Color correction method and system for liquid crystal panel

Abstract

The invention discloses a color correction method and system for a liquid crystal panel, and particularly relates to the technical field of liquid crystal panels. The method comprises the following steps: firstly, acquiring color reference data of a panel, establishing a reference model, then detecting a color shift condition in real time through a color sensor, predicting a color shift trend and calculating a color compensation coefficient based on a machine learning model, dynamically adjusting a driving signal of the liquid crystal panel, optimizing backlight brightness, RGB sub-pixel compensation and a Gamma curve according to the coefficient, and finally adjusting the color shift condition of the liquid crystal panel. For the area with serious color drift, a local area correction strategy is adopted, partition-level compensation is executed, the color uniformity of the whole screen is improved, the limitation of traditional static color correction is broken through, intelligent and self-adaptive dynamic color correction is achieved, the color consistency and long-term use stability of the liquid crystal panel are effectively improved, and the color uniformity of the liquid crystal panel is improved. The method is particularly suitable for high-refresh-rate display equipment, the problem of unnatural color transition is solved, and the visual experience of a user is remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of liquid crystal panels, and in particular to a color correction method and system for a liquid crystal panel. Background Art

[0002] Liquid crystal panel (LCD) is the mainstream technology currently widely used in display devices (such as TVs, smart phones, tablets, etc.). Its display quality is affected by many factors, including backlight uniformity, pixel arrangement, color management algorithm, etc. In order to ensure accurate color reproduction, color calibration technology is usually required to adjust the color gamut distribution of the three primary colors of red (R), green (G), and blue (B) to conform to standard color spaces such as sRGB, AdobeRGB, and DCI-P3.

[0003] At present, color correction mainly relies on factory calibration and software algorithm adjustment. Factory calibration generally uses spectrometer detection + calibration file writing to make the panel achieve high color accuracy when it leaves the factory. However, during long-term use, LCD is affected by factors such as ambient temperature changes, backlight attenuation, and liquid crystal aging, and the color accuracy will gradually decrease, resulting in color deviation problems and affecting user experience.

[0004] The prior art has the following deficiencies: After the LCD panel displays fixed color content for a long time (such as static UI elements, long-term video playback of a specific color tone), the response characteristics of the liquid crystal molecules of some pixels will shift. Even if they switch to other colors, the previous color characteristics will be retained for a short time, resulting in transient color cast in dynamic images. This problem is similar to the "burn-in" effect of OLED screens, but it manifests as a short-term residual color retention on LCDs, especially in high refresh rate display modes (such as 120Hz, 240Hz), which affects the color accuracy of dynamic images. Existing color correction methods are mainly aimed at static color adjustment, and cannot effectively eliminate the dynamic color cast problem caused by the "color memory effect", resulting in unnatural color transitions and even "ghost images" in some scenes, which seriously affects the color consistency and user experience of high-end display devices. Summary of the invention

[0005] The object of the present invention is to provide a color correction method and system for a liquid crystal panel to solve the deficiencies in the background technology.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a color correction method for a liquid crystal panel, comprising the following steps: S1: Collect color benchmark data of the LCD panel, including the color gamut range, gamma curve, color temperature parameters, and pixel-level color response data at the time of leaving the factory; S2: Use the color sensor to detect the color display status of the LCD panel in different areas in real time, and obtain the brightness deviation, color drift and local color temperature change of each area; S3: Use a color shift prediction model based on machine learning to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient; S4: Dynamically adjust the driving signal of the LCD panel according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; S5: adopt a local area correction strategy to perform color compensation at the partition level for areas where severe color drift is detected; S6: Regularly performs color adaptive correction based on user usage patterns. If dynamic color cast is detected, a pixel refresh algorithm is used to eliminate residual color effects.

[0007] Preferably, the pixel-level color response data collected in S1 includes initial RGB sub-pixel brightness values, color uniformity data, and dynamic color response time of different areas of the liquid crystal panel.

[0008] Preferably, in S2, the color display state of the liquid crystal panel in different areas is detected in real time by a color sensor to obtain the brightness deviation, color drift and local color temperature change of each area, which specifically includes: The test color card is displayed on the LCD panel, and the color sensor measures the actual color value of each area, recording the color value of each detection area. : Measures the brightness of the three primary colors of red, green and blue; Chromaticity coordinates (x, y): Measures the color coordinates according to the CIE 1931 color space; Color temperature value: Calculates the current color temperature of the panel and compares it with the standard color temperature; Calculate the brightness deviation using the formula: ;in: is the brightness deviation of the i-th detection area; The actual brightness value detected by the color sensor; It is the reference brightness value measured at the factory; Calculate the color drift using the formula: ;in: The color drift amount of the i-th area; L is the brightness component; a, b are the chromaticity coordinates in the CIE Lab color space; meas is the actual detection value, and ref is the factory reference value; Calculate the local color temperature change, the calculation formula is: ;in: is the color temperature deviation of the i-th detection area; The actual color temperature measured by the color sensor; This is the factory reference color temperature.

[0009] Preferably, in S3, a color shift prediction model based on machine learning is used to analyze the impact of different usage environments on the color performance of each area of ​​the liquid crystal panel and calculate the color drift compensation coefficient, including: The brightness deviation, color drift and local color temperature change are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as inputs of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the impact value labels of different usage environments on the color performance of each area of ​​the LCD panel as the prediction target, and takes minimizing the sum of the prediction errors of the impact value labels of all different usage environments on the color performance of each area of ​​the LCD panel as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The color drift compensation coefficient is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0010] Preferably, in S4, the driving signal of the liquid crystal panel is dynamically adjusted according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; According to the brightness attenuation of different areas of the panel, adjust the local backlight brightness to ensure the overall screen brightness is consistent. The calculation formula is: ;in: is the adjusted backlight brightness value of the ith area, is the actual backlight brightness value of the current i-th area, is the color drift compensation coefficient, λ is the brightness compensation weight; if >0, increase the area LED backlight brightness, if <0, reduce the LED backlight brightness in the area. After the adjustment is completed, detect the brightness deviation again. If it still exceeds the threshold, perform fine-grained compensation. Specifically, if the brightness deviation ΔL exceeds 10% or the color drift ΔE > 3, perform local backlight brightness adjustment or increase the correction frequency at the pixel level.

[0011] Preferably, in view of the color drift phenomenon, the driving voltage of the RGB sub-pixel is adjusted, and the calculation formula is: ;in, , , is the adjusted RGB sub-pixel driving signal, is the original RGB driving signal, α, β, γ are the RGB compensation weights; if >5, perform high-intensity RGB compensation, including adjusting the compensation coefficient of the RGB sub-pixel drive voltage to 10%~20%; if 3 < ≤5, perform small RGB refinement compensation and adjust the compensation coefficient of RGB sub-pixel driving voltage to 5%~10%.

[0012] Preferably, the panel Gamma curve is corrected to restore the standard color display, and the calculation formula is: ;in: is the output signal after Gamma correction, is the input signal, γ is the standard Gamma value, Indicates the amount of gamma adjustment based on the color drift compensation coefficient; the corrected gamma curve is calculated through the Gamma LUT to adjust the display color tone.

[0013] Preferably, in S6, color adaptive correction is performed regularly in combination with the user's usage pattern, and if dynamic color cast is detected, the residual color influence is eliminated by a pixel refresh algorithm; Monitor the usage time of LCD panel , count the display ratio of highlight areas to low-brightness areas, analyze the local brightness or color shift caused by long-term use; record the display time of fixed UI elements to determine whether there is a local color memory effect; set the color correction trigger condition: if , trigger color correction. If the color sensor detects that the local color drift ΔE>3 or ΔL>10%, local color correction is triggered.

[0014] Preferably, a pixel refresh algorithm is used to eliminate dynamic color cast: ;in: is the pixel status after refresh, is the current pixel state, is the standard brightness value that the pixel should have, η is the pixel refresh intensity; if dynamic color cast is detected, color flushing is performed pixel by pixel, and the compensation color is displayed for a short time to restore the pixel state; if ΔE>5, multiple refresh cycles are performed to eliminate color residue, and the overall tone is adjusted in combination with gamma compensation, and the color offset is re-detected. If ΔE<3, the correction is completed, otherwise the optimization continues.

[0015] The present invention also provides a color correction system for a liquid crystal panel, including a color reference data storage module, a color detection module, a color offset prediction module, a color drive adjustment module, a local area color compensation module and a color adaptive correction module; Color reference data storage module: collects the color reference data of the LCD panel, including the color gamut range, gamma curve, color temperature parameters, and pixel-level color response data at the time of leaving the factory; Color detection module: Through the color sensor, the color display status of the LCD panel in different areas is detected in real time to obtain the brightness deviation, color drift and local color temperature changes of each area; Color shift prediction module: uses a color shift prediction model based on machine learning to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient; Color drive adjustment module: dynamically adjusts the driving signal of the LCD panel according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; Local area color compensation module: adopts local area correction strategy to perform partition-level color compensation for areas where serious color drift is detected; Color adaptive correction module: Based on the user's usage pattern, color adaptive correction is performed regularly. If dynamic color cast is detected, the pixel refresh algorithm is used to eliminate the residual color impact.

[0016] In the above technical solution, the technical effects and advantages provided by the present invention are: 1. The present invention collects factory color reference data and detects the color status of the panel in real time. The present invention can accurately identify the brightness deviation, color drift and local color temperature changes of each area. A machine learning model based on polynomial regression is used to comprehensively analyze the impact of different usage environments on the color performance of the liquid crystal panel, calculate the color drift compensation coefficient, and ensure the accuracy of the correction. Based on the compensation coefficient, the present invention dynamically adjusts the drive signal of the liquid crystal panel, including backlight brightness optimization, RGB sub-pixel compensation and Gamma curve correction, effectively suppressing local brightness attenuation, color shift and uneven color tone. In addition, for areas with severe color drift, a local area correction strategy is adopted, and high-precision color compensation is performed at the partition level to further improve the color uniformity and consistency of the entire screen.

[0017] 2. The present invention also combines user usage patterns to perform color adaptive correction regularly, dynamically eliminates color residual effects through pixel refresh algorithms, and solves the "ghost image" problem that is difficult to deal with with traditional static color correction. When dynamic color cast is detected, color flushing is performed pixel by pixel, and the overall color tone is optimized in combination with gamma compensation to ensure natural color transitions and restore true color performance. Compared with the prior art, the present invention provides an intelligent, adaptive, and refined color management solution for liquid crystal panels, which is particularly suitable for high refresh rate display devices (such as 120Hz, 240Hz), effectively improving color stability, reducing dynamic picture color cast, and enhancing the visual experience and product competitiveness of high-end display devices. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0019] Figure 1 The figure is a flow chart of the method of the present invention.

[0020] Figure 2 It is a system module diagram of the present invention. DETAILED DESCRIPTION

[0021] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Example 1, please refer to Figure 1 As shown, a color correction method for a liquid crystal panel described in this embodiment includes the following steps: S1: Collect color benchmark data of the LCD panel, including the color gamut range, gamma curve, color temperature parameters, and pixel-level color response data at the time of leaving the factory; S2: Use the color sensor to detect the color display status of the LCD panel in different areas in real time, and obtain the brightness deviation, color drift and local color temperature change of each area; S3: Use a color shift prediction model based on machine learning to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient; S4: Dynamically adjust the driving signal of the LCD panel according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; S5: adopt a local area correction strategy to perform color compensation at the partition level for areas where severe color drift is detected; S6: Regularly performs color adaptive correction based on user usage patterns. If dynamic color cast is detected, a pixel refresh algorithm is used to eliminate residual color effects.

[0023] In S1, key indicators such as the color gamut range (such as sRGB, AdobeRGB, DCI-P3), gamma curve, color temperature parameters, etc. of the LCD panel during the factory calibration stage are recorded as a reference for color correction.

[0024] The initial RGB sub-pixel brightness values ​​of different areas of the panel are recorded through factory color detection equipment or the panel's built-in detection system to ensure that the basic data for color display is accurate.

[0025] Calculate the color uniformity data of the panel, that is, measure the brightness and color shift changes when the LCD panel displays the same color in different areas, and evaluate the initial color consistency.

[0026] Record the dynamic color response time of the LCD panel, that is, measure the time required for the LCD pixel to switch from one color to another (such as grayscale switching) to analyze the dynamic color performance ability of the panel.

[0027] The collected color reference data is stored in the panel driver chip or color management module so as to be used as a comparison reference in the subsequent color correction process to analyze color drift and calculate compensation parameters.

[0028] Set standard values ​​such as gamma curve tolerance, RGB brightness offset threshold, color uniformity deviation range, etc. to determine whether compensation adjustment is needed during subsequent color correction.

[0029] S2: Use the color sensor to detect the color display status of the LCD panel in different areas in real time, and obtain the brightness deviation, color drift and local color temperature change of each area.

[0030] A specific test color card (including standard colors such as white, gray, red, green, and blue) is displayed on the LCD panel, and the color sensor measures the actual color value of each area.

[0031] Record each detection area : RGB brightness value : Measures the brightness of the three primary colors red, green and blue. Chromaticity coordinates (x, y): Measures the color coordinates according to the CIE 1931 color space. Color temperature value (Tmeas): Calculates the current color temperature of the panel and compares it with the standard color temperature.

[0032] Calculate the brightness deviation using the formula: ;in: is the brightness deviation of the i-th detection area (cd / m²); The actual brightness value detected by the color sensor; This is the reference brightness value measured at the factory.

[0033] Calculate the color drift using the formula (ΔE color difference formula, based on CIE76 calculation method): ;in: The color drift of the ith area; L is the brightness component (L*); a, b are the chromaticity coordinates in the CIE Lab color space; meas is the actual detection value, and ref is the factory reference value. When ΔE > 3, the human eye can clearly perceive the color difference. When ΔE > 5, the color deviation is serious and needs to be corrected.

[0034] Calculate the local color temperature change, the calculation formula is: ;in: is the color temperature deviation of the i-th detection area (unit: K); is the actual color temperature measured by the color sensor (Kelvin, K); It is the factory reference color temperature (Kelvin, K).

[0035] S3: Use a color shift prediction model based on machine learning to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient.

[0036] The brightness deviation, color drift and local color temperature change are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as inputs of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the impact value labels of different usage environments on the color performance of each area of ​​the LCD panel as the prediction target, and takes minimizing the sum of the prediction errors of the impact value labels of all different usage environments on the color performance of each area of ​​the LCD panel as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The color drift compensation coefficient is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

[0037] The method for obtaining the color drift compensation coefficient is as follows: from the comprehensive feature vector training data of the trained machine learning model, the corresponding function expression is obtained: ; In the formula, is the output function of the model, is the color drift compensation coefficient.

[0038] S4: Dynamically adjust the driving signal of the liquid crystal panel according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction.

[0039] According to the brightness attenuation of different areas of the panel, adjust the local backlight brightness to ensure the overall screen brightness is consistent. The calculation formula is: ;in: is the adjusted backlight brightness value of the ith area (cd / m²), is the actual backlight brightness value of the current i-th area (cd / m²), is the color drift compensation coefficient. λ is the brightness compensation weight (based on experimental optimization). >0 (the area is dark), increase the LED backlight brightness in that area. <0 (the area is too bright), reduce the LED backlight brightness in the area. After the adjustment is completed, detect the brightness deviation again. If it still exceeds the threshold, perform fine-grained compensation. Specifically: if the brightness deviation ΔL exceeds 10% or the color drift ΔE > 3, perform fine-grained compensation, including fine-tuning the local backlight brightness or increasing the correction frequency at the pixel level to reduce local color errors; Local backlight brightness fine-tuning includes: calculating the LED backlight brightness value of the adjustment area based on the color drift compensation coefficient, increasing the brightness if it is too dark, and reducing the brightness if it is too bright, so as to reduce uneven brightness; Increasing the frequency of pixel-level correction includes: for areas with ΔE > 3, shortening the color compensation update cycle from 30 minutes to 5-10 minutes; for areas with ΔE > 5, using frame-by-frame real-time color compensation and applying a LUT lookup table to optimize pixel-level color adjustment to ensure color uniformity.

[0040] In view of the color drift phenomenon, the driving voltage of the RGB sub-pixels is adjusted to make the output color closer to the standard value. The calculation formula is: ;in, , , is the adjusted RGB sub-pixel driving signal, is the original RGB driving signal, α, β, γ are RGB compensation weights (set according to different color drift conditions).

[0041] like >5 (severe color drift), perform high-intensity RGB compensation, including adjusting the compensation coefficient of the RGB sub-pixel drive voltage to 10%~20%; if 3 < ≤ 5 (slight drift), perform small RGB refinement compensation, adjust the compensation coefficient of RGB sub-pixel driving voltage to 5%~10% to ensure that the color error is reduced to ΔE ≤ 3. The specific RGB compensation method can be combined with a lookup table (LUT) to ensure that the compensation does not cause color over-correction.

[0042] Correct the panel Gamma curve and restore the standard color display. The calculation formula (Gamma correction formula) is: ;in: is the output signal after Gamma correction, is the input signal, γ is the standard Gamma value (usually 2.2), Indicates the amount of gamma adjustment based on the color drift compensation coefficient. The corrected gamma curve is calculated through the Gamma LUT to adjust the display color tone. Gamma correction is applied pixel by pixel to ensure a natural color transition.

[0043] Use the color sensor to re-detect the color offset ΔE and brightness deviation ΔL to ensure that the adjusted panel meets the standard. If ΔE>3 or ΔL>10%, repeat the calibration process until the color calibration target is achieved.

[0044] S5: adopt a local area correction strategy to perform color compensation at the partition level for areas where severe color drift is detected; The color drift compensation coefficient obtained in each area is compared with the color drift compensation coefficient reference threshold pre-set according to historical data. If the color drift compensation coefficient in the area is greater than or equal to the pre-set color drift compensation coefficient reference threshold, it means that high-precision compensation is required in the area; if the color drift compensation coefficient in the area is less than the pre-set color drift compensation coefficient reference threshold, it means that compensation can be skipped in the area.

[0045] For areas with severe drift, calculate brightness compensation, color compensation and gamma curve adjustment values ​​respectively If the partition color drift is large, adjust the RGB color components to restore them to the standard value, and calculate the partition Gamma curve adjustment value. The expression is: ;in: is the corrected Gamma value, γ is the standard Gamma value at the factory (such as 2.2), Adjust the gamma curve at the partition level to make color transitions smoother.

[0046] S6. Based on user usage patterns, color adaptive correction is performed regularly. If dynamic color cast is detected, the pixel refresh algorithm is used to eliminate the residual color effect.

[0047] Record user usage habits: monitor the usage time of LCD panels . Count the display ratio of highlight areas to low-brightness areas, and analyze the local brightness or color shift caused by long-term use. Record the display time of fixed UI elements (such as the status bar and navigation bar) to determine whether there is a local color memory effect.

[0048] Set the color correction trigger condition: If (i.e. the cumulative screen usage time exceeds the set threshold), color correction is triggered. If the color sensor detects that the local color drift ΔE>3 or ΔL>10%, local color correction is triggered.

[0049] Use pixel refresh algorithm to eliminate dynamic color cast: ;in: is the pixel status after refresh, is the current pixel state (RGB sub-pixel brightness), is the standard brightness value that the pixel should have (determined according to factory data), and η is the pixel refresh intensity (the value range is 0-1, the larger η is, the stronger the correction amplitude is).

[0050] If dynamic color cast is detected, color flashing is performed pixel by pixel, and the compensation color is displayed for a short time to restore the pixel status. If ΔE>5, multiple refresh cycles are performed to eliminate color residue. Combined with gamma compensation, the overall color tone is adjusted to ensure a natural transition of colors after correction. Re-detect the color offset. If ΔE<3, the correction is completed, otherwise continue to optimize.

[0051] In this embodiment, first, the color reference data of the liquid crystal panel, including the color gamut range, Gamma curve, color temperature parameters and pixel-level color response data, are collected to provide a reference for subsequent correction. Then, the color display state is detected in real time using a color sensor to obtain the brightness deviation, color drift and local color temperature changes in different areas. Based on these data, a machine learning model is used to predict the color shift trend and calculate the color drift compensation coefficient to accurately compensate for the impact of different environments on the panel color. Subsequently, the driving signal of the liquid crystal panel is dynamically adjusted according to the compensation coefficient, including backlight brightness optimization, RGB sub-pixel compensation and Gamma curve correction to ensure color accuracy. For areas with severe color drift, a local area correction strategy is adopted to perform partition-level color compensation to improve the color consistency of the entire screen. In addition, color adaptive correction is performed regularly in combination with the user's usage mode. If dynamic color cast (such as color memory effect) is detected, the residual color influence is eliminated by the pixel refresh algorithm to maintain a long-term stable color display effect. This method realizes high-precision and intelligent liquid crystal panel color management through intelligent analysis and dynamic compensation, and improves the user's visual experience and the color consistency of the display device.

[0052] Example 2, please refer to Figure 2 As shown, a color correction system for a liquid crystal panel described in this embodiment includes a color reference data storage module, a color detection module, a color shift prediction module, a color drive adjustment module, a local area color compensation module and a color adaptive correction module; Color reference data storage module: collects the color reference data of the LCD panel, including the color gamut range, gamma curve, color temperature parameters, and pixel-level color response data at the time of leaving the factory; Color detection module: Through the color sensor, the color display status of the LCD panel in different areas is detected in real time to obtain the brightness deviation, color drift and local color temperature changes of each area; Color shift prediction module: uses a color shift prediction model based on machine learning to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient; Color drive adjustment module: dynamically adjusts the driving signal of the LCD panel according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; Local area color compensation module: adopts local area correction strategy to perform partition-level color compensation for areas where serious color drift is detected; Color adaptive correction module: Based on the user's usage pattern, color adaptive correction is performed regularly. If dynamic color cast is detected, the pixel refresh algorithm is used to eliminate the residual color impact.

[0053] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0054] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0055] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0056] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A color correction method for a liquid crystal panel, characterized in that: The following steps are involved: S1: Collect color benchmark data of the LCD panel, including the color gamut range, gamma curve, color temperature parameters, and pixel-level color response data at the time of leaving the factory; S2: Use the color sensor to detect the color display status of the LCD panel in different areas in real time, and obtain the brightness deviation, color drift and local color temperature change of each area; S3: Use a color shift prediction model based on machine learning to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient; S4: Dynamically adjust the driving signal of the LCD panel according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; S5: adopt a local area correction strategy to perform color compensation at the partition level for areas where severe color drift is detected; S6: Regularly performs color adaptive correction based on user usage patterns. If dynamic color cast is detected, a pixel refresh algorithm is used to eliminate residual color effects.

2. The color correction method of a liquid crystal panel according to claim 1, characterized in that: The pixel-level color response data collected in S1 includes initial RGB sub-pixel brightness values, color uniformity data, and dynamic color response time of different areas of the liquid crystal panel.

3. The color correction method of a liquid crystal panel according to claim 2, characterized in that: In S2, the color display status of the LCD panel in different areas is detected in real time through the color sensor to obtain the brightness deviation, color drift and local color temperature change of each area, including: The test color card is displayed on the LCD panel, and the color sensor measures the actual color value of each area, recording the color value of each detection area. : Measures the brightness of the three primary colors of red, green and blue; Chromaticity coordinates (x, y): Measures the color coordinates according to the CIE 1931 color space; Color temperature value: Calculates the current color temperature of the panel and compares it with the standard color temperature; Calculate the brightness deviation using the formula: ;in: is the brightness deviation of the i-th detection area; The actual brightness value detected by the color sensor; It is the reference brightness value measured at the factory; Calculate the color drift amount using the formula: ;in: The color drift amount of the i-th area; L is the brightness component; a, b are the chromaticity coordinates in the CIE Lab color space; meas is the actual detection value, and ref is the factory reference value; Calculate the local color temperature change, the calculation formula is: ;in: is the color temperature deviation of the i-th detection area; The actual color temperature measured by the color sensor; This is the factory reference color temperature.

4. The color correction method of a liquid crystal panel according to claim 3, characterized in that: In S3, a color shift prediction model based on machine learning is used to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient, including: The brightness deviation, color drift and local color temperature change are converted into comprehensive feature vectors, and the comprehensive feature vectors are used as inputs of the machine learning model. The machine learning model uses each group of comprehensive feature vectors to predict the impact value labels of different usage environments on the color performance of each area of ​​the LCD panel as the prediction target, and takes minimizing the sum of the prediction errors of the impact value labels of all different usage environments on the color performance of each area of ​​the LCD panel as the training target. The machine learning model is trained until the sum of the prediction errors converges, and the model training is stopped. The color drift compensation coefficient is determined according to the model output results, wherein the machine learning model is a polynomial regression model.

5. The color correction method of a liquid crystal panel according to claim 4, characterized in that: In S4, the driving signal of the liquid crystal panel is dynamically adjusted according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; According to the brightness attenuation of different areas of the panel, adjust the local backlight brightness to ensure the overall screen brightness is consistent. The calculation formula is: ;in: is the adjusted backlight brightness value of the ith area, is the actual backlight brightness value of the current i-th area, is the color drift compensation coefficient, λ is the brightness compensation weight; if >0, increase the area LED backlight brightness, if <0, reduce the LED backlight brightness in the area. After the adjustment is completed, detect the brightness deviation again. If it still exceeds the threshold, perform fine-grained compensation. Specifically, if the brightness deviation ΔL exceeds 10% or the color drift ΔE > 3, perform local backlight brightness adjustment or increase the correction frequency at the pixel level.

6. The color correction method of a liquid crystal panel according to claim 5, characterized in that: To address the color drift phenomenon, the driving voltage of the RGB sub-pixels is adjusted, and the calculation formula is: ;in, , , is the adjusted RGB sub-pixel driving signal, is the original RGB driving signal, α, β, γ are the RGB compensation weights; if >5, perform high-intensity RGB compensation, including adjusting the compensation coefficient of the RGB sub-pixel drive voltage to 10%~20%; if 3 < ≤5, perform small RGB refinement compensation and adjust the compensation coefficient of RGB sub-pixel driving voltage to 5%~10%.

7. The color correction method of a liquid crystal panel according to claim 6, characterized in that: Correct the panel Gamma curve and restore the standard color display. The calculation formula is: ;in: is the output signal after Gamma correction, is the input signal, γ is the standard Gamma value, Indicates the amount of gamma adjustment based on the color drift compensation coefficient; the corrected gamma curve is calculated through the Gamma LUT to adjust the display color tone.

8. The color correction method of a liquid crystal panel according to claim 1, characterized in that: In S6, color adaptive correction is performed regularly based on user usage patterns. If dynamic color cast is detected, the residual color effect is eliminated through a pixel refresh algorithm; Monitor the usage time of LCD panel , count the display ratio of highlight areas to low-brightness areas, analyze the local brightness or color shift caused by long-term use; record the display time of fixed UI elements to determine whether there is a local color memory effect; set the color correction trigger condition: if , trigger color correction. If the color sensor detects that the local color drift ΔE>3 or ΔL>10%, local color correction is triggered.

9. The color correction method of a liquid crystal panel according to claim 8, characterized in that: Use pixel refresh algorithm to eliminate dynamic color cast: ;in: is the pixel status after refresh, is the current pixel state, is the standard brightness value that the pixel should have, η is the pixel refresh intensity; if dynamic color cast is detected, color flushing is performed pixel by pixel, and the compensation color is displayed for a short time to restore the pixel state; if ΔE>5, multiple refresh cycles are performed to eliminate color residue, and the overall tone is adjusted in combination with gamma compensation, and the color offset is re-detected. If ΔE<3, the correction is completed, otherwise the optimization continues.

10. A color correction system for a liquid crystal panel, used to implement a color correction method for a liquid crystal panel according to any one of claims 1 to 9, characterized in that: It includes a color reference data storage module, a color detection module, a color offset prediction module, a color drive adjustment module, a local area color compensation module and a color adaptive correction module; Color reference data storage module: collects the color reference data of the LCD panel, including the color gamut range, gamma curve, color temperature parameters, and pixel-level color response data at the time of leaving the factory; Color detection module: Through the color sensor, the color display status of the LCD panel in different areas is detected in real time to obtain the brightness deviation, color drift and local color temperature changes of each area; Color shift prediction module: uses a color shift prediction model based on machine learning to analyze the impact of different usage environments on the color performance of each area of ​​the LCD panel and calculate the color drift compensation coefficient; Color drive adjustment module: dynamically adjusts the driving signal of the LCD panel according to the color drift compensation coefficient, including backlight brightness distribution adjustment, RGB sub-pixel compensation and Gamma curve correction; Local area color compensation module: adopts local area correction strategy to perform partition-level color compensation for areas where serious color drift is detected; Color adaptive correction module: Based on the user's usage pattern, color adaptive correction is performed regularly. If dynamic color cast is detected, the pixel refresh algorithm is used to eliminate the residual color impact.

Images