the target screen is photographed again according to step S101 to obtain a new target image; steps S102-S104 are performed on the new target image to obtain a new predicted brightness compensation coefficient through the compensation coefficient prediction network; the new predicted brightness compensation coefficient is re-verified according to the above steps S1061-S1065.

[0119] 1.4.3: Specific methods when multiple verifications fail:

[0120] In one possible implementation, the method further includes:

[0121] If at least one verification fails, record the predicted brightness compensation coefficient used for each brightness compensation, and / or output a manual brightness compensation prompt for the target screen.

[0122] In this embodiment, if the verification fails, the method proposed in 1.4.2 can be followed: acquire a new target image, determine a new predicted brightness compensation coefficient using the compensation coefficient prediction network, and re-verify. If the verification still fails after multiple attempts, relevant information (the target image acquired in each round of brightness compensation and the predicted brightness compensation coefficient) is recorded. A prompt message (i.e., a manual brightness compensation prompt for the target screen) can also be output to remind relevant management personnel to manually adjust the brightness of the target screen.

[0123] A second aspect of this application also provides a screen brightness compensation method. Referring to FIG7, FIG7 shows a flowchart of the steps of a screen brightness compensation method. As shown in FIG7, the method includes:

[0124] Step S301: Based on the screen area corresponding to each pixel in the target image captured for the target screen, query the pre-stored brightness compensation information to determine the predicted brightness compensation coefficient corresponding to each pixel in the target image. The brightness compensation information includes the predicted brightness compensation coefficient of each screen area of ​​the target screen. The predicted brightness compensation information is determined by the screen brightness compensation coefficient determination method described in the first aspect of the embodiments of this application.

[0125] Step S302: Perform brightness compensation on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image.

[0126] In this embodiment, after obtaining the predicted brightness compensation information for each screen area of ​​the target screen according to steps S101-S104 above, it is stored as brightness compensation information in the target screen's memory (e.g., PCB flash). The target screen extracts the predicted brightness compensation coefficient for each pixel from the memory based on the screen area corresponding to that pixel (for example, if pixel a is determined to belong to screen area A1, and the predicted brightness compensation coefficient corresponding to screen area A1 is 0.5, then the predicted brightness compensation coefficient for pixel a is determined to be 0.5). For the target screen, brightness compensation is performed according to the predicted brightness compensation coefficient corresponding to each pixel.

[0127] In one possible implementation, the method further includes:

[0128] Obtain the precharge value corresponding to each pixel in the target image;

[0129] Based on the pre-charge value corresponding to each pixel in the target image, determine the compensation value corresponding to each pixel in the target image;

[0130] Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image, including:

[0131] Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient and compensation value corresponding to each pixel in the target image.

[0132] Referring to Figure 8, which illustrates a logic diagram for brightness compensation of a target screen, as shown in Figure 8, the pixel values ​​of the target image captured on the target screen are first obtained, as shown in Figure 8 as the input pixel (R). x,y G x,y B x,y Read the precharge value corresponding to each pixel, i.e., the current precharge data value (R′) shown in Figure 8. x,y , G′ x,y B′ x,y ).

[0133] Furthermore, the brightness compensation information also includes a brightness compensation information table (LUT), which represents the relationship curve between the pixel value, pre-charge value, and compensation value of a pixel. Based on the pixel's position (x, y), the screen area where the pixel is located is determined, and the corresponding predicted brightness compensation coefficient (Gain as shown in Figure 8) is determined, along with pre-stored brightness compensation information tables (R_LUT, G_LUT, and B_LUT as shown in Figure 8).

[0134] Therefore, based on the pixel value and precharge value of each pixel, the addressing index is determined in the corresponding brightness compensation information table (LUT) to obtain the compensation value corresponding to each pixel. For example, as shown in Figure 8, based on the pixel's (R... x,y , R′ x,y In the corresponding brightness compensation information table R_LUT, an addressing index is performed to obtain R. x,y The corresponding compensation value C R .

[0135] According to the predicted brightness compensation coefficient Gain and compensation value (as shown in Figure 8) for each pixel in the target image: C R C G C B The target screen is then subjected to brightness compensation according to the following formula:

[0136] After compensation R x,y =R x,y +C R *Gain;

[0137] After compensation G x,y =G x,y +C G*Gain;

[0138] After compensation B x,y =B x,y +C B *Gain;

[0139] As shown in Figure 8, the brightness compensation pixel value of each pixel is output to complete the brightness compensation of the target screen.

[0140] This application proposes that, in the actual process of brightness compensation, a pre-trained brightness compensation coefficient prediction network is used to obtain the predicted brightness compensation coefficients for each screen area. This enables the target screen to obtain the predicted brightness compensation coefficients corresponding to each pixel by querying the pre-stored brightness compensation information, thereby completing the brightness compensation of the target screen, solving the problem of uneven screen brightness, and improving the compensation efficiency of screen brightness compensation.

[0141] The third aspect of this application also provides a screen brightness compensation system. Referring to FIG9, FIG9 shows a schematic diagram of another screen brightness compensation system. As shown in FIG9, the system includes at least: a host computer, a camera, and a screen.

[0142] The host computer includes a first processor, which is used to execute the screen brightness compensation coefficient determination method described in the first aspect of the embodiments of this application;

[0143] The screen includes: a screen memory and a screen processor, wherein the screen processor is used to execute the screen brightness compensation method described in the second aspect of the embodiments of this application;

[0144] The camera is used to capture images of the screen.

[0145] A fourth aspect of this application also provides a screen brightness compensation coefficient determination device, applied to perform the screen brightness compensation coefficient determination method described in the first aspect of this application. Referring to FIG10, FIG10 shows a schematic diagram of the structure of a screen brightness compensation coefficient determination device. As shown in FIG10, the device includes:

[0146] The image acquisition module is used to acquire a target image captured from the target screen.

[0147] An image region segmentation module is used to divide the target image into multiple image regions corresponding to different screen regions of the target screen;

[0148] The average brightness calculation module is used to calculate the average brightness of each image region in the target image;

[0149] The brightness compensation coefficient determination module is used to input the average brightness of each image region in the target image into a pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient for each screen region of the target screen. The brightness compensation coefficient prediction network is trained by using sample images taken for the sample screen as training samples and the standard brightness compensation coefficients of each screen region corresponding to the sample images as labels.

[0150] In one possible implementation, the brightness compensation coefficient prediction network is trained through the following steps:

[0151] Obtain the sample image captured for the sample screen, and the standard brightness compensation coefficient for each screen area corresponding to the sample image;

[0152] The sample image is divided into multiple sample image regions corresponding to different screen regions of the sample screen;

[0153] Calculate the mean sample brightness of each sample image region in the sample image;

[0154] The average brightness of the samples is input into the neural network to be trained to obtain the sample brightness compensation coefficient for each screen area of ​​the sample screen.

[0155] The loss function value is calculated based on the sample brightness compensation coefficient and the standard brightness compensation coefficient;

[0156] Repeat the above steps until the preset number of training iterations or the loss function value converges, then end the training and obtain the brightness compensation coefficient prediction network.

[0157] In one possible implementation, the device further includes:

[0158] The first writing module is used to write the predicted brightness compensation coefficient into the memory of the target screen, so that the target screen can use the predicted brightness compensation coefficient to complete the brightness compensation for the target screen.

[0159] In one possible implementation, the device further includes:

[0160] A standard image acquisition module is used to acquire a standard image corresponding to the target screen, wherein the standard image corresponding to the target screen is: an image taken of the target screen after brightness compensation;

[0161] The verification module is used to verify the effectiveness of the predicted brightness compensation coefficient using a standard image corresponding to the target screen.

[0162] The second writing module is used to write the predicted brightness compensation coefficient into the memory of the target screen if the predicted brightness compensation coefficient is verified to be valid.

[0163] In one possible implementation, the verification module includes:

[0164] The sending submodule is used to send the predicted brightness compensation coefficient of each screen area of ​​the target screen to the screen processor of the target screen;

[0165] The brightness-compensated image acquisition submodule, in response to the screen processor performing brightness compensation using the predicted brightness compensation coefficient, acquires a brightness-compensated image captured for the target screen.

[0166] The brightness comparison submodule is used to compare the brightness of the brightness-compensated image with the standard image corresponding to the target screen.

[0167] The first verification submodule is used to determine that the predicted brightness compensation coefficient has passed verification if the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is less than a target threshold.

[0168] The second verification submodule is used to determine that the predicted brightness compensation coefficient fails verification if the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is not less than the target threshold.

[0169] In one possible implementation, the device further includes:

[0170] The re-verification module is used to reacquire the target image captured on the target screen when the predicted brightness compensation coefficient fails verification, and obtain a new predicted brightness compensation coefficient for each screen area of ​​the target screen through the compensation coefficient prediction network, so as to re-verify the validity of the new predicted brightness compensation coefficient.

[0171] In one possible implementation, the device further includes:

[0172] The prompting module is used to record the predicted brightness compensation coefficient used for each brightness compensation attempt if at least one verification fails, and / or output a manual brightness compensation prompt for the target screen.

[0173] The fifth aspect of this application also provides a screen brightness compensation device, applied to the screen brightness compensation method described in the second aspect of this application. Referring to FIG11, FIG11 shows a schematic diagram of the structure of a screen brightness compensation device. As shown in FIG11, the device includes:

[0174] The information query module is used to query pre-stored brightness compensation information based on the screen area corresponding to each pixel in the target image captured for the target screen, and determine the predicted brightness compensation coefficient corresponding to each pixel in the target image. The brightness compensation information includes the predicted brightness compensation coefficient of each screen area of ​​the target screen. The predicted brightness compensation information is determined by the screen brightness compensation coefficient determination method described in the first aspect of the embodiments of this application.

[0175] The brightness compensation module is used to perform brightness compensation on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image.

[0176] In one possible implementation, the device further includes:

[0177] A precharge value acquisition module is used to acquire the precharge value corresponding to each pixel in the target image;

[0178] The compensation value determination module is used to determine the compensation value corresponding to each pixel in the target image based on the pre-charge value corresponding to each pixel in the target image.

[0179] Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image, including:

[0180] Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient and compensation value corresponding to each pixel in the target image.

[0181] This application also provides an electronic device. Referring to FIG12, FIG12 is a schematic diagram of the structure of the electronic device proposed in this application. As shown in FIG12, the electronic device 100 includes: a memory 110 and a processor 120. The memory 110 and the processor 120 are connected via a bus communication connection. The memory 110 stores a computer program, which can run on the processor 120 to implement the steps of the screen brightness compensation coefficient determination method described in the first aspect of this application, or the steps of the screen brightness compensation method described in the second aspect of this application.

[0182] This application also provides a computer-readable storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements the steps of the screen brightness compensation coefficient determination method described in the first aspect of this application, or the steps of the screen brightness compensation method described in the second aspect of this application.

[0183] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of the screen brightness compensation coefficient determination method as described in the first aspect of this application, or the steps of the screen brightness compensation method as described in the second aspect of this application.

[0184] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0185] This application describes embodiments with reference to flowchart illustrations and / or block diagrams of methods, apparatus, electronic devices, and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing terminal equipment to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal equipment, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0186] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0187] These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable terminal equipment, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0188] Although preferred embodiments of the present application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present application.

[0189] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0190] The above provides a detailed description of the screen brightness compensation coefficient determination method, compensation method, and product provided in this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A method for determining screen brightness compensation coefficient, wherein, The method includes: Acquire a target image captured from the target screen; The target image is divided into multiple image regions corresponding to different screen regions of the target screen; Calculate the average brightness of each image region in the target image; The average brightness of each image region in the target image is input into a pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient for each screen region of the target screen. The brightness compensation coefficient prediction network is trained by using sample images taken for the sample screen as training samples and the standard brightness compensation coefficients of each screen region corresponding to the sample images as labels.

2. The method for determining the screen brightness compensation coefficient according to claim 1, wherein, The brightness compensation coefficient prediction network is trained through the following steps: Obtain the sample image captured for the sample screen, and the standard brightness compensation coefficient for each screen area corresponding to the sample image; The sample image is divided into multiple sample image regions corresponding to different screen regions of the sample screen; Calculate the mean sample brightness of each sample image region in the sample image; The average brightness of the samples is input into the neural network to be trained to obtain the sample brightness compensation coefficient for each screen area of ​​the sample screen. The loss function value is calculated based on the sample brightness compensation coefficient and the standard brightness compensation coefficient; Repeat the above steps until the preset number of training iterations or the loss function value converges, then end the training and obtain the brightness compensation coefficient prediction network.

3. The method for determining the screen brightness compensation coefficient according to claim 1, wherein, The method further includes: The predicted brightness compensation coefficient is written into the memory of the target screen so that the target screen can use the predicted brightness compensation coefficient to perform brightness compensation for the target screen.

4. The method for determining the screen brightness compensation coefficient according to claim 1, wherein, The method further includes: Acquire a standard image corresponding to the target screen, wherein the standard image corresponding to the target screen is: an image taken of the target screen after brightness compensation; The effectiveness of the predicted brightness compensation coefficient is verified using a standard image corresponding to the target screen. If the predicted brightness compensation coefficient passes verification, the predicted brightness compensation coefficient is written into the memory of the target screen.

5. The method for determining the screen brightness compensation coefficient according to claim 4, wherein, The effectiveness of the predicted brightness compensation coefficient is verified using a standard image corresponding to the target screen, including: The predicted brightness compensation coefficient for each screen area of ​​the target screen is sent to the screen processor of the target screen; In response to the screen processor performing brightness compensation using the predicted brightness compensation coefficient, a brightness-compensated image of the target screen is acquired. The brightness of the brightness-compensated image is compared with the brightness of the standard image corresponding to the target screen. If the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is less than the target threshold, the predicted brightness compensation coefficient is determined to have passed the verification. If the brightness difference between the brightness-compensated image and the standard image corresponding to the target screen is not less than the target threshold, the predicted brightness compensation coefficient is determined to fail verification.

6. The method for determining the screen brightness compensation coefficient according to claim 5, wherein, The method further includes: If the predicted brightness compensation coefficient fails the verification, a new target image is captured for the target screen, and a new predicted brightness compensation coefficient for each screen area of ​​the target screen is obtained through the compensation coefficient prediction network to re-verify the effectiveness of the new predicted brightness compensation coefficient.

7. The method for determining the screen brightness compensation coefficient according to any one of claims 4-6, wherein, The method further includes: If at least one verification fails, record the predicted brightness compensation coefficient used for each brightness compensation, and / or output a manual brightness compensation prompt for the target screen.

8. A screen brightness compensation method, wherein, The method includes: Based on the screen area corresponding to each pixel in the target image captured for the target screen, the pre-stored brightness compensation information is queried to determine the predicted brightness compensation coefficient corresponding to each pixel in the target image. The brightness compensation information includes the predicted brightness compensation coefficient for each screen area of ​​the target screen. The predicted brightness compensation information is determined by the screen brightness compensation coefficient determination method according to any one of claims 1-7. The target screen is brightness compensated according to the predicted brightness compensation coefficient corresponding to each pixel in the target image.

9. The screen brightness compensation method according to claim 8, wherein, The method further includes: Obtain the precharge value corresponding to each pixel in the target image; Based on the pre-charge value corresponding to each pixel in the target image, determine the compensation value corresponding to each pixel in the target image; Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image, including: Brightness compensation is performed on the target screen according to the predicted brightness compensation coefficient and compensation value corresponding to each pixel in the target image.

10. A screen brightness compensation system, wherein, The system includes at least: a host computer, a camera, and a screen; The host computer includes a first processor, which is used to execute the screen brightness compensation coefficient determination method according to any one of claims 1-7; The screen includes: a screen memory and a screen processor, wherein the screen processor is used to execute the screen brightness compensation method as described in claim 8 or 9; The camera is used to capture images of the screen.

11. A device for determining screen brightness compensation coefficient, wherein, The apparatus is used to perform the screen brightness compensation coefficient determination method according to any one of claims 1-7, the apparatus comprising: The image acquisition module is used to acquire a target image captured from the target screen. An image region segmentation module is used to divide the target image into multiple image regions corresponding to different screen regions of the target screen; The average brightness calculation module is used to calculate the average brightness of each image region in the target image; The brightness compensation coefficient determination module is used to input the average brightness of each image region in the target image into a pre-trained brightness compensation coefficient prediction network to obtain the predicted brightness compensation coefficient for each screen region of the target screen. The brightness compensation coefficient prediction network is trained by using sample images taken for the sample screen as training samples and the standard brightness compensation coefficients of each screen region corresponding to the sample images as labels.

12. A screen brightness compensation device, wherein, The device, applied to the screen brightness compensation method of claim 8 or 9, comprises: The information query module is used to query pre-stored brightness compensation information based on the screen area corresponding to each pixel in the target image captured for the target screen, and determine the predicted brightness compensation coefficient corresponding to each pixel in the target image. The brightness compensation information includes the predicted brightness compensation coefficient of each screen area of ​​the target screen, and the predicted brightness compensation information is determined by the screen brightness compensation coefficient determination method according to any one of claims 1-7. The brightness compensation module is used to perform brightness compensation on the target screen according to the predicted brightness compensation coefficient corresponding to each pixel in the target image.

13. An electronic device comprising a memory and a processor, wherein the memory stores a computer program executable on the processor, wherein... When the processor executes the computer program, it implements the steps of the screen brightness compensation coefficient determination method as described in any one of claims 1-7, or the steps of the screen brightness compensation method as described in claim 8 or 9.

14. A computer-readable storage medium, wherein, It stores a computer program that, when executed by a processor, implements the steps of the screen brightness compensation coefficient determination method as described in any one of claims 1-7, or the steps of the screen brightness compensation method as described in claim 8 or 9.

Images