Method and system for detecting and correcting brightness and color difference of LED liquid crystal display screen

Abstract

The invention discloses an LED liquid crystal display screen brightness and color difference detection and correction method and system, and belongs to the technical field of liquid crystal display. Initial brightness values and color values of all display units of a display screen are obtained; constructing a brightness and color difference reference model based on the convolutional neural network, and calculating a brightness deviation delta L and a color deviation delta C between the brightness and color difference reference model and a standard value; constructing a brightness-color difference error matrix W; according to the error matrix and in combination with a self-adaptive threshold algorithm, identifying a brightness-color difference abnormal region and corresponding coordinates of the brightness-color difference abnormal region; based on a deviation scoring result, introducing a gradient regression model to generate a brightness gain coefficient and a color adjustment coefficient, and constructing a correction parameter set P; the parameter set is issued to a control chip, dynamic image signal modulation and local frame level refreshing are executed, and point-by-point brightness and color difference correction is achieved; the method has the advantages of high precision, high automation, high adaptive capacity and the like, and is suitable for improving the brightness and color difference uniformity in various LED liquid crystal display screen scenes.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of liquid crystal display, and particularly relates to an LED liquid crystal display screen bright color difference detection correction method and system. BACKGROUND

[0002] With the continuous development of display technology, LED liquid crystal display screens are widely used in advertising media, traffic information publishing, security monitoring and command center fields due to their high brightness, low power consumption, bright color and other advantages. In order to ensure the consistency of display effect and the picture restoration degree, the LED liquid crystal display screen usually needs to be corrected in terms of brightness and color uniformity before leaving the factory. However, due to the manufacturing errors between modules, the different aging degrees of LED lamp beads, the response differences of driving circuits and other factors, there are certain differences in brightness and color in different areas, which is easy to form "bright color difference", that is, the local brightness and color are inconsistent, thereby affecting the user's viewing experience.

[0003] The existing bright color difference correction method mainly depends on manual visual detection or image sensor-based acquisition analysis, but has the problems of low precision, low efficiency and high cost, and it is difficult to realize fine correction in the scene of large-size display screen. Therefore, an automatic, high-precision and low-cost LED liquid crystal display screen bright color difference detection correction method is needed to improve the consistency and overall display quality of the display screen, which has become a key technical problem to be solved in the field. SUMMARY

[0004] The purpose of the present application is to provide an LED liquid crystal display screen bright color difference detection correction method and system to solve the problems in the background art.

[0005] In order to achieve the above purpose, the present application provides the following technical scheme: an LED liquid crystal display screen bright color difference detection correction method, comprising: S100, obtaining initial brightness values and color values of each display unit on the LED liquid crystal display screen; S200, calculating the brightness deviation ΔL and the color deviation ΔC between each display unit and the standard value according to the standard brightness and color reference model; S300, constructing a bright color difference error matrix W according to ΔL and ΔC; S400, analyzing the error matrix W according to a preset threshold, identifying the bright color difference abnormal area and determining the position coordinates of the corresponding display unit; S500, generating a corresponding correction parameter set P including the brightness gain coefficient and the color adjustment coefficient according to the deviation degree of the bright color difference abnormal area; S600, applying the correction parameter set P to the corresponding display unit to perform the bright color difference correction operation; S700, repeating steps S100 to S600 until the luminance and color deviation of all display units are less than the preset threshold value.

[0006] Preferably, the S200 specifically includes: S201, constructing a luminance and color deviation reference model based on a convolutional neural network, the model input being the original RGB data and the ambient light parameter of each display unit, and the output being a target luminance value Lref and a target color value Cref; S202, standardizing the current luminance Lcur and color value Ccur of each display unit actually collected; S203, calculating the luminance deviation ΔL and color deviation ΔC of each display unit using a weighted difference algorithm.

[0007] Preferably, the S300 specifically includes: S301, dividing the display screen into a grid according to the pixel array, establishing a two-dimensional coordinate system corresponding to the physical position, and respectively mapping the ΔL and ΔC values of each display unit; S302, performing feature compression on ΔL and ΔC using principal component analysis to extract the dominant components of luminance and color deviation and retain high variance features; S303, embedding the compressed feature vector into a two-dimensional error tensor structure to construct a luminance and color deviation error matrix W, wherein each element of the matrix is generated by combining the principal deviation components of the corresponding pixel points.

[0008] Preferably, the S400 specifically includes: S401, performing multi-threshold segmentation processing on the luminance and color deviation error matrix W, and dynamically determining the optimal boundary threshold of the joint deviation of ΔL and ΔC using an adaptive Otsu algorithm to obtain a preliminary abnormal region mask; S402, performing morphological filtering on the abnormal region mask based on region connectivity analysis to extract a stable luminance and color deviation abnormal profile; S403, mapping the abnormal profile back to the original display unit grid, combining the matrix index and the coordinate mapping function, and determining the two-dimensional position coordinates (i, j) of the corresponding display unit.

[0009] Preferably, the S500 specifically includes: S501, for each luminance and color deviation abnormal region, calculating its comprehensive deviation score R according to the amplitude and distribution density of its corresponding ΔL and ΔC, wherein R is formed by weighted fusion of luminance deviation intensity, color shift angle, and area; S502, introducing an adaptive gradient regression model based on the score R to respectively fit and generate the luminance gain coefficient GL and the color adjustment coefficient GC of the corresponding display unit, and the model learns the optimal correction strategy under different deviation modes through training samples. S503, combine GL and GC as a correction parameter pair P(i,j) = {GL(i,j), GC(i,j)} and interpolate and propagate in the abnormal area; S504, construct a correction parameter set P containing parameter pairs P(i,j) of all display units in the abnormal area and bind a unique area identifier ID with a coordinate index.

[0010] Preferably, the S600 specifically includes: S601, issue the correction parameter set P to the LED display screen control module through the drive control interface and perform point-by-point mapping and binding according to the display unit coordinates (i,j); S602, set a real-time correction register channel in the display control chip, dynamically modulate the input image signal according to the luminance gain coefficient GL and the color adjustment coefficient GC in P(i,j), including luminance amplitude reconstruction and RGB color matrix rotation transformation; S603, synchronously perform a local redrawing operation to refresh the update area at the frame level; S604, monitor the residual error change between each frame of image output after correction and the target luminance and color model, and if the residual error exceeds the tolerance range, automatically return to S500 for parameter adaptive iterative optimization.

[0011] The application also provides an LED liquid crystal display screen luminance and color difference detection and correction system, comprising: an image acquisition module that acquires initial luminance values and color values of each display unit on the LED liquid crystal display screen; a deviation calculation module that calculates luminance deviations ΔL and color deviations ΔC between each display unit and the standard values according to a standard luminance and color reference model; an error modeling module that constructs a luminance and color difference error matrix W according to ΔL and ΔC; an abnormality detection module that analyzes the error matrix W according to a preset threshold, identifies luminance and color difference abnormal areas and determines the position coordinates of the corresponding display units; a parameter generation module that generates a corresponding correction parameter set P including a luminance gain coefficient and a color adjustment coefficient according to the deviation degree of the luminance and color difference abnormal area; an image correction module that applies the correction parameter set P to the corresponding display units and performs a luminance and color difference correction operation; a control and feedback module that repeatedly optimizes until the luminance and color deviations of all display units are less than the preset threshold.

[0012] In the above technical solution, the application provides technical effects and advantages: 1、The application realizes high-precision identification and spatial mapping of the brightness and color deviation of the LED liquid crystal display screen by introducing a bright color difference reference model based on a convolutional neural network, combining principal component extraction of bias vectors and error matrix modeling. Compared with the traditional scheme relying on fixed templates or manual detection, the application has stronger adaptability and stability, can dynamically cope with the complex changes of different screen types, display content and lighting environment, and significantly improves the detection precision and accuracy of abnormal positioning.

[0013] 2、The application constructs a closed-loop self-correction mechanism for parameter generation and application, adaptively outputs the brightness gain coefficient and color adjustment coefficient through a gradient regression model, and realizes dynamic image modulation and local refresh in the control chip, supplemented by error residual feedback control, effectively avoiding over-correction and visual fragmentation. The overall technical path has the advantages of high automation, strong scalability and good visual consistency, and is suitable for high-end display scenarios with extremely high requirements for picture uniformity and color accuracy. BRIEF DESCRIPTION OF DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed in the embodiments will be briefly introduced as follows. Obviously, the drawings described in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0015] Figure 1 The method mind map of the present application.

[0016] Figure 2 The system module mind map of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0018] Embodiment 1, please refer to Figure 1 The LED liquid crystal display screen bright color difference detection and correction method described in this embodiment comprises: S100, obtaining the initial brightness value and color value of each display unit on the LED liquid crystal display screen; S200, calculating the brightness deviation ΔL and color deviation ΔC between each display unit and the standard value according to the standard brightness and color reference model; S300, constructing a bright color difference error matrix W according to AL and AC; S400, analyzing the error matrix W according to a preset threshold, identifying a bright color difference abnormal area and determining the position coordinates of the corresponding display unit; S500, generating a corresponding correction parameter set P including a brightness gain coefficient and a color adjustment coefficient according to the deviation degree of the bright color difference abnormal area; S600, applying the correction parameter set P to the corresponding display unit to perform a bright color difference correction operation; S700, repeating steps S100 to S600 until the brightness and color deviation of all display units are less than the preset threshold.

[0019] S100 specifically includes the following steps: A high-resolution imaging device is arranged in front of the LED liquid crystal display screen, preferably an industrial camera module with a wide dynamic range (HDR) is used, and a uniformly distributed illumination reference plate is combined to minimize environmental light interference during the acquisition process. The imaging device is fixed to the display screen by a stable support, the acquisition angle is perpendicular to the screen or controlled within 5 degrees, and the geometric consistency of the picture is improved.

[0020] The display screen plays a standard test image sequence, and the image content includes pure white, pure red, pure green, pure blue, gray scale strips and color gradient stripes, etc., to stimulate the brightness and color response of the LED unit in the typical working state. During the playing process, the constant brightness level and refresh frequency are maintained to avoid image fluctuation.

[0021] The display image is acquired frame by frame by the camera, and the original image is denoised, distorted and gamma inverse corrected. Bilateral filtering or median filtering is used to remove small area noise, and camera calibration parameters are used for image correction to ensure that the image data is strictly aligned with the physical layout of the display screen.

[0022] The processed image is divided into a pixel grid area corresponding to the display unit (such as NxN pixel blocks corresponding to each module), and the representative brightness value Lcur and color value Ccur are extracted by averaging the pixels in each area. The brightness value can be calculated based on the Y channel (for example, converted from RGB to YCbCr space), and the color value is represented in CIE Lab or HSV space to enhance the response to the sensitive area of the human eye.

[0023] Lcur and Ccur are bound to the two-dimensional coordinates (i,j) of the display unit to form a complete data structure D(i,j) = {Lcur(i,j), Ccur(i,j)}, which is stored in the initialization data matrix to provide basic input for the deviation calculation in step S200.

[0024] S200 specifically includes the following sub-steps: A deep learning model is established as a bright color difference reference standard generator, adopting a multi-layer convolutional neural network (CNN) structure, and the input layer receives the three-channel RGB values of each display unit and the environmental light parameters (such as light intensity, direction, and color temperature). The middle layer extracts local color texture and brightness gradient features through multi-scale convolution kernels, fuses BatchNorm and ReLU activation, and enhances the robustness of the model.

[0025] The model is trained with a large amount of display screen sample data and can output target brightness value Lref and target color value Cref, which represent the brightness and color performance in the ideal display state respectively. The output values reflect the screen factory standard or user-set reference on the physical level and have cross-screen generalization ability.

[0026] For the actually collected Lcur and Ccur, normalization and light compensation processing is performed. The brightness value Lcur adopts the maximum-minimum normalization method and performs linear light inversion combined with the environmental light intensity to remove the influence of overall exposure difference on local unit brightness.

[0027] The color value Ccur is converted to Lab or HSV color space, the channel is normalized, and the edge pixel jump is suppressed through median smoothing processing. This processing step ensures that the deviation value in the subsequent calculation has cross-region consistency and contrast.

[0028] For each display unit (i, j), the brightness deviation is calculated according to the formula , and the color deviation is . A region weighting function W(i, j) is introduced, which is adaptively generated based on the consistency of the pixel neighborhood and the local gradient change rate, and is used to adjust the deviation influence weight.

[0029] In particular, the color deviation ΔC is calculated using a vector difference method, which considers the hue angle difference and saturation difference, to avoid the distortion problem of traditional Euclidean distance in non-uniform color space.

[0030] Finally, ΔL and ΔC are output as error information for subsequent steps, with high resolution, high reliability, and interpretability.

[0031] S300 specifically includes the following sub-steps: The LED liquid crystal display screen is divided into an M×N pixel array grid, and each grid unit (i, j) corresponds to an actual display pixel unit. Based on the ΔL(i, j) and ΔC(i, j) data collected and calculated in the early stage, a two-dimensional coordinate system is constructed to map the position of each display unit and its brightness color difference value, forming a brightness deviation field ΔLmap and a color deviation field ΔCmap.

[0032] The space mapping ensures that all deviation information can be mapped to the real physical display area, providing a basic position reference for subsequent matrix construction.

[0033] The principal component analysis (PCA) is performed on the deviation vector set composed of ΔLmap and ΔCmap to extract the characteristic component with the largest variance contribution. This step is used to remove redundant information, compress high-dimensional deviation data, and maintain the most sensitive change trend to the bright color difference abnormal area.

[0034] The first k principal components (usually k = 1 or 2) are retained during compression to ensure that more than 95% of the original deviation information is not lost, while significantly improving data processing efficiency.

[0035] The compressed main characteristic components are remapped to the original two-dimensional coordinate grid and embedded to construct a two-dimensional tensor structure W. W is a matrix with a size of M x N, where each element W(i,j) represents the combined value of the main deviation of the display unit, in the form of: ; Where α and β are the weighting coefficients of the brightness and color principal components, which can be customized according to the actual display preference or visual perception model.

[0036] The error matrix W can be regarded as a numerical "deviation map" for describing the comprehensive deviation distribution of the entire display screen in terms of brightness and color, providing a quantitative basis for subsequent abnormal area identification and correction strategy formulation.

[0037] Specifically, S400 includes the following sub-steps: The combined deviation value W(i,j) of ΔL and ΔC is extracted from the constructed brightness and color difference error matrix W as the basis for segmentation, and an adaptive multi-threshold segmentation method is used for region division. In specific implementation, based on the improved Otsu algorithm, a set of optimal gray threshold values T1, T2,..., T n , n is the total number of gray thresholds, and the inter-class variance is maximized and the number of segmentation layers is adaptively adjusted.

[0038] This method can accurately divide the normal area and multiple levels of bright color difference abnormalities according to the actual variance of the deviation value in the full screen distribution, avoiding false positives or false negatives caused by uneven distribution of fixed threshold method.

[0039] The output result is a binary mask map M, where M(i,j) = 1 indicates an abnormal area, and M(i,j) = 0 indicates a normal area, forming the initial boundary profile of the bright color difference abnormal area.

[0040] Region connectivity analysis is performed on the preliminary mask map M, using 8-neighborhood connectivity rule to identify all closed or nearly closed bright color difference abnormal blocks. To enhance the stability of region boundaries and suppress noise interference, further morphological opening and closing operations are performed on the mask map (opening operation denoising, closing operation hole filling), to remove false difference values and refine the outline shape.

[0041] After filtering is completed, all stable existing abnormal region outlines R1, R2,..., R k , k is the total number of abnormal region outlines; record its boundary point set and region characteristic parameters (area, shape factor, etc.), to provide structural input for positioning and correction.

[0042] Each abnormal outline region Ri is inversely mapped to the original display cell grid, using matrix indexing and two-dimensional coordinate mapping functions for accurate positioning, to generate the corresponding cell coordinate set S = {(i1,j1), (i2,j2),..., (i n , j n )}.

[0043] The mapping process maintains the alignment of the error matrix W and the physical pixel array structure, and introduces position offset correction (such as camera distortion compensation parameters) when necessary, to ensure that the identified abnormal regions have actual operable positioning accuracy on the display screen.

[0044] The output result is the abnormal display cell coordinate set and the outline region index, which can be used to establish the region label and coordinate binding relationship in the subsequent correction parameter generation step.

[0045] S500 specifically includes the following sub-steps: For each identified bright color difference abnormal region, extract its internal display cell ΔL and ΔC values, and calculate the comprehensive deviation score R based on the following three dimensions: Luminance deviation intensity : the root mean square (RMS) of ΔL values within the region, reflecting the degree of luminance non-uniformity; Color shift angle : the vector deviation angle of ΔC in Lab or HSV color space, to quantify the hue direction error; Region area weight : the number of display cells contained in the abnormal region, reflecting its impact degree in the entire screen.

[0046] Score , where is an empirical weight coefficient, based on actual scene adjustment and optimization.

[0047] An adaptive gradient regression model (such as a gradient boosting regression tree GBRT or a lightweight neural network model) is introduced to score R as an input feature, and to fit the output target as a luminance gain coefficient G_L and a color adjustment coefficient GC.

[0048] The training data is derived from a historical correction sample library, and the sample control ΔL, ΔC deviation type and the correction parameter after artificial or simulated optimization form a supervised learning input-output pair. The model has nonlinear fitting capability and can adapt to different light color difference patterns and output fine parameter prediction results.

[0049] Each display unit in each abnormal area can independently obtain the corresponding parameter pair: .

[0050] In order to eliminate the display fault caused by the jump of the correction parameter at the region boundary, a bilinear interpolation or boundary weight smoothing interpolation algorithm is used to continuously interpolate and diffuse GL and GC in the abnormal area. The interpolation algorithm considers the deviation gradient change trend of the region center-edge, and ensures that the correction parameter naturally transitions in space.

[0051] In addition, a "buffer extension" is performed on the edge of the adjacent non-abnormal area to construct a transition layer, further reducing the visual fragmentation caused by correction.

[0052] Finally, all the parameter pairs P(i,j) in the abnormal area are packaged according to the region number to form a structured correction parameter set P, which includes: Region unique identifier ID; The coordinates (i,j) of each display unit in the region; The corresponding luminance gain coefficient GL and color adjustment coefficient GC; Region deviation score R and model adaptation state.

[0053] The parameter set P has the properties of scalability, callability and traceability, which facilitates the real-time access and execution of correction control by subsequent driving modules.

[0054] Specifically, S600 includes the following sub-steps: The correction parameter set P constructed is sent to the control module of the LED display screen through the driving control interface (such as SPI, I2C or FPGA on-chip bus) of the main control system. The parameter data packet contains fields such as display unit coordinates (i,j), luminance gain coefficient GL(i,j) and color adjustment coefficient GC(i,j).

[0055] The control module accurately binds the parameters to the corresponding driving channel or control register according to the coordinate index, ensures that each pixel point receives a unique corresponding correction instruction, and realizes the high-precision control strategy of "point-by-point mapping and point-by-point correction".

[0056] In the LED display screen control chip, a real-time correction register channel is configured for inserting a correction module in the image signal processing chain. The specific implementation is as follows: The luminance gain modulation is performed on the original image input signal of each pixel, and the luminance amplitude is dynamically reconstructed according to GL(i,j); The color matrix rotation transformation or gamma space mapping correction is performed on the RGB channel value, and the hue direction and saturation are fine-tuned according to GC(i,j).

[0057] The above processing is performed online in the front end of the display control frame buffer, and the vector correction of all pixel-level images is completed before each frame refresh, ensuring that the correction effect is synchronized with the image in real time.

[0058] To improve the system response efficiency, the control module supports a local area-level redraw refresh strategy. Only the abnormal area applying the correction parameter is executed to perform the redraw operation, triggering the data update of the corresponding area in the frame buffer, avoiding the resource waste and display jitter caused by full-screen refresh.

[0059] The refresh operation is synchronized with the display refresh rate (such as 60Hz or 120Hz), ensuring that there is no lag in the display phenomenon after the correction parameter takes effect, and improving the user's visual consistency experience.

[0060] After each frame of image output is completed, the image feedback module or external image acquisition device is called to compare the actual luminance and color output with the target reference model (Lref, Cref). If the ΔL' or ΔC' of some area exceeds the tolerance range (such as ±5% or ΔE>3), it is considered that the correction effect is insufficient.

[0061] At this time, the system automatically triggers the closed-loop mechanism, returns to the S500 step, re-evaluates the score R, and builds a new round of correction model based on the historical residual, realizing self-adaptive iterative optimization and continuously improving the correction accuracy.

[0062] S700 specifically includes the following sub-steps: The overall system design is a closed-loop light color difference detection-correction feedback framework. After the first execution of S100 to S600, the corrected display state is input again, returned to the S100 step to re-collect the luminance value Lcur' and color value Ccur' of each display unit, for the second round of error evaluation.

[0063] The iterative mechanism ensures that each round of correction is based on the latest state adjustment, avoiding the secondary deviation caused by insufficient or excessive correction in the first correction.

[0064] After each iteration, the S200-S300 steps are re-executed to calculate the new ΔL' and ΔC' values, and the error matrix W' is reconstructed. The error aggregation analysis is performed on the full-screen display unit, and the following two indicators are extracted: maximum deviation value max(ΔL', ΔC'); average deviation value mean(ΔL', ΔC'); The system compares the two indicators with preset threshold values, such as ΔL threshold = 3%, ΔC threshold (color difference ΔE) = 2.5, to determine whether the current correction result has reached a stable state.

[0065] If any unit deviation still exceeds the threshold value, the system automatically enters the next iteration; if all unit ΔL' and ΔC' are less than the corresponding threshold value, or the error change rate of two consecutive iterations is lower than the set convergence threshold (such as <0.2%), it is judged that the correction converges, and the cycle is terminated.

[0066] The system supports setting the maximum number of iterations Nmax (such as 3-5 times) to prevent infinite loops in abnormal situations and improve the safety and stability of operation.

[0067] When the iteration is terminated, the system outputs the final correction parameter set Pfinal, the error matrix Wfinal, and the error change log of each round, and permanently stores the correction parameters in the controller Flash as the system default calibration state. Optionally, the correction heat map and convergence trend curve are output for visual quality assessment.

[0068] The system automatically switches the display control state to "lock mode" to stop subsequent image signal modulation intervention, ensuring the consistency and stability of the final display state.

[0069] Embodiment 2, please refer to Figure 2 The LED liquid crystal display screen bright color difference detection and correction system described in this embodiment includes: an image acquisition module, which acquires the initial brightness value and color value of each display unit on the LED liquid crystal display screen; a deviation calculation module, which calculates the brightness deviation ΔL and color deviation ΔC between each display unit and the standard value according to the standard brightness and color reference model; an error modeling module, which constructs a bright color difference error matrix W according to ΔL and ΔC; an anomaly detection module, which analyzes the error matrix W according to the preset threshold value, identifies the bright color difference abnormal area, and determines the position coordinates of the corresponding display unit; a parameter generation module, which generates a corresponding correction parameter set P according to the deviation degree of the bright color difference abnormal area, including a brightness gain coefficient and a color adjustment coefficient; an image correction module, which applies the correction parameter set P to the corresponding display unit to perform bright color difference correction operation; a control and feedback module, which repeats optimization until the brightness and color deviation of all display units are less than the preset threshold value.

[0070] The above description is only the specific implementation of the present application, but the protection scope of the present application is not limited to this. Any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered in the protection scope of the present application.

Claims

1. A LED liquid crystal display screen bright color difference detection correction method, characterized in that: The method comprises the following steps: S100, acquiring initial brightness values and color values of each display unit on an LED liquid crystal display screen; S200, calculating brightness deviation ΔL and color deviation ΔC between each display unit and a standard value according to a standard brightness and color reference model; S300, constructing a brightness and color difference error matrix W according to ΔL and ΔC; S400, analyzing the error matrix W according to a preset threshold value, identifying a brightness and color difference abnormal area and determining the position coordinates of the corresponding display unit; S500, generating a corresponding correction parameter set P including a brightness gain coefficient and a color adjustment coefficient according to the deviation degree of the brightness and color difference abnormal area; S600, applying the correction parameter set P to the corresponding display unit to perform a brightness and color difference correction operation; S700, repeating steps S100 to S600 until the brightness and color deviation of all display units is less than the preset threshold value.

2. The LED liquid crystal display screen bright chromatic aberration detection and correction method according to claim 1, characterized in that: The S200 specifically comprises: S201, constructing a brightness and color difference reference model based on a convolutional neural network, the model input being original RGB data and ambient light parameters of each display unit, and the output being a target brightness value Lref and a target color value Cref; S202, performing standardization processing on the current brightness Lcur and color value Ccur of each display unit actually collected; S203, calculating the brightness deviation ΔL and the color deviation ΔC of each display unit by using a weighted difference algorithm.

3. The LED liquid crystal display screen bright chromatic aberration detection and correction method according to claim 1, characterized in that: The S300 specifically comprises: S301, grid dividing the display screen according to a pixel array, establishing a two-dimensional coordinate system corresponding to the physical position one by one, and respectively mapping the ΔL and ΔC values of each display unit; S302, performing principal component analysis on ΔL and ΔC to compress the features, extract the dominant components of the brightness and color deviation, and retain the high-variance features; S303, embedding the compressed feature vectors into a two-dimensional error tensor structure to construct the brightness and color difference error matrix W, wherein each element of the matrix is generated by combining the main deviation components of the corresponding pixel points.

4. The LED liquid crystal display screen bright chromatic aberration detection and correction method according to claim 1, characterized in that: The S400 specifically comprises: S401, performing multi-threshold segmentation processing on the brightness and color difference error matrix W, and dynamically determining the optimal boundary threshold of the joint deviation of ΔL and ΔC by using an adaptive Otsu algorithm to obtain a preliminary abnormal area mask; S402, performing morphological filtering on the abnormal area mask based on region connectivity analysis to extract a stable brightness and color difference abnormal profile; S403, mapping the abnormal profile back to the original display unit grid, combining the matrix index and the coordinate mapping function, and determining the two-dimensional position coordinates (i, j) of the corresponding display unit.

5. The LED liquid crystal display screen bright chromatic aberration detection and correction method according to claim 1, characterized in that: The S500 specifically comprises: S501, for each brightness and color difference abnormal area, calculating a comprehensive deviation score R according to the amplitude and distribution density of the corresponding ΔL and ΔC, wherein R is formed by weighted fusion of the brightness deviation intensity, the color shift angle and the area; S502, introducing an adaptive gradient regression model based on the score R to respectively fit and generate a brightness gain coefficient GL and a color adjustment coefficient GC of the corresponding display unit, and the model learns the optimal correction strategy under different deviation modes through training samples. S503, combine GL and GC as the correction parameter pair P(i,j) = {GL(i,j), GC(i,j)} and interpolate and propagate in the abnormal area; S504, construct the correction parameter set P containing the parameter pairs P(i,j) of all display units in the abnormal area and bind the unique area identifier ID and the coordinate index.

6. The method for detecting and correcting brightness and color difference of an LED liquid crystal display according to claim 1, wherein: The S600 specifically includes: S601, issue the correction parameter set P to the LED display screen control module through the drive control interface and perform point-by-point mapping and binding according to the display unit coordinates (i,j); S602, set a real-time correction register channel in the display control chip, dynamically modulate the input image signal according to the luminance gain coefficient GL and the color adjustment coefficient GC in P(i,j), including luminance amplitude reconstruction and RGB color matrix rotation transformation; S603, synchronously perform a local redrawing operation to refresh the update area at the frame level; S604, monitor the residual error between each frame of image output after correction and the target luminance and color model, and if the residual error exceeds the tolerance range, automatically return to S500 for adaptive iterative optimization of the parameters.

7. A system for detecting and correcting the brightness and color difference of an LED liquid crystal display screen, which is used to implement the method for detecting and correcting the brightness and color difference of an LED liquid crystal display screen according to any one of claims 1-6, characterized in that: It includes: An image acquisition module that acquires the initial luminance and color values of each display unit on the LED liquid crystal display screen; A deviation calculation module that calculates the luminance deviation ΔL and the color deviation ΔC between each display unit and the standard value according to the standard luminance and color reference model; An error modeling module that constructs a luminance and color difference error matrix W according to ΔL and ΔC; An abnormality detection module that analyzes the error matrix W according to a preset threshold, identifies the luminance and color difference abnormal area, and determines the position coordinates of the corresponding display unit; A parameter generation module that generates a corresponding correction parameter set P including a luminance gain coefficient and a color adjustment coefficient according to the deviation degree of the luminance and color difference abnormal area; An image correction module that applies the correction parameter set P to the corresponding display unit and performs a luminance and color difference correction operation; A control and feedback module that repeatedly optimizes until the luminance and color deviations of all display units are less than the preset threshold.

Images