Display panel brightness compensation model construction method, compensation method and device

Abstract

The present application provides a method for constructing a display panel brightness compensation model, a compensation method and a device, the method comprising determining a training sample set, the training sample set comprising display parameters and corresponding target display parameters obtained by photographing an actual display image of a display panel displaying a predetermined grayscale through an image acquisition device; inputting the training sample set into a pre-constructed neural network model to train the neural network model to obtain a trained compensation model, the compensation model being used to predict the brightness compensation value of each pixel on the display panel based on the display parameters of the display panel. Compared with the existing Demura technology, the present application considers the influence of each pixel and the surrounding pixels and the image acquisition device to predict the brightness compensation value, thereby improving the accuracy of the brightness compensation value prediction, and thus improving the compensation accuracy and compensation effect.

Description

Technical Field

[0001] The present application belongs to the field of display technology, and in particular relates to a display panel brightness compensation model construction method, a compensation method and a device. Background Art

[0002] With the development of screen display technology, various screen display technologies such as liquid crystal display (LCD), organic light-emitting diode (OLED), active-matrix organic light-emitting diode (AMOLED) and micro light-emitting diode (MicroLightEmitting Diode, Micro LED) have been widely used in various fields.

[0003] Due to various reasons in the process, there will be brightness differences or color differences between the light-emitting elements in the display panel, which is the mura phenomenon. The mura phenomenon exists in the various screen display technologies mentioned above. Take Micro LED display technology as an example. This technology is a display technology that integrates micron-level semiconductor light-emitting diodes (Light Emitting Diode, LED) in a matrix form with high density on a chip. However, due to the limitations of the crystallization process, when low-temperature polycrystalline silicon (Low-Temperature Polycrystalline Silico, LTPS) technology is used on a large-area glass substrate, thin film transistors (Thin Film Transistor, TFT) at different positions often have non-uniformity in electrical parameters such as threshold voltage and mobility. This non-uniformity will be converted into current differences and brightness differences in the MicroLED display panel, and will be perceived by the human eye, which is the mura phenomenon.

[0004] In order to compensate for the mura phenomenon caused by process defects, the prior art generally adopts demura technology to correct the brightness of the display panel through brightness compensation, thereby eliminating the mura phenomenon. However, the formula algorithm used in the existing demura technology is relatively complex, and its processing accuracy is low for low-brightness images and edge images, resulting in poor compensation effect and low compensation accuracy. Summary of the invention

[0005] One object of the present application is to provide a method for constructing a display panel brightness compensation model, to construct a compensation model for display panel brightness compensation based on an optimized neural network model, to predict the brightness compensation value corresponding to each pixel in the display panel, to achieve the prediction and compensation of the brightness compensation value corresponding to each pixel, and to greatly improve the accuracy of Demura brightness compensation. Another object of the present application is to provide a display panel brightness compensation method. Another object of the present application is to provide a display panel brightness compensation model construction device. Still another object of the present application is to provide a display panel brightness compensation device.

[0006] In order to achieve the above-mentioned object, the present application discloses, on one hand, a method for constructing a display panel brightness compensation model, comprising:

[0007] Determine a training sample set, wherein the training sample set includes display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale by an image acquisition device and corresponding target display parameters;

[0008] The training sample set is input into a pre-built neural network model to train the neural network model to obtain a trained compensation model, and the compensation model is used to predict the brightness compensation value of each pixel on the display panel based on the display parameters of the display panel.

[0009] Optionally, the target display parameter is a display parameter corresponding to a target display image of the predetermined gray scale displayed on the display panel photographed by an image acquisition device; or

[0010] The target display parameters are target brightness compensation values ​​for each pixel on the display panel obtained based on display parameters obtained by photographing an actual display image of a predetermined gray scale displayed on the display panel through an image acquisition device and display parameters corresponding to a target display image of the predetermined gray scale displayed on the display panel through an image acquisition device.

[0011] Optionally, the display parameters include position information of each data point on the actual display image corresponding to each pixel of the display panel and a corresponding brightness value;

[0012] The target display parameters are display parameters corresponding to the target display image of the predetermined gray scale displayed on the display panel captured by an image acquisition device, and the target display parameters include position information and corresponding brightness values ​​of each pixel of the display panel corresponding to the target display image.

[0013] Optionally, the display parameters of the training sample set and the target display parameters further include the predetermined gray scale.

[0014] Optionally, the step of inputting the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model includes:

[0015] Dividing the training sample set into training samples and verification samples;

[0016] Inputting the training samples into a pre-built neural network model to train the neural network model to obtain a preliminary model;

[0017] Determine, by using the verification sample, an error value between a brightness compensation value of each pixel in the display panel predicted by the preliminary model and a target brightness compensation value;

[0018] When the error value does not satisfy the training stop condition, the steps of adjusting the weight coefficient of the preliminary model and using the training sample set to train the preliminary model with the adjusted weight coefficient are repeated until the error value satisfies the training stop condition to obtain the compensation model.

[0019] Optionally, the training stop condition is that the error value is less than a preset threshold;

[0020] The error value is obtained by:

[0021]

[0022] Wherein, MSE is the error value; m is the total number of rows of pixels in the display panel; n is the total number of columns of pixels in the display panel; i is the row number of the current pixel in the display panel; j is the column number of the current pixel in the display panel; A brightness compensation value predicted for a current pixel in the display panel; is the target brightness compensation value of the current pixel in the display panel.

[0023] Optionally, the display panel includes a plurality of regions obtained by pixel division, the training sample set includes a regional training sample set corresponding to each of the regions, the compensation model is a regional compensation model corresponding to each of the regions, and the regional training sample set is obtained by the following steps:

[0024] Using an image acquisition device to capture an actual display image of a predetermined gray scale displayed on the display panel;

[0025] Extracting the display parameters of the actual display image corresponding to each of the regions to obtain the regional display parameters;

[0026] The regional target display parameters corresponding to the regional display parameters of each of the regions are determined, and the regional training sample set is obtained based on the regional display parameters and the regional target display parameters.

[0027] Optionally, the neural network model is a convolutional neural network model, which includes a convolutional layer, a pooling layer and multiple fully connected layers.

[0028] Optionally, the MR of the image acquisition device is ≥2, and the MR is the ratio of the data points of the image captured by the image acquisition device to the number of pixels of the display panel.

[0029] The present application also discloses a display panel brightness compensation method, comprising:

[0030] The display parameters are obtained by photographing an actual display image of a predetermined gray scale displayed on a display panel by an image acquisition device;

[0031] Inputting the display parameters into a pre-trained compensation model to obtain a brightness compensation value corresponding to each pixel in the display panel;

[0032] Brightness compensation is performed on the display panel according to the brightness compensation value corresponding to each pixel.

[0033] The present application also discloses a display panel brightness compensation model construction device, comprising:

[0034] A data acquisition module, used to determine a training sample set, wherein the training sample set includes display parameters and corresponding target display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale through an image acquisition device;

[0035] A model training module is used to input the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, and the compensation model is used to predict the brightness compensation value of each pixel on the display panel based on the display parameters of the display panel.

[0036] The present application also discloses a display panel brightness compensation device, comprising:

[0037] A data acquisition module, used for obtaining display parameters by photographing an actual display image of a predetermined gray scale displayed by the display panel through an image acquisition device;

[0038] A model determination module, used for inputting the display parameters into a pre-trained compensation model to obtain a brightness compensation value corresponding to each pixel in the display panel;

[0039] The brightness compensation module is used to perform brightness compensation on the display panel according to the brightness compensation value corresponding to each pixel.

[0040] The beneficial effects of the present invention are as follows:

[0041] Compared with the prior art, the present application provides a method for constructing a display panel brightness compensation model to perform brightness compensation on each pixel of the display panel. The present application combines the existing AI basic theory, neural network and traditional Demura compensation technology, and modifies and optimizes the existing neural network model. The display parameters of the display panel are collected by an image acquisition device to form a training sample set. The optimized neural network model is trained to obtain a compensation model to perform brightness compensation on the display panel, and the brightness of the display panel can be compensated according to the brightness compensation value corresponding to each pixel. Compared with the existing Demura technology, the present application can obtain the brightness information of each pixel and the surrounding pixels and the corresponding position information of the pixels, and bring all the information into the convolution layer and the full connection layer of the neural network for training, taking into account the interference of the surrounding pixel light emission during the image acquisition process and the influence of the slight brightness difference of pixels at different positions, so as to improve the accuracy of the determined brightness compensation value, and thus improve the compensation accuracy. During the whole process, no personnel participation is required during training, and the corresponding parameters can also be adjusted according to the target display parameters. It is conducive to improving the compensation effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 A schematic diagram of a flow chart of a method for constructing a display panel brightness compensation model provided in an embodiment of the present application;

[0044] Figure 2 A schematic diagram corresponding to the training principle of the compensation model of the display panel brightness compensation model construction method provided in the embodiment of the present application;

[0045] Figure 3 A schematic diagram of a flow chart of a method S100 for constructing a display panel brightness compensation model provided in an embodiment of the present application;

[0046] Figure 4 A schematic diagram of a flow chart of a method S200 for constructing a display panel brightness compensation model provided in an embodiment of the present application;

[0047] Figure 5 A schematic diagram of the process of constructing a regional training sample set for a display panel brightness compensation model construction method provided in an embodiment of the present application;

[0048] Figure 6a One of the schematic diagrams of performing image segmentation on a training image by the display panel brightness compensation model construction method provided in an embodiment of the present application;

[0049] Figure 6b A second schematic diagram of image segmentation of a training image by the display panel brightness compensation model construction method provided in an embodiment of the present application;

[0050] Figure 7 A schematic diagram of a compensation model for a display panel brightness compensation model construction method provided in an embodiment of the present application;

[0051] Figures 8a-8d A schematic diagram comparing the display panel brightness compensation model construction method provided in the embodiment of the present application with the compensation effect of the prior art;

[0052] Fig. 9 A schematic diagram of a flow chart of a display panel brightness compensation method provided in an embodiment of the present application;

[0053] Fig.10 A schematic diagram of the structure of a display panel brightness compensation model construction device provided in an embodiment of the present application;

[0054] Fig.11 A schematic diagram of the structure of a display panel brightness compensation device provided in an embodiment of the present application;

[0055] Fig.12 A schematic diagram of the structure of a computer device suitable for implementing the method of the embodiment of the present application is provided for the embodiment of the present application. DETAILED DESCRIPTION

[0056] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0057] 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.

[0058] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0059] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0060] 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.

[0061] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0062] Demura technology is a method used to correct the uneven brightness and color of display panel pixels. Since each pixel of MicroLED is an independent light emitter, differences in brightness and color are inevitable during the manufacturing process, which will lead to uneven display effects. Therefore, Demura technology is applied to solve these problems.

[0063] At present, Demura technology first scans the Micro LED panel through a high-precision camera or optical sensor to detect the brightness and color deviation of each pixel. A specialized algorithm is used to process this data to generate a correction coefficient for each pixel. This process may involve complex mathematical models and machine learning algorithms to ensure that the corrected display effect reaches the optimal level. The correction coefficient is applied to the display drive circuit to adjust the drive current or PWM (pulse width modulation) signal of each pixel to correct the brightness and color non-uniformity. After applying the correction data, it is scanned and tested again to ensure that the corrected display effect meets the expectations. If necessary, the correction coefficient can be further fine-tuned.

[0064] Demura is achieved by obtaining the display image of the display panel through a camera, and then calculating the current or voltage that needs to be compensated based on the brightness or chromaticity change data on the display image, so that the brightness of the pixels can reach the standard brightness, making the screen look more uniform and achieving the purpose of eliminating mura.

[0065] However, because the camera itself has random noise, dark current and other influences, especially when the screen is at low grayscale, more exposure time is required, which deepens the influence of random noise such as dark current. As a result, although the current traditional algorithm has achieved good results in high grayscale compensation, it is not good in low grayscale compensation.

[0066] The camera lens is also distorted, so the accuracy of the value obtained in the center area of ​​the lens is higher than that in the periphery. Therefore, when compensating, the existing practice is to perform a correction on the entire lens on the displayed image. Even if this correction is nonlinear, the result cannot satisfy the requirement that each pixel is accurately corrected and cannot be accurate to each pixel.

[0067] In order to solve the above technical problems, the present application provides a method for constructing a display panel brightness compensation model. Figure 1 As shown, in this embodiment, the method includes:

[0068] S100: Determine a training sample set, where the training sample set includes display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale through an image acquisition device and corresponding target display parameters.

[0069] S200: Inputting the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, wherein the compensation model is used to predict a brightness compensation value of each pixel on the display panel based on display parameters of the display panel.

[0070] The display panel brightness compensation model construction method of the present application uses an image acquisition device to shoot an actual display image of a display panel displaying a predetermined gray scale, and sets the target display parameters corresponding to the actual display image to form a training sample set. The display parameters and target display parameters in the training sample set fully consider the difference in display brightness of each pixel on the display panel, the interference of the pixel brightness collected on the display image by the display brightness of its surrounding pixels, and the influence of the exposure time and the distortion of the shooting lens when the image acquisition device is shooting. The compensation model obtained by training the neural network model with the training sample set can determine the brightness compensation value for each pixel separately, eliminate the influencing factors of the brightness compensation value required for calculating the display panel to successfully display the predetermined gray scale, obtain an accurate brightness compensation value, improve the accuracy of the determined brightness compensation value, and then improve the compensation accuracy. During the whole process, no personnel participation is required during training, and the corresponding parameters can also be adjusted according to the target display parameters. It is conducive to improving the compensation effect.

[0071] In an optional implementation, the target display parameter is a display parameter corresponding to a target display image of the predetermined gray scale displayed on the display panel captured by an image acquisition device. Or,

[0072] The target display parameters are target brightness compensation values ​​for each pixel on the display panel obtained based on display parameters obtained by photographing an actual display image of a predetermined gray scale displayed on the display panel through an image acquisition device and display parameters corresponding to a target display image of the predetermined gray scale displayed on the display panel through an image acquisition device.

[0073] It is understandable that, in an optional implementation, the display parameters of the training sample set are the actual display images of the display panel displaying the predetermined gray scale captured by the image acquisition device. In order to take into account the interference of the pixel brightness on the display panel with the same display parameters with the display brightness of the surrounding pixels and the influence of the exposure time and the distortion of the shooting lens when the image acquisition device is shooting, the target display parameters may be the display parameters corresponding to the target display image of the display panel displaying the predetermined gray scale captured by the image acquisition device. Even if the display panel successfully displays the predetermined gray scale, the target display parameters are obtained by capturing the display image of the display panel by the image acquisition device.

[0074] Of course, in other optional implementations, the target brightness compensation value from when the display panel actually displays the predetermined grayscale to when it successfully displays the predetermined grayscale can also be directly calculated as the target display parameter. Here, the target brightness compensation value of the target display parameter also needs to take into account the influence of the pixel brightness on the display brightness of its surrounding pixels and the exposure time and lens distortion of the image acquisition device during shooting, so that the trained compensation model can predict an accurate brightness compensation value based on the actual display image captured.

[0075] In an optional implementation, the display parameters include position information of each data point on the actual display image corresponding to each pixel of the display panel and the corresponding brightness value.

[0076] The target display parameters are display parameters corresponding to the target display image of the predetermined gray scale displayed on the display panel captured by an image acquisition device, and the target display parameters include position information and corresponding brightness values ​​of each pixel of the display panel corresponding to the target display image.

[0077] Specifically, the display panel controls each pixel on the display panel to emit light to display the predetermined grayscale based on the display instruction of displaying the predetermined grayscale. However, the actual grayscale displayed by the display panel may be different from the predetermined grayscale. The display effect of the display panel displaying the predetermined grayscale can be reflected by the brightness value of each data point in the actual display image. The brightness value of each data point is obtained by detection, and the position information corresponding to the data point is used together as the display parameter of the display panel.

[0078] For example, for Figure 2 The pixels arranged in a 3*3 array are shown, and the 3*3 pixels need to be adjusted to 64 grayscales. The position information and the corresponding brightness value of the data point corresponding to each pixel in the actual display image of the current 3*3 pixels are used as the display parameters for training, and the corresponding brightness compensation value is determined as the target display parameter by taking 64 grayscales as the predetermined grayscale of the target display of each pixel, or the target display parameter is obtained by photographing the target display image obtained by the display panel when the 64 grayscales are successfully displayed, so as to form a training sample set for model training. During the training process, the brightness compensation value of each pixel in the 3*3 pixels is predicted by the convolution layer in the compensation model by fully considering the influence of the brightness of the surrounding pixels on the brightness of each pixel and the lens distortion of the image acquisition device, so as to realize separate brightness compensation for each pixel. The brightness compensation value predicted by the trained compensation model takes into account the influence of the brightness display of each pixel on the brightness of the surrounding pixels and the influence of the lens distortion on the pixel position to obtain the targeted brightness compensation value of each pixel. The accuracy of the pixel brightness compensation is high, which greatly improves the display effect of the display panel.

[0079] In an optional embodiment, if Figure 3 As shown, the step S100 of determining the training sample set includes:

[0080] S110: photographing an actual display image of a predetermined gray scale displayed on the display panel by an image acquisition device.

[0081] S120: Perform brightness detection on each data point of the actual display image to obtain a corresponding brightness value.

[0082] S130: Using the brightness value and corresponding position information of each data point on the actual display image as the display parameter.

[0083] Specifically, in S110, for a display panel, it is first necessary to light up the display panel so that each pixel therein displays a predetermined grayscale image, and then the display image of the display panel is photographed by an image acquisition device to obtain the image to be detected. An image acquisition device such as a camera or a video camera can be used to photograph the display panel to capture the actual display image. Of course, in actual applications, other feasible image acquisition devices can also be used for shooting, and this application does not limit this.

[0084] Among them, the position information of the pixels in the display panel can be expressed in a variety of ways. In one example, all pixels can be arranged in rows and columns, and the position information of the pixel in the display panel can be expressed according to the row position and column position of each pixel in the display panel. In other examples, the specific position of each pixel in the display panel can also be determined according to the coordinate value of each pixel, such as using the horizontal direction of the display panel as the horizontal axis and the vertical direction of the display panel as the vertical axis, so that the coordinate value of each pixel can be used as its position information in the display panel. Those skilled in the art can also use other methods to determine the position of each pixel in the display panel, which is not specifically limited.

[0085] It should be noted that the ratio MR of the data points of the image captured by the image acquisition device to the number of pixels of the display panel may be 1 or greater than 1. When MR is 1, the position information of the data points on the captured display image may be consistent with the position information of the pixel, or the position information corresponding to the pixel position may be set separately. When MR is greater than 1, a pixel on the display panel corresponds to multiple data points of the display image, and the position information may be set separately for each data point. For example, the position information of the row and column position or the position information of the coordinates may be used to calibrate the position of the data point. Those skilled in the art may set it according to actual needs, and this application does not limit this.

[0086] In an optional implementation, the MR of the image acquisition device is ≥2, and the MR is the ratio of the data points of the image captured by the image acquisition device to the number of pixels of the display panel.

[0087] Specifically, the present application uses a picture taken with MR=2 or 2.5 (i.e., one pixel on the display panel corresponds to 2×2 pixels on the camera, and the machine resolution is 4 times that of the screen), and the target value is the target value that needs to be compensated at present. For example, if compensation to 64 grayscale is required, all target values ​​are 64 for training. MR=2 or 2.5 adopted in the present application can obtain multiple brightness data for a pixel that needs to be compensated. Multiple brightness data can truly reflect the influence of lens distortion of the collected pixels, reduce calculation deviation in the model pooling process, and improve the accuracy of brightness compensation value prediction.

[0088] In an optional implementation, the display parameters of the training sample set and the target display parameters further include the predetermined gray scale.

[0089] Specifically, the existing Demura technology is affected by random noise and dark current in the camera itself, especially when the screen is at low grayscale, so more exposure time is required, which aggravates the influence of random noise such as dark current. As a result, although the current traditional algorithm has achieved good results in high grayscale compensation, it is not good in low grayscale compensation.

[0090] Therefore, in view of the situation where different grayscales have different effects on brightness compensation, this optional implementation adds the predetermined grayscale that the display panel currently needs to display to the training sample set, and the trained compensation model predicts the corresponding brightness compensation value for the predetermined grayscale to improve the prediction accuracy of the brightness compensation value under low grayscale conditions.

[0091] Of course, in other implementations, corresponding training sample sets may be set for different predetermined grayscales to be displayed, and the corresponding training sample sets are used to train the pre-set neural network model at different predetermined grayscales to obtain compensation models corresponding to different predetermined grayscales. In practical applications, the compensation model corresponding to the predetermined grayscale is selected based on the predetermined grayscale displayed by the current display panel to predict the brightness compensation value, thereby improving the accuracy of the brightness compensation value prediction when displaying different grayscales.

[0092] In an optional embodiment, if Figure 4 As shown, the step S200 inputs the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, including:

[0093] S210: Divide the training sample set into training samples and validation samples.

[0094] S220: Input the training samples into a pre-built neural network model to train the neural network model to obtain a preliminary model.

[0095] S230: Determine, by using the verification sample, an error value between the brightness compensation value of each pixel in the display panel predicted by the preliminary model and the target brightness compensation value.

[0096] S240: When the error value does not satisfy the training stop condition, repeatedly adjust the weight coefficient of the preliminary model and use the training sample set to train the preliminary model with the adjusted weight coefficient until the error value satisfies the training stop condition to obtain the compensation model.

[0097] In the embodiment of the present application, the training stop condition may be that the error value of the preset compensation model is less than a preset threshold. The error value of the preset compensation model may be obtained by the following formula (1):

[0098] Formula (1)

[0099] In formula (1), MSE is the error value; m is the total number of rows of pixels in the display panel; n is the total number of columns of pixels in the display panel; i is the row number of the current pixel in the display panel; j is the column number of the current pixel in the display panel; I(i, j) is the predicted brightness compensation value of the current pixel in the display panel; T(i, j) is the target brightness compensation value of the current pixel in the display panel.

[0100] It should be noted that technical personnel in this field can set the training stop condition separately according to needs and actual conditions, such as setting the training stop condition to the number of training times being greater than a preset threshold, or setting the training stop condition to the training time being greater than a preset market, without specific limitation.

[0101] Furthermore, in order to improve the prediction accuracy of the compensation model, a feedback network can be set for the compensation model in the embodiment of the present application. During the training process, the weight coefficient inside the compensation model is reversely adjusted according to the error between the predicted brightness compensation value output by the compensation model and the preset target brightness data.

[0102] Specifically, the error function of the feedback network can be determined according to formula (2):

[0103] Formula (2)

[0104] In formula (2), Wi follows the gradient according to the set learning rate changes, approaching the minimum error setting value; it can be determined according to the following formula (3):

[0105] Formula (3)

[0106] The descent function can be the derivative of the Relu activation function as shown in formula (4):

[0107] Formula (4)

[0108] In formula (3), W is the weight matrix of each link point, T is the target value, E is the error value, and I is the input matrix of the previous layer.

[0109] In an optional embodiment, if Figure 5 As shown, the display panel includes a plurality of regions obtained by pixel division, the training sample set includes a regional training sample set corresponding to each of the regions, the compensation model is a regional compensation model corresponding to each of the regions, and the regional training sample set is obtained by the following steps:

[0110] S310: photographing an actual display image of a predetermined gray scale displayed on a display panel by an image acquisition device.

[0111] S320: extracting display parameters of the actual display image corresponding to each of the regions to obtain region display parameters.

[0112] S330: Determine the regional target display parameter corresponding to the regional display parameter of each of the regions, and obtain the regional training sample set based on the regional display parameter and the regional target display parameter.

[0113] Specifically, it is understandable that as the pixels of the display panel develop in an increasingly higher direction and the data points of the image acquisition device increase, the complexity of the brightness compensation value prediction algorithm and model for the pixels of the display panel as a whole becomes increasingly higher, which also leads to the fact that deep learning and neural network technology cannot be simply applied to Demura. In order to solve this problem, the present application divides the display panel into multiple areas to greatly reduce the amount of data of the compensation model training sample set, and forms a training sample set for each single area to train the corresponding compensation model, thereby simplifying the complexity and training process of the compensation model, improving the training efficiency and pertinence of the compensation model, and improving the accuracy of the calculation of the brightness compensation value when the compensation model compensates for the middle area or edge area. In actual applications, after determining the area where the pixel to be brightness compensated is located, the compensation model corresponding to the area can be called to predict the brightness compensation value, thereby improving the accuracy of the brightness compensation value prediction of pixels in different areas.

[0114] In other implementations, the training display image may be segmented to obtain compensation models corresponding to different regions. There are many ways to segment regions or images. In one example, the display image may be segmented into multiple sub-display images corresponding to different regions in a rectangular shape. Figure 6a and Figure 6b, which is a schematic diagram of image segmentation for a display image provided in an embodiment of the present application, a display image 10 can be segmented into a plurality of sub-display images 11 , each of which is in a rectangular shape.

[0115] In other examples, the display image may also be divided into sub-display images of other shapes, such as circle, ellipse, polygon, etc. Those skilled in the art may make a selection according to needs and actual conditions, and there is no specific limitation.

[0116] Furthermore, when segmenting an image to obtain training samples, the shape of the segmented sub-display image can be determined according to the shape of the display panel, that is, the shape of the sub-display image can be consistent with the shape of the display panel, thereby further improving the accuracy of the model prediction and further improving the accuracy of the Demura technology.

[0117] In an optional embodiment, the neural network model is a convolutional neural network model, which includes a convolutional layer, a pooling layer and multiple fully connected layers.

[0118] Among them, taking into account that the edges of the display panel may be curved, and that there may be double data distortion after the body and lens of the image acquisition device are combined, the convolutional neural network is modified and adjusted in the embodiment of the present application to make the optimized convolutional neural network adapt to the prediction of pixel brightness compensation values.

[0119] Specifically, the present application determines the corresponding brightness compensation value for each pixel. In order to retain the characteristics of each pixel, only one convolution layer is set when constructing the convolutional neural network. The influence of the brightness of the surrounding pixels on the pixel is considered through the convolution calculation of one convolution layer. In order to further improve the adequacy of considering the influence of the brightness of the surrounding pixels on the pixel, the convolution kernel size of the convolution layer can be preferably set to 9*9.

[0120] Furthermore, in order to highlight the brightness characteristics of each pixel, the number of pooling layers is reduced, and only one pooling layer is set for dimensionality reduction processing. Preferably, the MR of the image acquisition device is ≥ 2, so that the captured display image can be processed by only one pooling layer to achieve dimensionality reduction, thereby preventing overfitting to a certain extent.

[0121] In other optional implementations, multiple convolutional layers may be provided between the pooling layer and the full-link layer. For example, the compensation model may include a pooling layer 101, multiple convolutional layers 102, and multiple full-link layers 103. Figure 7As shown, it is a schematic diagram of the structure of a compensation model provided in an embodiment of the present application. The compensation model 100 may include 4 convolutional layers, namely, a first convolutional layer 1021, a second convolutional layer 1022, a third convolutional layer 1023, and a fourth convolutional layer 1024. A convolutional layer, namely, the first convolutional layer 1021, is provided before the pooling layer 101; three sequentially connected convolutional layers, namely, the second convolutional layer 1022, the third convolutional layer 1023, and the fourth convolutional layer 1024, may be provided after the pooling layer 101; and three sequentially connected full-link layers 103 may be provided after the last convolutional layer (i.e., the fourth convolutional layer 1024).

[0122] The convolution layer before the pooling layer 101 (i.e., the first convolution layer 1021) is also called a filter layer, which is used to extract features from the input of the compensation model, i.e., to extract the ROI area. Considering the influence of the current pixel and the surroundings, as well as the influence of lens distortion, the convolution kernel size of the convolution layer before the pooling layer 101 can be larger than the convolution kernel size of the convolution layer after the pooling layer 101. Figure 7 Taking the structure of the compensation model shown as an example, the convolution kernel size of the first convolution layer 1021 can be 9*9, and the convolution kernel sizes of the second convolution layer 1022, the third convolution layer 1023 and the fourth convolution layer 1024 can all be 5*5. The convolution kernel size is determined according to the actual fitting situation and is not limited here.

[0123] It should be noted that Figure 7 The structure of the compensation model shown in the figure is only a preferred example. Those skilled in the art can adjust the number and position of the pooling layer 101, the convolution layer 102 and the full connection layer 103 as needed, and this application does not make any specific limitation.

[0124] In an optional embodiment, the method also includes, after compensating the brightness of the display panel, re-shooting the actual display image to calculate the brightness compensation value, and through multi-frequency brightness compensation, the final display panel can successfully display the predetermined gray scale, ensuring that the display effect after compensation meets the expectations.

[0125] In a specific example, it is necessary to perform brightness compensation on the display panel of a predetermined grayscale of 64, and the brightness compensation value of each pixel is predicted by a corresponding compensation model. The current or voltage displayed by the pixel of the display panel is adjusted based on the brightness compensation value so that the display panel actually displays an image of grayscale 64. Since the actual display effect after brightness compensation may still be affected by various factors, the display parameters can be detected after the actual display image is photographed again after brightness compensation. If there are still pixels on the display panel that fail to successfully display an image of grayscale 64 after brightness compensation, for example, the brightness value of the actual displayed image is the brightness value of grayscale 62, then the step of calling the corresponding compensation model to predict the brightness compensation value of the pixel that failed to successfully display the predetermined grayscale and performing brightness compensation on each pixel of the display panel is re-executed. The above brightness compensation steps are repeated until all pixels of the display panel successfully display the predetermined grayscale. Through this real-time interactive continuous compensation, the entire display panel reaches the predetermined grayscale display and the mura phenomenon is eliminated.

[0126] After the compensation model provided in the embodiment of the present application is used to perform brightness compensation on the display panel, the effect of brightness compensation can be significantly improved. Figures 8a to 8d As shown, it is a comparison diagram of the effects provided by the embodiments of the present application, from Figures 8a to 8d It can be seen that the trained compensation model is used to calibrate and compensate the brightness of the display panel, whether it needs to be compensated to 64 grayscales (reference Figure 8a ), or 32 grayscale (reference Figure 8b ), or 16 grayscale (reference Figure 8c ) or 8 grayscale (reference Figure 8d ), and its effect is obviously better than the compensation effect of the traditional algorithm in the prior art.

[0127] In summary, the compensation model of the present application fully considers the different display brightness of each pixel on the display panel, the interference of the display brightness of the pixels collected on the display image by the display brightness of the surrounding pixels, and the exposure time and lens distortion of the image acquisition device when shooting. The compensation model obtained by training the neural network model with the training sample set can determine the brightness compensation value for each pixel separately, eliminate the influencing factors of the brightness compensation value required for calculating the display panel to successfully display the predetermined grayscale, obtain accurate brightness compensation value, improve the accuracy of the determined brightness compensation value, and thus improve the compensation accuracy. The present application also adopts real-time signal interaction and dynamic compensation mechanism, continuously acquires the image to be tested, and continuously performs compensation training to ensure that the compensation can adapt to the changes in the device state in real time, and improve the practicality and effect of compensation. The samples in the present application involve multiple grayscales, which can more accurately capture and process different types of Mura phenomena, surpassing the processing capabilities of traditional algorithms, especially in the processing of low grayscale Mura.

[0128] Based on the same principle, the embodiment of the present application also discloses a display panel brightness compensation method. Fig. 9 As shown, in this embodiment, the method includes:

[0129] S410: obtaining display parameters by photographing an actual display image of a predetermined gray scale displayed by a display panel through an image acquisition device.

[0130] S420: Inputting the display parameters into a pre-trained compensation model to obtain a brightness compensation value corresponding to each pixel in the display panel.

[0131] S430: Performing brightness compensation on the display panel according to the brightness compensation value corresponding to each pixel.

[0132] In an optional implementation manner, the step S420 of inputting the display parameters into a pre-trained compensation model includes:

[0133] S421: Determine a model label corresponding to the display parameter of the display panel, wherein the model label includes a predetermined gray scale and / or area.

[0134] S422: Obtain a pre-trained compensation model corresponding to the model label.

[0135] S423: Input the display parameters into the corresponding compensation model.

[0136] Based on the same principle, the embodiment of the present application also discloses a device for constructing a display panel brightness compensation model. Fig.10 As shown, in this embodiment, the device includes a data acquisition module 1 and a model training module 2.

[0137] The data acquisition module 1 is used to determine a training sample set, which includes display parameters and corresponding target display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale through an image acquisition device.

[0138] The model training module 2 is used to input the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, and the compensation model is used to predict the brightness compensation value of each pixel on the display panel based on the display parameters of the display panel.

[0139] Since the principle of solving the problem by the device is similar to that of the above method, the implementation of the device can refer to the implementation of the method and will not be repeated here.

[0140] Based on the same principle, the embodiment of the present application also discloses a display panel brightness compensation device. Fig.11As shown, in this embodiment, the device includes a data acquisition module 3, a model determination module 4 and a brightness compensation module 5.

[0141] The data acquisition module 3 is used to obtain display parameters by photographing an actual display image of a predetermined gray scale displayed by the display panel through an image acquisition device.

[0142] The model determination module 4 is used to input the display parameters into a pre-trained compensation model to obtain a brightness compensation value corresponding to each pixel in the display panel.

[0143] The brightness compensation module 5 is used to perform brightness compensation on the display panel according to the brightness compensation value corresponding to each pixel.

[0144] Since the principle of solving the problem by the device is similar to that of the above method, the implementation of the device can refer to the implementation of the method and will not be described in detail here.

[0145] Based on the same principle, the embodiment of the present application also discloses a display panel brightness compensation system, which includes a display panel, an image acquisition device, a display panel brightness compensation model construction device as described in the embodiment, and a display panel brightness compensation device as described in the embodiment.

[0146] Since the principle of solving the problem by this system is similar to that of the above method and device, the implementation of this system can refer to the implementation of the method and device, which will not be repeated here.

[0147] An embodiment of the present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0148] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0149] Those skilled in the art should understand that the embodiments of the present application can be provided as methods, systems, or computer programs to produce the systems, devices, modules or units described in the above embodiments, which can be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer device, and specifically, the computer device can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0150] In a typical example, the computer device specifically includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the method executed by the client as described above is implemented; or, when the processor executes the program, the method executed by the server as described above is implemented.

[0151] Reference below Fig.12 , which shows a schematic diagram of the structure of a computer device 600 suitable for implementing an embodiment of the present application.

[0152] like Fig.12 As shown, the computer device 600 includes a central processing unit (CPU) 601, which can perform various appropriate tasks and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 to a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other through a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0153] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal feedback device (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 606 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed as needed as the storage section 608.

[0154] In particular, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program tangibly contained on a machine-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 609, and / or installed from a removable medium 611.

[0155] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0156] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0157] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0158] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0159] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0160] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0161] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0162] The present application may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0163] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0164] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for constructing a display panel brightness compensation model, characterized in that: include: Determine a training sample set, wherein the training sample set includes display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale by an image acquisition device and corresponding target display parameters; Inputting the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, wherein the compensation model is used to predict a brightness compensation value of each pixel on the display panel based on display parameters of the display panel; The target display parameter is a display parameter corresponding to a target display image obtained by photographing the display panel by an image acquisition device when each pixel of the display panel successfully displays the predetermined grayscale; or The target display parameters are target brightness compensation values ​​for each pixel on the display panel obtained based on display parameters obtained by photographing an actual display image of a predetermined gray scale displayed on the display panel through an image acquisition device and display parameters corresponding to a target display image of the predetermined gray scale displayed on the display panel through an image acquisition device.

2. The method according to claim 1, characterized in that The display parameters include position information of each data point on the actual display image corresponding to each pixel of the display panel and the corresponding brightness value; The target display parameters are display parameters corresponding to the target display image obtained by photographing the display panel with an image acquisition device when each pixel of the display panel successfully displays the predetermined grayscale. The target display parameters include position information and corresponding brightness values ​​of each pixel of the display panel corresponding to the target display image.

3. The method according to claim 1, characterized in that The display parameters of the training sample set and the target display parameters also include the predetermined gray scale.

4. The method according to claim 1, characterized in that: The step of inputting the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model comprises: Dividing the training sample set into training samples and verification samples; Inputting the training samples into a pre-built neural network model to train the neural network model to obtain a preliminary model; Determine, by using the verification sample, an error value between a brightness compensation value of each pixel in the display panel predicted by the preliminary model and a target brightness compensation value; When the error value does not satisfy the training stop condition, the steps of adjusting the weight coefficient of the preliminary model and using the training sample set to train the preliminary model with the adjusted weight coefficient are repeated until the error value satisfies the training stop condition to obtain the compensation model.

5. The method according to claim 4, characterized in that The training stop condition is that the error value is less than a preset threshold; The error value is obtained by: Wherein, MSE is the error value; m is the total number of rows of pixels in the display panel; n is the total number of columns of pixels in the display panel; i is the row number of the current pixel in the display panel; j is the column number of the current pixel in the display panel; A brightness compensation value predicted for a current pixel in the display panel; is the target brightness compensation value of the current pixel in the display panel.

6. The method according to claim 1, characterized in that The display panel includes a plurality of regions obtained by pixel division, the training sample set includes a regional training sample set corresponding to each of the regions, the compensation model is a regional compensation model corresponding to each of the regions, and the regional training sample set is obtained by the following steps: Using an image acquisition device to capture an actual display image of a predetermined gray scale displayed on the display panel; Extracting the display parameters of the actual display image corresponding to each of the regions to obtain the regional display parameters; Determine the regional target display parameters corresponding to the regional display parameters of each of the regions, and obtain the regional training sample set based on the regional display parameters and the regional target display parameters.

7. The method according to claim 1, characterized in that The neural network model is a convolutional neural network model, which includes a convolutional layer, a pooling layer and multiple fully connected layers.

8. The method according to claim 1, characterized in that: The MR of the image acquisition device is ≥2, and the MR is the ratio of the data points of the image captured by the image acquisition device to the number of pixels of the display panel.

9. A display panel brightness compensation method, characterized in that: include: The display parameters are obtained by photographing an actual display image of a predetermined gray scale displayed on a display panel by an image acquisition device; Inputting the display parameters into a pre-trained compensation model to obtain a brightness compensation value corresponding to each pixel in the display panel; Performing brightness compensation on the display panel according to the brightness compensation value corresponding to each pixel; The method for constructing the compensation model includes: Determine a training sample set, wherein the training sample set includes display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale by an image acquisition device and corresponding target display parameters; Inputting the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, wherein the compensation model is used to predict a brightness compensation value of each pixel on the display panel based on display parameters of the display panel; The target display parameter is a display parameter corresponding to a target display image obtained by photographing the display panel by an image acquisition device when each pixel of the display panel successfully displays the predetermined grayscale; or The target display parameters are target brightness compensation values ​​for each pixel on the display panel obtained based on display parameters obtained by photographing an actual display image of a predetermined gray scale displayed on the display panel through an image acquisition device and display parameters corresponding to a target display image of the predetermined gray scale displayed on the display panel through an image acquisition device.

10. A display panel brightness compensation model construction device, characterized in that: include: A data acquisition module, used to determine a training sample set, wherein the training sample set includes display parameters and corresponding target display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale through an image acquisition device; A model training module, used for inputting the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, wherein the compensation model is used for predicting a brightness compensation value of each pixel on the display panel based on display parameters of the display panel; The target display parameter is a display parameter corresponding to a target display image obtained by photographing the display panel by an image acquisition device when each pixel of the display panel successfully displays the predetermined grayscale; or The target display parameters are target brightness compensation values ​​for each pixel on the display panel obtained based on display parameters obtained by photographing an actual display image of a predetermined gray scale displayed on the display panel through an image acquisition device and display parameters corresponding to a target display image of the predetermined gray scale displayed on the display panel through an image acquisition device.

11. A display panel brightness compensation device, characterized in that: include: A display panel brightness compensation model construction device, the device comprising: A data acquisition module, used to determine a training sample set, wherein the training sample set includes display parameters and corresponding target display parameters obtained by photographing an actual display image of a display panel displaying a predetermined gray scale through an image acquisition device; A model training module, used for inputting the training sample set into a pre-built neural network model to train the neural network model to obtain a trained compensation model, wherein the compensation model is used for predicting a brightness compensation value of each pixel on the display panel based on display parameters of the display panel; The display panel brightness compensation device comprises: A data acquisition module, used for obtaining display parameters by photographing an actual display image of a predetermined gray scale displayed by the display panel through an image acquisition device; A model determination module, used for inputting the display parameters into a pre-trained compensation model to obtain a brightness compensation value corresponding to each pixel in the display panel; A brightness compensation module, used to perform brightness compensation on the display panel according to the brightness compensation value corresponding to each pixel; The target display parameter is a display parameter corresponding to a target display image obtained by photographing the display panel by an image acquisition device when each pixel of the display panel successfully displays the predetermined grayscale; or The target display parameters are target brightness compensation values ​​for each pixel on the display panel obtained based on display parameters obtained by photographing an actual display image of a predetermined gray scale displayed on the display panel through an image acquisition device and display parameters corresponding to a target display image of the predetermined gray scale displayed on the display panel through an image acquisition device.

Images