Brightness compensation method, device, storage medium and electronic device

Abstract

The present application discloses a brightness compensation method, device, storage medium, and electronic device, wherein the brightness compensation method includes shooting an initial MURA distribution image of a display screen; using an image classification model to identify and classify the initial MURA distribution image to obtain a classification result; according to the classification result, configuring the corresponding optimal shooting parameters and performing at least one exposure acquisition on the display screen to obtain an image set containing one or more exposure images; then, based on the classification result, fusing the image set to generate a target brightness image; comparing the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map; finally, selecting the corresponding optimal compensation parameter set according to the classification result, and performing brightness compensation on the display screen based on the compensation parameter set and the pixel brightness deviation map. The embodiments of the present application can solve the problem of uneven pixel brightness caused by manufacturing process fluctuations on different screens.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of display technology, and specifically to a brightness compensation method, device, storage medium, and electronic device. Background Art

[0002] With the rapid development of electronic products and mobile terminals, flat panel displays are widely used in smart phones, tablets, laptops, TVs, industrial equipment and other fields. High resolution, high refresh rate and comfortable visual experience have become the goals that display technology continues to pursue.

[0003] However, during mass production, subtle variations in panel manufacturing processes, driver circuit consistency, backlight module (BMU) performance, and component performance often lead to uneven pixel brightness across different areas, a phenomenon commonly known as "uneven brightness" or "MURA." This defect is particularly noticeable in dark and mid-gray images, impacting not only visual perception but also potentially negatively impacting user perception of product quality and ultimately affecting the market competitiveness of the final product. Summary of the Invention

[0004] The embodiments of the present application provide a brightness compensation method, device, storage medium, and electronic device, which can solve the problem of uneven pixel brightness caused by fluctuations in the manufacturing process of different screens.

[0005] In a first aspect, an embodiment of the present application provides a brightness compensation method, comprising:

[0006] Take the initial MURA distribution image of the display screen;

[0007] Using an image classification model to identify and classify the initial MURA distribution image to obtain a classification result;

[0008] According to the classification result, configuring corresponding optimal shooting parameters and performing at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images;

[0009] Then, based on the classification result, the image set is fused to generate a target brightness image;

[0010] Comparing the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map;

[0011] Finally, a corresponding optimal compensation parameter set is selected according to the classification result, and brightness compensation is performed on the display screen based on the compensation parameter set and the pixel brightness deviation map.

[0012] In the brightness compensation method provided in the embodiment of the present application, fusing the image set to generate a target brightness image includes:

[0013] For a pixel at the same pixel position in each exposure image in the image set, determining a brightness range in which a brightness value of the pixel lies;

[0014] According to the judgment result, a corresponding weight value is assigned to each pixel of the exposure image;

[0015] The image set is fused according to the weight value to generate a target brightness image.

[0016] In the brightness compensation method provided in the embodiment of the present application, fusing the image set according to the weight value to generate a target brightness image includes:

[0017] For pixels at the same pixel position in each exposure image, performing a weighted average of their brightness values ​​and the corresponding weight values ​​to obtain a fused brightness value of the pixel;

[0018] The fused brightness value is mapped back to the same brightness range as the exposure image, and a final target brightness image is output.

[0019] In the brightness compensation method provided in the embodiment of the present application, the target brightness image is compared with the theoretical brightness image to generate a pixel brightness deviation map, including:

[0020] Respectively obtain the target brightness value and the theoretical brightness value of the pixel corresponding to each pixel position of the target brightness image and the theoretical brightness image;

[0021] Comparing the target brightness value with the theoretical brightness value to obtain a brightness deviation value for each pixel;

[0022] A pixel brightness deviation map is generated based on the brightness deviation values.

[0023] In the brightness compensation method provided in the embodiment of the present application, generating a pixel brightness deviation map based on the brightness deviation value includes:

[0024] Combining the brightness deviation values ​​into a brightness deviation matrix;

[0025] Perform median filtering on the brightness deviation matrix to obtain a pixel brightness deviation map.

[0026] In the brightness compensation method provided in an embodiment of the present application, the compensation parameter set includes a gain adjustment coefficient, a local filter radius, a noise suppression strength, and a brightness mapping mode. The brightness compensation of the display screen based on the compensation parameter set and the pixel brightness deviation map includes:

[0027] performing local filtering on the pixel brightness deviation map using the local filtering radius and the noise suppression strength;

[0028] Brightness compensation is performed on the display screen based on the brightness mapping method, each brightness deviation value in the filtered pixel brightness deviation map, and the gain adjustment coefficient.

[0029] In the brightness compensation method provided in an embodiment of the present application, the brightness compensation of the display screen based on the brightness mapping mode, each brightness deviation value in the filtered pixel brightness deviation map, and the gain adjustment coefficient includes:

[0030] Inputting each brightness deviation value in the filtered pixel brightness deviation map into the brightness mapping method to obtain a compensation gain for each pixel;

[0031] Combining the compensation gain with the original brightness value of the corresponding pixel according to the gain adjustment coefficient to generate a compensated pixel brightness value;

[0032] The compensated pixel brightness values ​​of all pixels are sent to the display screen through the display driver interface to achieve real-time brightness uniformity compensation.

[0033] In a second aspect, an embodiment of the present application provides a brightness compensation device, including:

[0034] A shooting unit, used for shooting an initial MURA distribution image of the display screen;

[0035] A classification unit, configured to identify and classify the initial MURA distribution image using an image classification model to obtain a classification result;

[0036] an acquisition unit, configured to configure corresponding optimal shooting parameters according to the classification result and perform at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images;

[0037] a fusion unit, configured to fuse the image set according to the classification result to generate a target brightness image;

[0038] a comparing unit, configured to compare the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map;

[0039] A compensation unit is configured to select a corresponding optimal compensation parameter set according to the classification result, and perform brightness compensation on the display screen based on the compensation parameter set and the pixel brightness deviation map.

[0040] In a third aspect, the present application provides a storage medium storing a plurality of instructions, wherein the instructions are suitable for loading by a processor to execute any of the brightness compensation methods described above.

[0041] In a fourth aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-described brightness compensation methods when executing the computer program.

[0042] In summary, the brightness compensation method provided in the embodiment of the present application includes capturing an initial MURA distribution image of a display screen; using an image classification model to identify and classify the initial MURA distribution image to obtain a classification result; based on the classification result, configuring the corresponding optimal shooting parameters and performing at least one exposure acquisition on the display screen to obtain an image set containing one or more exposure images; then, based on the classification result, fusing the image set to generate a target brightness image; comparing the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map; finally, selecting the corresponding optimal compensation parameter set based on the classification result, and performing brightness compensation on the display screen based on the compensation parameter set and the pixel brightness deviation map. The embodiment of the present application can dynamically select the most appropriate measurement and compensation strategy for MURA defects caused by different batches and different process fluctuations through the process of "first classification → then adaptive acquisition → then pixel-level compensation". The classification stage differentiates the severity of uneven brightness displayed on the screen and the image form presented by MURA. Adaptive multi-exposure solves the measurement accuracy issue, and the adaptive parameter set ensures that the compensation algorithm produces optimal results for MURA of different severities and different image forms, effectively solving the problem of uneven pixel brightness caused by fluctuations in the manufacturing process on different screens. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0044] Figure 1 This is a schematic diagram of an application scenario of the brightness compensation method provided in an embodiment of the present application.

[0045] Figure 2 It is a flowchart of the brightness compensation method provided in an embodiment of the present application.

[0046] Figure 3 Schematic diagram of the structure of the brightness compensation device provided in an embodiment of the present application.

[0047] Figure 4 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] Exemplary embodiments will be described in detail herein, with examples illustrated in the accompanying drawings. In the following description, when referring to the drawings, identical numerals in different figures represent identical or similar elements, unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.

[0049] It should be noted that, in this document, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising 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, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. In addition, components, features, and elements with the same name in different embodiments of the present application may have the same meaning or different meanings, and their specific meanings need to be determined by their explanation in the specific embodiment or further combined with the context of the specific embodiment.

[0050] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0051] In the subsequent description, the use of suffixes such as "module", "component" or "unit" to represent elements is only for the purpose of facilitating the description of the present application and has no specific meaning. Therefore, "module", "component" or "unit" can be used interchangeably.

[0052] In the description of this application, it should be noted that the terms "upper," "lower," "left," "right," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate the description of this application and simplify the description. They are not intended to indicate or imply that the devices or components referred to must have a specific orientation, be constructed, or operate in a specific orientation. Therefore, they should not be construed as limitations on this application. Furthermore, terms such as "first" and "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0053] During mass production, subtle variations in panel manufacturing processes, driver circuit consistency, backlight module (BMU) and component performance often lead to uneven pixel brightness across different areas, a phenomenon commonly known as "uneven brightness" or "MURA." This defect is particularly noticeable in dark and mid-gray images, impacting not only visual perception but also potentially negatively impacting user perception of product quality and even compromising the market competitiveness of the final product.

[0054] Based on this, the embodiments of the present application provide a brightness compensation method, device, storage medium and electronic device. Specifically, the brightness compensation device can be integrated into an electronic device, which can be a server or a terminal; wherein the terminal can include a mobile phone, a wearable smart device, a tablet computer, a laptop computer, and a personal computer (PC); the server can be a single server or a server cluster composed of multiple servers, and can be a physical server or a virtual server.

[0055] For example, Figure 1 As shown, the electronic device can capture an initial MURA distribution image of a display screen through a camera; then use an image classification model to identify and classify the initial MURA distribution image to obtain a classification result; based on the classification result, configure the corresponding optimal shooting parameters and perform at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images; then, based on the classification result, fuse the image set to generate a target brightness image; compare the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map; finally, select the corresponding optimal compensation parameter set based on the classification result, and perform brightness compensation on the display screen based on the compensation parameter set and the pixel brightness deviation map.

[0056] The following will describe the technical solutions of this application in detail through specific embodiments. It should be noted that the order of description of the following embodiments does not limit the priority order of the embodiments.

[0057] See also Figure 2 , Figure 2 : is a flow chart of the brightness compensation method provided in the embodiment of the present application. The specific process of the brightness compensation method can be as follows:

[0058] 101. Capture an initial MURA distribution image of the display screen.

[0059] In some embodiments, the display screen can be turned on before shooting, and allowed to continuously display standard test signals (such as pure red, pure green, pure blue, and pure white) for 10 seconds each to allow the panel to fully preheat and reach a stable operating temperature. The preheating time is generally no less than 5 minutes.

[0060] After the warm-up is complete, set the full-screen input in the display driver to a 50% grayscale signal (i.e., a numerical code of approximately 8-bit grayscale value 128) to ensure that the brightness of each pixel on the screen is within the middle brightness range. Wait about 2 seconds for the brightness of all pixels on the display to stabilize to the stable value corresponding to 50% grayscale.

[0061] After the display is stable at 50% grayscale, you can perform a pre-capture with the camera to obtain the initial MURA distribution image of the display. This initial MURA distribution image can then be saved as an uncompressed 8-bit grayscale image (.tiff or .raw format), along with metadata such as the ambient temperature, capture time, camera serial number, lens focal length, exposure time, and gain.

[0062] After the initial MURA distribution image is obtained, image preprocessing may be performed on it to obtain a preprocessed initial MURA distribution image.

[0063] Specifically, a 3×3 window median filter operator (each pixel takes the median of the grayscale values ​​of its surrounding 3×3 neighborhood as the output) can be used to perform median filtering denoising on the initial MURA distribution image to effectively suppress single-point noise and salt-and-pepper noise, thereby obtaining the denoised initial MURA distribution image.

[0064] Finally, the grayscale values ​​of the denoised initial MURA distribution image are linearly normalized, and the pixel values ​​are linearly mapped from the original 0 to 255 to 0.0 to 1.0 to obtain the normalized initial MURA distribution image.

[0065] 102. Use the image classification model to identify and classify the initial MURA distribution image to obtain the classification result.

[0066] It's understandable that this image classification model is pre-trained. Specifically, multiple sets of display screen images from different batches and at different brightness levels (e.g., 50% grayscale, 70% grayscale, etc.) are collected. Each pre-processed initial MURA distribution image is then visually inspected or tested using specialized instrumentation to determine the MURA defect level, classifying it into four categories: no unevenness, mild unevenness, moderate unevenness, and severe unevenness. It's important to ensure a balanced sample size across the four categories, with at least 2,000 images per category, for a total of approximately 8,000 training samples. 20% of the data is retained as validation and test sets.

[0067] In some embodiments, the image classification module can be trained as a lightweight convolutional neural network (CNN), such as MobileNetV2 or a customized small ResNet variant.

[0068] This image classification model includes an input layer, a first convolutional layer, a depthwise separable convolutional layer, a global average pooling layer, a fully connected layer, and a softmax layer. The first convolutional layer has a kernel size of 3×3, a stride of 1, and 16 output channels, followed by batch normalization (BatchNorm) and ReLU. The depthwise separable convolutional layer consists of two layers, each with 32 and 64 output channels, respectively, both followed by BatchNorm and ReLU. The global average pooling layer aggregates intermediate feature maps into a vector with a length equal to the number of channels. The fully connected layer has an input feature length of 64 and outputs four neurons, corresponding to the four MURA rating categories. The softmax layer maps the four outputs into probability distributions, such as p0: the probability of "no imbalance"; p1: the probability of "mild imbalance"; p2: the probability of "moderate imbalance"; and p3: the probability of "severe imbalance."

[0069] The specific training process can refer to the existing model training, and the embodiments of this application will not describe them one by one.

[0070] It is understandable that when the pre-processed initial MURA distribution image is input into the image classification model to obtain p0, p1, p2, and p3, the "maximum probability value" strategy can be used. For example, if the maximum probability corresponds to p1, the classification result is "mild unevenness"; if it corresponds to p2, the classification result is "moderate unevenness", and so on.

[0071] 103. According to the classification result, configure corresponding optimal shooting parameters and perform at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images.

[0072] In the embodiment of the present application, a mapping relationship between the classification results and the shooting parameters is preset, and a set of shooting parameter combinations are pre-designed and verified for different MURA levels, including exposure time and corresponding sensor gain.

[0073] For example, if there is no unevenness (C=0), only one standard exposure is required: the exposure time is about 10ms and the gain (ISO) is about 100.

[0074] Slight unevenness (C=1): Again, only one exposure is needed, but the gain can be adjusted slightly (e.g. ISO 120) to capture slight differences in brightness.

[0075] Moderate unevenness (C=2): Use "double exposure." Short exposure: Approximately 5ms exposure time, ISO gain approximately 80, primarily used to capture details in highlights. Long exposure: Approximately 20ms exposure time, ISO gain approximately 160, primarily used to capture brightness information in shadows.

[0076] Severe unevenness (C=3): Triple exposure is used. Ultra-short exposure: approximately 3ms, gain approximately ISO 60, used to capture the brightest areas; medium exposure: approximately 12ms, gain approximately ISO 120, used for mid-brightness areas; ultra-long exposure: approximately 30ms, gain approximately ISO 240, used to capture deep shadows. The optimal combination of exposure time and gain can be determined through repeated offline testing based on the actual display brightness range and camera performance.

[0077] After obtaining the classification result C, if C=0 or C=1, only one exposure is configured: exposure time T1 and gain G1; if C=2, two sets of exposure parameters are configured in sequence: (T2 short, G2 short) and (T2 long, G2 long); if C=3, three sets of exposure parameters are configured in sequence: (T3 ultra-short, G3 ultra-short), (T3 medium, G3 medium), and (T3 ultra-long, G3 ultra-long).

[0078] After that, you can call the interface through the camera SDK to switch the camera to "manual mode" and write the exposure time, gain, and shutter speed parameters to the registers. This triggers an image acquisition, waits for the camera buffer to complete, and then saves the captured image as a single file (for example, in ".tiff" or ".raw" format).

[0079] For moderate or severe unevenness, repeat the following:

[0080] Set the camera parameters to the "short exposure / ultra-short exposure" parameter value, trigger and save the first image I_short;

[0081] Switch the camera parameters to the "long exposure / medium exposure" parameter value, trigger and save the second image I_mid;

[0082] If it is classified as severely uneven, switch the parameter to "super long exposure" and save the third image I_long;

[0083] It should be noted that the camera position must not be moved before and after each shot, and the same grayscale (50% grayscale) is maintained on the display to ensure that the brightness differences between the three images are only caused by the exposure parameters.

[0084] In some embodiments, image preprocessing may be performed on each exposure image in the image exposure set. The specific process is the same as the above-mentioned image preprocessing, and will not be described in detail in this embodiment.

[0085] 104. Based on the classification results, the image set is fused to generate a target brightness image.

[0086] Specifically, for the pixels at the same pixel position in each exposure image in the image set, we can first determine the brightness range in which the brightness value of the pixel lies; then, based on the judgment result, we assign corresponding weight values ​​to the pixels of each exposure image; finally, based on the weight values, we perform multiple exposure fusion on the image set to generate the target brightness image.

[0087] Among them, "based on the weight value, the image set is subjected to multiple exposure fusion to generate the target brightness image" can be specifically as follows: for the pixels at the same pixel position in each exposure image, its brightness value is weighted averaged with the corresponding weight value to obtain the fused brightness value of the pixel; the fused brightness value is mapped back to the same brightness range as the exposure image, and the final target brightness image is output.

[0088] During image preprocessing, the pixel brightness of all exposed images is normalized to a uniform range (e.g., 0.0–1.0, corresponding to darkest to brightest). To distinguish between the "intermediate brightness range" and the "extreme brightness range," a reasonable brightness threshold range is pre-set in the system parameters.

[0089] For example, the middle brightness range is defined as pixels with normalized brightness values ​​within the range of [0.1–0.9]. Values ​​below 0.1 or above 0.9 are considered "extreme brightness" and their corresponding weights should be appropriately reduced. This threshold range can be fine-tuned during offline debugging based on the actual panel brightness distribution to balance the fusion of bright and dark areas in images with different exposures.

[0090] In the specific implementation process, the normalized brightness value of the pixel at the same pixel position (x, y) of each exposure image in the image set can be read first:

[0091] L short (x,y): the brightness of the pixel at (x,y) in the short exposure image;

[0092] L mid (x,y): The brightness of the pixel at (x,y) in the medium exposure image (if any);

[0093] L long (x,y): The brightness of the pixel at (x,y) in the long exposure image.

[0094] For a pixel at the same pixel position in each exposure image in the image set, whether the brightness value of the pixel is in the middle brightness range can be determined as follows:

[0095] For example, if L i (x,y) satisfies 0.1≤L i If (x,y)≤0.9, the brightness value of the pixel is considered to be in the "middle brightness range"; otherwise, the brightness value of the pixel is considered to be in the "brightness edge area" (that is, too dark or too bright).

[0096] According to the judgment result, the corresponding weight value is assigned to each pixel of the exposure image as follows:

[0097] For example, if the brightness value of a pixel is in the middle brightness range, it is given a higher weight, which can be recorded as W i (x,y)=1.0;

[0098] If the brightness value of the pixel is in the brightness edge area, it is given a lower weight, such as W i (x,y)=0.1;

[0099] It should be noted that the weight value can be further optimized offline according to the actual panel characteristics, but the general principle is that the "pixels in the middle area" are fused first, and the "pixels in the edge area" are minimized to minimize their impact on the fusion result.

[0100] In addition, in the case of two exposure images, the following combinations are possible:

[0101] The same pixel of the two images is in the middle area: the weight of each is high;

[0102] One image is in the middle area and the other is in the edge area: the image in the middle area has a higher weight and the image in the edge area has a lower weight;

[0103] Both images are in the edge region: both are given low weights.

[0104] For the three exposure images, three sets of weight values ​​are judged and assigned respectively in the same way.

[0105] For each pixel at position (x, y), obtain its brightness value L in each exposure image. i (x,y) and the corresponding weight W i (x,y), where i can be "short", "mid", or "long".

[0106] Multiply the brightness value of each exposed image pixel by the corresponding weight, sum these weighted brightness values, and then divide them by the sum of the weights to obtain the fused brightness value of the pixel:

[0107] For example, if there are two exposure images, the fused brightness is:

[0108] Numerator part = W short (x,y)×L short (x,y)+W long (x,y)×L long (x,y);

[0109] Denominator = W short (x,y)+Wlong (x,y);

[0110] Fusion brightness value = numerator ÷ denominator.

[0111] For triple-exposure images, the fused brightness is calculated by dividing the sum of the three weighted brightnesses by the sum of the three weights. This effectively utilizes the more reliable brightness information of pixels in the "middle zone" while appropriately weakening the information of pixels that are too dark or overexposed, ensuring that the fused image performs well across all brightness ranges.

[0112] After the fusion is completed, the fused brightness of each pixel position is obtained within the normalized range [0.0–1.0]. After performing the above weighted fusion on the entire image, a normalized fused image with the same size as the original exposure image is generated.

[0113] Next, the fused brightness value needs to be converted back to a brightness representation range consistent with the original image. For example:

[0114] If the original exposure image is represented by 8-bit grayscale (0–255), the fused brightness of each pixel is multiplied by 255 and rounded to an integer brightness value between 0 and 255;

[0115] If the original exposure image represents physical brightness (e.g., in cd / m²), then multiply the normalized value by the corresponding maximum physical brightness and add the minimum physical brightness offset to obtain the physical brightness value;

[0116] The final result is a "target brightness image" that is consistent with the format and range of the original exposure image, which can be recorded as I fusion .

[0117] Will I fusionI _Save in the same file format as the original exposure image (such as ".tiff" or ".raw") and record the following metadata: the image is the fusion result; the exposure image file name used for weighted fusion and its corresponding weight value mapping; the upper and lower brightness limits used for normalization and denormalization; the image generation timestamp, operator or system identification, etc.

[0118] 105. Compare the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map.

[0119] Specifically, the target brightness value and theoretical brightness value of the pixel corresponding to each pixel position in the target brightness image and the theoretical brightness image can be obtained respectively; the target brightness value and the theoretical brightness value are compared to obtain the brightness deviation value of each pixel; and a pixel brightness deviation map is generated based on the brightness deviation value.

[0120] The step of “generating a pixel brightness deviation map based on the brightness deviation values” may specifically include: combining the brightness deviation values ​​into a brightness deviation matrix; and performing median filtering on the brightness deviation matrix to obtain the pixel brightness deviation map.

[0121] It should be noted that the theoretical brightness image refers to a reference image formed by the brightness distribution that each pixel of the display should ideally achieve under specified grayscale, driving conditions and environment, without considering real deviations such as manufacturing process, aging, and temperature drift.

[0122] 106. Finally, the best compensation parameter set is selected according to the classification result, and brightness compensation is performed on the display screen based on the compensation parameter set and the pixel brightness deviation map.

[0123] In the embodiment of the present application, during the offline debugging phase, corresponding compensation parameter sets are pre-configured for each of the four MURA levels (no unevenness / mild / moderate / severe). Each set of compensation parameter sets consists of four elements:

[0124] Gain adjustment coefficient (referred to as "gain coefficient"): used to control the overall strength of the compensation gain during the final adjustment;

[0125] Local filter radius (referred to as "filter radius"): used to determine the size of the value area when performing local smoothing on the deviation map;

[0126] Noise suppression strength (abbreviated as "noise strength"): used to adjust the smoothness during filtering. A larger value indicates stronger noise suppression.

[0127] Brightness mapping method (referred to as "mapping method"): The rule used to convert the deviation value into the compensation gain, such as linear mapping, logarithmic mapping, or piecewise curve mapping.

[0128] For example, in the system you can define:

[0129] No unevenness (C=0): Gain coefficient = 1.0; Filter radius = 1 pixel; Noise intensity = weak (for example, 0.5); Mapping method = linear mapping (deviation and compensation gain are one-to-one).

[0130] Mild non-uniformity (C=1): Gain factor = 1.2; Filter radius = 2 pixels; Noise intensity = Medium (e.g. 1.0); Mapping method = Linear mapping.

[0131] Moderate unevenness (C=2): Gain factor = 1.5; Filter radius = 3 pixels; Noise intensity = Strong (e.g. 1.5); Mapping method = Segmented curve (small deviations use a small slope, large deviations use a large slope).

[0132] Severe nonuniformity (C=3): Gain factor = 2.0; Filter radius = 5 pixels; Noise intensity = Maximum (e.g., 2.0); Mapping method = Logarithmic mapping (the mapping is more sensitive to large deviations).

[0133] These four sets of parameter sets are obtained through multiple sample panel tests in the offline stage, and the above parameter values ​​are stored in a configuration file or database for easy online loading.

[0134] That is, the compensation parameter set includes a gain adjustment coefficient, a local filter radius, a noise suppression strength, and a brightness mapping mode.

[0135] Specifically, the pixel brightness deviation map can be locally filtered using the local filtering radius and noise suppression strength; and the display screen is brightness compensated based on the brightness mapping method, each brightness deviation value in the filtered pixel brightness deviation map, and the gain adjustment coefficient.

[0136] For example, based on the "filter radius", a square neighborhood window of size (2R+1)×(2R+1) can be defined, where R is the loaded filter radius value (in pixels).

[0137] For example: if the filter radius = 3, the window size = 7×7; if the filter radius = 1, the window size = 3×3.

[0138] In some embodiments, local smoothing is performed by weighted averaging or Gaussian weighting. To better preserve regional edge information, this embodiment uses "weighted Gaussian filtering."

[0139] In the "weighted Gaussian filter", the closer the point is to the center pixel in the neighborhood, the higher the weight. Specifically, a Gaussian template of size (2R+1)×(2R+1) can be used for weighting.

[0140] "Noise Strength" determines the standard deviation (σ) of the Gaussian template. A larger standard deviation results in a more pronounced smoothing effect; a smaller standard deviation results in a filter closer to the mean but better detail preservation.

[0141] In some embodiments, each brightness deviation value in the filtered pixel brightness deviation map can be input into a brightness mapping method to obtain a compensation gain for each pixel; based on a gain adjustment coefficient, the compensation gain is combined with the original brightness value of the corresponding pixel to generate a compensated pixel brightness value; the compensated pixel brightness values ​​of all pixels are sent to the display screen through a display driver interface to achieve real-time brightness uniformity compensation.

[0142] It is understood that the final compensation gain can be obtained by multiplying the gain adjustment coefficient by the compensation gain, and the final compensation gain is combined with the original brightness value of the corresponding pixel to generate the compensated pixel brightness value.

[0143] The final compensation gain can be combined with the original brightness value of the corresponding pixel in an "accumulation" or "product" manner. This embodiment adopts the "product" manner, that is, the original brightness is amplified when the deviation is positive and the original brightness is reduced when the deviation is negative.

[0144] In summary, the brightness compensation method provided by the embodiment of the present application includes shooting the initial MURA distribution image of the display screen; using the image classification model to identify and classify the initial MURA distribution image to obtain a classification result; according to the classification result, configuring the corresponding optimal shooting parameters and performing at least one exposure acquisition on the display screen to obtain an image set containing one or more exposure images; then based on the classification result, fusing the image set to generate a target brightness image; comparing the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map; finally, selecting the corresponding optimal compensation parameter set based on the classification result, and performing brightness compensation on the display screen based on the compensation parameter set and the pixel brightness deviation map. The embodiment of the present application can dynamically select the most appropriate measurement and compensation strategy for MURA defects caused by different batches and different process fluctuations through the process of "first classification → then adaptive acquisition → then pixel-level compensation". The classification stage distinguishes the severity of screen unevenness, adaptive multi-exposure solves the measurement accuracy problem, and the adaptive parameter set ensures that the compensation algorithm can produce the best effect for different levels of MURA, thereby effectively solving the problem of pixel brightness unevenness caused by manufacturing process fluctuations on different screens.

[0145] To facilitate better implementation of the brightness compensation method provided in the embodiment of the present application, the embodiment of the present application also provides a brightness compensation device, wherein the meanings of the terms are the same as those in the above brightness compensation method, and the specific implementation details can be referred to the description in the method embodiment.

[0146] See also Figure 3 , Figure 3 Schematic diagram of the structure of the brightness compensation device provided by the embodiment of the present application. The brightness compensation device may include a shooting unit 201, a classification unit 202, a collection unit 203, a fusion unit 204, a comparison unit 205 and a compensation unit 206.

[0147] A shooting unit 201 is used to shoot an initial MURA distribution image of the display screen;

[0148] The classification unit 202 is configured to identify and classify the initial MURA distribution image of the display screen using an image classification model based on the initial MURA distribution image to obtain a classification result;

[0149] The acquisition unit 203 is configured to configure corresponding optimal shooting parameters according to the classification result and perform at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images;

[0150] A fusion unit 204 is configured to fuse the image set according to the classification result to generate a target brightness image;

[0151] A comparison unit 205 is used to compare the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map;

[0152] The compensation unit 206 is configured to select a corresponding optimal compensation parameter set according to the classification result, and perform brightness compensation on the display screen based on the compensation parameter set and the pixel brightness deviation map.

[0153] The specific implementation of each of the above units can be found in the above embodiment of the brightness compensation method, and will not be described in detail here.

[0154] In summary, the brightness compensation device provided in the embodiments of the present application can capture an initial MURA distribution image of a display screen via a capture unit 201; a classification unit 202 uses an image classification model to identify and classify the initial MURA distribution image of the display screen based on the initial MURA distribution image to obtain a classification result; an acquisition unit 203 configures the corresponding optimal capture parameters based on the classification result and performs at least one more exposure acquisition on the display screen to obtain an image set containing one or more exposure images; a fusion unit 204 fuses the image set based on the classification result to generate a target brightness image; a comparison unit 205 compares the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map; and a compensation unit 206 selects the corresponding optimal compensation parameter set based on the classification result and performs brightness compensation on the display screen based on the compensation parameter set and the pixel brightness deviation map. Through the "classification → adaptive acquisition → pixel-level compensation" process, the embodiments of the present application can dynamically select the most appropriate measurement and compensation strategy for MURA defects caused by different batches and process fluctuations. The classification stage differentiates the severity of uneven brightness across the display and the image type presented by MURA. Adaptive multi-exposure solves measurement accuracy issues, and the adaptive parameter set ensures the compensation algorithm produces optimal results for MURA of varying severity and image types, effectively addressing uneven pixel brightness across different displays caused by manufacturing process fluctuations.

[0155] The embodiment of the present application further provides an electronic device, in which the brightness compensation device of the embodiment of the present application can be integrated, such as Figure 4 , which shows a schematic diagram of the structure of the electronic device involved in the embodiment of the present application, specifically:

[0156] The electronic device may include one or more processing core processors 301 and one or more computer readable storage media memories 302 and other components. Those skilled in the art will understand that Figure 4 The electronic device structure shown in the figure does not constitute a limitation of the electronic device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0157] The processor 301 is the control center of the electronic device. It connects the various parts of the entire electronic device using various interfaces and lines. By running or executing the software programs and / or this application stored in the memory 302, and calling the data stored in the memory 302, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operation of storage media, user interface and application programs, etc., and the modem processor mainly handles wireless communication. It is understandable that the above-mentioned modem processor may not be integrated into the processor 301.

[0158] The memory 302 can be used to store software programs and the present application. The processor 301 executes various functional applications and data processing by running the software programs and the present application stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area, wherein the program storage area may store operating storage media, applications required for at least one function, etc.; the data storage area may store data created based on the use of the electronic device, etc. In addition, the memory 302 may include a high-speed random access memory and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0159] Although not shown, the electronic device may further include a display unit, an input unit, a power supply, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302 to implement various functions as follows:

[0160] Take the initial MURA distribution image of the display screen;

[0161] Based on the initial MURA distribution image, the image classification model is used to identify and classify the initial MURA distribution image of the display screen to obtain the classification result;

[0162] According to the classification result, configuring corresponding optimal shooting parameters and performing at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images;

[0163] Fuse the image set to generate the target brightness image;

[0164] Compare the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map;

[0165] A corresponding compensation parameter set is selected according to the classification result, and brightness compensation is performed on the display screen based on the compensation parameter set and the pixel brightness deviation map.

[0166] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0167] To this end, an embodiment of the present application provides a storage medium storing a plurality of instructions that can be loaded by a processor to execute the steps of any of the methods provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0168] Take the initial MURA distribution image of the display screen;

[0169] Based on the initial MURA distribution image, the image classification model is used to identify and classify the initial MURA distribution image of the display screen to obtain the classification result;

[0170] According to the classification result, configuring corresponding optimal shooting parameters and performing at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images;

[0171] Fuse the image set to generate the target brightness image;

[0172] Compare the target brightness image with the theoretical brightness image to generate a pixel brightness deviation map;

[0173] A corresponding compensation parameter set is selected according to the classification result, and brightness compensation is performed on the display screen based on the compensation parameter set and the pixel brightness deviation map.

[0174] The specific implementation of the above operations can be found in the previous embodiments and will not be repeated here.

[0175] The storage medium may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0176] Since the instructions stored in the storage medium can execute the steps in any method provided in the embodiments of the present application, the beneficial effects that can be achieved by any method provided in the embodiments of the present application can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0177] The brightness compensation method, device, storage medium, and electronic device provided by the present application are respectively introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the core idea of ​​the present application. At the same time, for those skilled in the art, according to the idea of ​​the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present application.

Claims

1. A brightness compensation method, characterized in that: include: Take the initial MURA distribution image of the display screen; Using an image classification model to identify and classify the initial MURA distribution image to obtain a classification result; According to the classification result, configuring corresponding optimal shooting parameters and performing at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images; Then, based on the classification result, the image set is fused to generate a target brightness image; Respectively obtain the target brightness value and the theoretical brightness value of the pixel corresponding to each pixel position of the target brightness image and the theoretical brightness image; Comparing the target brightness value with the theoretical brightness value to obtain a brightness deviation value for each pixel; Combining the brightness deviation values ​​into a brightness deviation matrix; Performing median filtering on the brightness deviation matrix to obtain a pixel brightness deviation map; Finally, the corresponding optimal compensation parameter set is selected according to the classification result, and the compensation parameter set includes a gain adjustment coefficient, a local filtering radius, a noise suppression strength and a brightness mapping method; the pixel brightness deviation map is locally filtered using the local filtering radius and the noise suppression strength; and the display screen is brightness compensated based on the brightness mapping method, each brightness deviation value in the filtered pixel brightness deviation map and the gain adjustment coefficient.

2. The brightness compensation method according to claim 1, wherein: The step of fusing the image set based on the classification result to generate a target brightness image includes: For a pixel at the same pixel position in each exposure image in the image set, determining a brightness range in which a brightness value of the pixel lies; According to the judgment result, a corresponding weight value is assigned to each pixel of the exposure image; The image set is fused according to the weight value to generate a target brightness image.

3. The brightness compensation method according to claim 2, wherein: The step of fusing the image set according to the weight value to generate a target brightness image includes: For pixels at the same pixel position in each exposure image, performing a weighted average of their brightness values ​​and the corresponding weight values ​​to obtain a fused brightness value of the pixel; The fused brightness value is mapped back to the same brightness range as the exposure image, and a final target brightness image is output.

4. The brightness compensation method according to claim 1, wherein: The performing brightness compensation on the display screen based on the brightness mapping mode, each brightness deviation value in the filtered pixel brightness deviation map, and the gain adjustment coefficient includes: Inputting each brightness deviation value in the filtered pixel brightness deviation map into the brightness mapping method to obtain a compensation gain for each pixel; Combining the compensation gain with the original brightness value of the corresponding pixel according to the gain adjustment coefficient to generate a compensated pixel brightness value; The compensated pixel brightness values ​​of all pixels are sent to the display screen through the display driver interface to achieve real-time brightness uniformity compensation.

5. A brightness compensation device, characterized in that: include: A shooting unit, used for shooting an initial MURA distribution image of the display screen; A classification unit, configured to identify and classify the initial MURA distribution image using an image classification model to obtain a classification result; an acquisition unit, configured to configure corresponding optimal shooting parameters according to the classification result and perform at least one more exposure acquisition on the display screen to obtain an image set including one or more exposure images; a fusion unit, configured to fuse the image set according to the classification result to generate a target brightness image; A comparison unit, configured to respectively obtain a target brightness value and a theoretical brightness value of a pixel corresponding to each pixel position in the target brightness image and the theoretical brightness image; Comparing the target brightness value with the theoretical brightness value to obtain a brightness deviation value for each pixel; Combining the brightness deviation values ​​into a brightness deviation matrix; Performing median filtering on the brightness deviation matrix to obtain a pixel brightness deviation map; A compensation unit is used to select a corresponding optimal compensation parameter set based on the classification result, the compensation parameter set including a gain adjustment coefficient, a local filtering radius, a noise suppression strength, and a brightness mapping method; locally filter the pixel brightness deviation map using the local filtering radius and the noise suppression strength; and perform brightness compensation on the display screen based on the brightness mapping method, each brightness deviation value in the filtered pixel brightness deviation map, and the gain adjustment coefficient.

6. A storage medium, characterized in that The storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the brightness compensation method according to any one of claims 1 to 4.

7. An electronic device, characterized in that: The method comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the brightness compensation method according to any one of claims 1 to 4 when executing the computer program.

Images