A color difference detection system and method for liquid crystal display screen

Abstract

The present invention discloses a color difference detection system and method for a liquid crystal display screen, and relates to the technical field of color difference detection, and includes the following steps: obtaining an image to be detected, preprocessing the image to be detected, obtaining a standard image, obtaining historical interference factors, constructing a color difference compensation model, calculating a color difference compensation value according to the color difference compensation model, obtaining a second color difference, training a machine learning model for predicting the second color difference, wherein the output of the machine learning model is the second color difference, and testing the machine learning model. The present invention is conducive to accurately detecting color differences by preprocessing the image to be detected and the standard image and extracting color values, establishing a color difference compensation model, making the detection result more stable and reliable, and predicting the second color difference by training the machine learning model, thereby improving the accuracy and efficiency of detection, and is conducive to meeting the ever-changing market requirements, and bringing better product quality control and user experience guarantee.

Description

Technical Field

[0001] The present invention relates to the technical field of color difference detection, and in particular to a liquid crystal display screen color difference detection system and method. Background Art

[0002] In recent years, the color difference detection system has been developing towards a high degree of automation and intelligence. From image acquisition, preprocessing, color analysis to result reporting, the entire detection process can be completed in a short time, and can automatically determine whether it is qualified or unqualified according to preset standards. This automation has greatly improved efficiency and reduced interference from human factors.

[0003] At present, a Chinese invention patent with publication number CN 110596924 B discloses a device and method for detecting color difference of a liquid crystal display screen. The method, through the effect of a clamping mechanism, is convenient for stably clamping a liquid crystal display screen placed on the surface of a placement plate, thereby improving the stability of the placement of the liquid crystal display screen, facilitating workers to stably fix the liquid crystal display screen during the detection process, and improving the detection effect. However, the related technology does not compensate for the error of color difference detection, lacks detection accuracy, does not predict the color difference based on multiple parameters, and lacks intelligent analysis. Summary of the invention

[0004] The technical problem solved by the present invention is that the related art does not compensate for the error of color difference detection, lacks detection accuracy, does not predict the color difference based on multiple parameters, and lacks analysis intelligence.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: In the first aspect, a method for detecting color difference of a liquid crystal display screen comprises the following steps:

[0006] Step S1, obtaining an image to be detected, preprocessing the image to be detected, extracting a first color value of the preprocessed image to be detected, converting the first color value into a first channel component value, and converting the first channel component into a first brightness value, a first red to green axis value, and a first yellow to blue axis value;

[0007] Step S2, acquiring a standard image, extracting a second color value of the standard image, converting the second color value into a second channel component, and converting the second channel component into a second brightness value, a second red to green axis value, and a second yellow to blue axis value;

[0008] Step S3, calculating the first color difference between the image to be detected and the standard image according to the color difference formula, obtaining historical interference factors, constructing a color difference compensation model according to the historical interference factors, calculating the color difference compensation value according to the color difference compensation model, and performing weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference;

[0009] Step S4: training a machine learning model for predicting the second color difference, where the output of the machine learning model is the second color difference, and testing the machine learning model.

[0010] As a preferred solution of the method for detecting color difference of a liquid crystal display screen according to the present invention, step S1 includes the following sub-steps:

[0011] Step S11, obtaining an image to be detected, and preprocessing the image to be detected, wherein the preprocessing includes filtering and segmentation, and the image to be detected is segmented into a plurality of sub-images, and the sub-images are numbered;

[0012] Step S12, extracting the first color value of the sub-image, the first color value includes a first R value, a first G value and a first B value, converting the first color value into a first channel component value, the first channel component value is a first tristimulus value, and converting the first channel component into a first lightness value, a first red to green axis value and a first yellow to blue axis value according to the CIELAB color space.

[0013] As a preferred solution of the method for detecting color difference of a liquid crystal display screen according to the present invention, step S2 includes the following sub-steps:

[0014] Step S21, extracting feature quantities of the preprocessed image to be detected, the feature quantities including edge feature quantities, shape feature quantities and size feature quantities, calling an image database, inputting the feature quantities into the image database, matching images corresponding to the feature quantities, and setting the images corresponding to the feature quantities as standard images;

[0015] Step S22, extracting the second color value of the standard image, converting the second color value into a second channel component, converting the second channel component into a second lightness value, a second red to green axis value, and a second yellow to blue axis value, the second color value includes a second R value, a second G value, and a second B value, converting the second color value into a second channel component value, the second channel component value is a second tristimulus value, and converting the second channel component into a second lightness value, a second red to green axis value, and a second yellow to blue axis value according to the CIELAB color space.

[0016] As a preferred solution of the method for detecting color difference of a liquid crystal display screen according to the present invention, step S3 includes the following sub-steps:

[0017] Step S31, obtaining a first lightness value, a first red-to-green axis value, a first yellow-to-blue axis value, a second lightness value, a second red-to-green axis value, and a second yellow-to-blue axis value, and calculating a first color difference between the image to be detected and the standard image according to a color difference formula;

[0018] Step S32, obtaining historical interference factors, historical first color difference and historical actual color difference, and constructing a color difference compensation model according to the historical interference factors, wherein the construction logic of the color difference compensation model includes:

[0019] Calculate the difference between the historical first color difference and the historical actual color difference, set the difference as the color difference compensation value, the historical interference factors include the historical light brightness and the historical detection distance, take the color difference compensation value as the dependent variable, take the historical light brightness and the historical detection distance as the independent variables, perform multiple regression analysis, and obtain the color difference compensation model;

[0020] Step S33, calculating the compensated color difference according to the color difference compensation model, performing weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference.

[0021] As a preferred solution of the method for detecting color difference of a liquid crystal display screen according to the present invention, the calculation expression of the color difference compensation model is:

[0022]

[0023] Among them, S is the color difference compensation value, d i is the i-th interference factor, C i is the coefficient corresponding to the i-th interference factor, and n is the number of interference factors.

[0024] As a preferred solution of the method for detecting color difference of a liquid crystal display screen according to the present invention, step S4 includes the following sub-steps:

[0025] Step S41, taking the historical light illuminance and the historical detection distance, the second brightness value, the second red-to-green axis value, the second yellow-to-blue axis value and the second color difference as a sample set, and dividing the sample set into a test set and a training set according to a certain ratio;

[0026] Step S42, training a machine learning model for predicting the second color difference, wherein the input of the machine learning model is the historical interference factor, the second brightness value, the second red to green axis value, and the second yellow to blue axis value, and the output is the second color difference, and testing the machine learning model until the accuracy reaches the first accuracy threshold and the testing is stopped.

[0027] As a preferred solution of the method for detecting color difference of a liquid crystal display screen described in the present invention, the machine learning model uses the predicted second color difference as the output, the actual second color difference as the training target, and minimizing the difference between the predicted second color difference and the actual second color difference as the training standard.

[0028] In a second aspect, a color difference detection system for a liquid crystal display screen includes an acquisition module, a calculation module, a compensation module and a training module;

[0029] The acquisition module is used to acquire an image to be detected, preprocess the image to be detected, extract a first color value of the preprocessed image to be detected, convert the first color value into a first channel component value, convert the first channel component into a first brightness value, a first red to green axis value, and a first yellow to blue axis value, acquire a standard image, extract a second color value of the standard image, convert the second color value into a second channel component, and convert the second channel component into a second brightness value, a second red to green axis value, and a second yellow to blue axis value;

[0030] The calculation module is used to calculate the first color difference between the image to be detected and the standard image according to the color difference formula;

[0031] The compensation module is used to obtain historical interference factors, construct a color difference compensation model according to the historical interference factors, calculate a color difference compensation value according to the color difference compensation model, and perform weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference;

[0032] The training module is used to train a machine learning model for predicting the second color difference, the output of the machine learning model is the second color difference, and test the machine learning model.

[0033] In a third aspect, the present invention provides an electronic device comprising a memory, a processor and storage in the memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in any one of the methods described above are executed.

[0034] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps in any one of the methods described above are executed.

[0035] The beneficial effects of the present invention are as follows: by preprocessing and extracting color values ​​of the image to be detected and the standard image, converting them into channel components and brightness values, and using the color difference formula to calculate the first color difference, it is beneficial to accurately detect the color difference between the image to be detected and the standard image, thereby accurately evaluating the color performance of the liquid crystal display screen; by acquiring historical interference factors, establishing a color difference compensation model, and correcting the color difference changes caused by other factors, the detection result is made more stable and reliable and not easily affected by external interference; by training a machine learning model to predict the second color difference, the accuracy and efficiency of detection are improved; the machine learning model can learn complex color change patterns based on a large amount of training data, thereby more accurately predicting the color difference; through intelligent detection methods, the detection efficiency is improved, and continuous optimization and improvement are made, which is beneficial to meeting the ever-changing market requirements and bringing better product quality control and user experience guarantee. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 A schematic diagram of the basic flow of a method for detecting color difference of a liquid crystal display screen provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0038] Example 1, reference Figure 1 , as an embodiment of the present invention, provides a method for detecting color difference of a liquid crystal display screen, comprising the following steps:

[0039] Step S1, obtaining an image to be detected, preprocessing the image to be detected, extracting a first color value of the preprocessed image to be detected, converting the first color value into a first channel component value, and converting the first channel component into a first brightness value, a first red to green axis value, and a first yellow to blue axis value;

[0040] Step S2, acquiring a standard image, extracting a second color value of the standard image, converting the second color value into a second channel component, and converting the second channel component into a second brightness value, a second red to green axis value, and a second yellow to blue axis value;

[0041] Step S3, calculating the first color difference between the image to be detected and the standard image according to the color difference formula, obtaining historical interference factors, constructing a color difference compensation model according to the historical interference factors, calculating the color difference compensation value according to the color difference compensation model, and performing weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference;

[0042] Step S4: training a machine learning model for predicting the second color difference, where the output of the machine learning model is the second color difference, and testing the machine learning model.

[0043] The present invention performs preprocessing and color value extraction on the image to be detected and the standard image, converts them into channel components and brightness values, and uses the color difference formula to calculate the first color difference, which is conducive to accurately detecting the color difference between the image to be detected and the standard image, so as to accurately evaluate the color performance of the liquid crystal display screen. By acquiring historical interference factors, establishing a color difference compensation model, and correcting the color difference changes caused by other factors, the detection result is made more stable and reliable and not easily affected by external interference. The second color difference is predicted by training a machine learning model, which improves the accuracy and efficiency of detection. The machine learning model can learn complex color change patterns based on a large amount of training data, so as to more accurately predict the color difference. Through intelligent detection methods, the detection efficiency is improved, and continuous optimization and improvement are carried out, which is conducive to meeting the ever-changing market requirements and bringing better product quality control and user experience guarantee.

[0044] The step S1 includes the following sub-steps:

[0045] Step S11, obtaining an image to be detected, and preprocessing the image to be detected, wherein the preprocessing includes filtering and segmentation, and the image to be detected is segmented into a plurality of sub-images, and the sub-images are numbered;

[0046] Step S12, extracting the first color value of the sub-image, the first color value includes a first R value, a first G value and a first B value, converting the first color value into a first channel component value, the first channel component value is a first tristimulus value, and converting the first channel component into a first lightness value, a first red to green axis value and a first yellow to blue axis value according to the CIELAB color space.

[0047] The step S2 includes the following sub-steps:

[0048] Step S21, extracting feature quantities of the preprocessed image to be detected, the feature quantities including edge feature quantities, shape feature quantities and size feature quantities, calling an image database, inputting the feature quantities into the image database, matching images corresponding to the feature quantities, and setting the images corresponding to the feature quantities as standard images;

[0049] Step S22, extracting the second color value of the standard image, converting the second color value into a second channel component, converting the second channel component into a second lightness value, a second red to green axis value, and a second yellow to blue axis value, the second color value includes a second R value, a second G value, and a second B value, converting the second color value into a second channel component value, the second channel component value is a second tristimulus value, and converting the second channel component into a second lightness value, a second red to green axis value, and a second yellow to blue axis value according to the CIELAB color space.

[0050] In a specific implementation, the conversion expression between the tristimulus values ​​and the color value is:

[0051]

[0052] Among them, R, G and B are red value, green value and blue value respectively, and M, N and Q are tristimulus values ​​respectively.

[0053] The step S3 includes the following sub-steps:

[0054] Step S31, obtaining a first lightness value, a first red-to-green axis value, a first yellow-to-blue axis value, a second lightness value, a second red-to-green axis value, and a second yellow-to-blue axis value, and calculating a first color difference between the image to be detected and the standard image according to a color difference formula;

[0055] Step S32, obtaining historical interference factors, historical first color difference and historical actual color difference, and constructing a color difference compensation model according to the historical interference factors, wherein the construction logic of the color difference compensation model includes:

[0056] Calculate the difference between the historical first color difference and the historical actual color difference, set the difference as the color difference compensation value, the historical interference factors include the historical light brightness and the historical detection distance, take the color difference compensation value as the dependent variable, take the historical light brightness and the historical detection distance as the independent variables, perform multiple regression analysis, and obtain the color difference compensation model;

[0057] In a specific implementation, by preprocessing and extracting color values ​​of the image to be detected and the standard image, converting them into channel components and brightness values, and using the color difference formula to calculate the first color difference, it is helpful to accurately detect the color difference between the image to be detected and the standard image, thereby accurately evaluating the color performance of the LCD screen.

[0058] Step S33, calculating the compensated color difference according to the color difference compensation model, performing weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference.

[0059] The calculation expression of the color difference formula is:

[0060]

[0061] In a specific implementation, sc is the color difference, L1, a1 and b1 are respectively the first lightness value, the first red to green axis value and the first yellow to blue axis value, and L2, a2 ​​and b2 are respectively the second lightness value, the second red to green axis value and the second yellow to blue axis value.

[0062] The calculation expression of the chromatic aberration compensation model is:

[0063]

[0064] Among them, S is the color difference compensation value, di is the i-th interference factor, C i is the coefficient corresponding to the i-th interference factor, and n is the number of interference factors.

[0065] In the specific implementation, by obtaining historical interference factors, establishing a color difference compensation model, and correcting the color difference changes caused by other factors, the detection results are made more stable and reliable and less susceptible to external interference.

[0066] The step S4 includes the following sub-steps:

[0067] Step S41, taking the historical light illuminance and the historical detection distance, the second brightness value, the second red-to-green axis value, the second yellow-to-blue axis value and the second color difference as a sample set, and dividing the sample set into a test set and a training set according to a certain ratio;

[0068] Step S42, training a machine learning model for predicting the second color difference, wherein the input of the machine learning model is the historical interference factor, the second brightness value, the second red to green axis value, and the second yellow to blue axis value, and the output is the second color difference, and testing the machine learning model until the accuracy reaches the first accuracy threshold and the testing is stopped.

[0069] The machine learning model uses the predicted second color difference as an output, the actual second color difference as a training target, and minimizes the difference between the predicted second color difference and the actual second color difference as a training standard.

[0070] In specific implementations, the accuracy and efficiency of detection are improved by training a machine learning model to predict the second color difference. The machine learning model can learn complex color change patterns based on a large amount of training data, thereby predicting the color difference more accurately.

[0071] The present invention performs preprocessing and color value extraction on the image to be detected and the standard image, converts them into channel components and brightness values, and uses the color difference formula to calculate the first color difference, which is conducive to accurately detecting the color difference between the image to be detected and the standard image, so as to accurately evaluate the color performance of the liquid crystal display screen. By acquiring historical interference factors, establishing a color difference compensation model, and correcting the color difference changes caused by other factors, the detection result is made more stable and reliable and not easily affected by external interference. The second color difference is predicted by training a machine learning model, which improves the accuracy and efficiency of detection. The machine learning model can learn complex color change patterns based on a large amount of training data, so as to more accurately predict the color difference. Through intelligent detection methods, the detection efficiency is improved, and continuous optimization and improvement are carried out, which is conducive to meeting the ever-changing market requirements and bringing better product quality control and user experience guarantee.

[0072] It should be understood by those skilled in the art that the embodiments of the present invention can be provided as methods, systems or computer program products. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program codes. Among them, the storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read Only Memory, referred to as EPROM), programmable read-only memory (Programmable Red-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for detecting color difference of a liquid crystal display screen, characterized in that: The following steps are involved: Step S1, obtaining an image to be detected, preprocessing the image to be detected, extracting a first color value of the preprocessed image to be detected, converting the first color value into a first channel component value, and converting the first channel component into a first brightness value, a first red to green axis value, and a first yellow to blue axis value; Step S2, acquiring a standard image, extracting a second color value of the standard image, converting the second color value into a second channel component, and converting the second channel component into a second brightness value, a second red to green axis value, and a second yellow to blue axis value; Step S3, calculating the first color difference between the image to be detected and the standard image according to the color difference formula, obtaining historical interference factors, constructing a color difference compensation model according to the historical interference factors, calculating the color difference compensation value according to the color difference compensation model, and performing weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference; Step S4: training a machine learning model for predicting the second color difference, where the output of the machine learning model is the second color difference, and testing the machine learning model.

2. A method for detecting color difference of a liquid crystal display screen as claimed in claim 1, characterized in that: The step S1 includes the following sub-steps: Step S11, obtaining an image to be detected, and preprocessing the image to be detected, wherein the preprocessing includes filtering and segmentation, and the image to be detected is segmented into a plurality of sub-images, and the sub-images are numbered; Step S12, extracting the first color value of the sub-image, the first color value includes a first R value, a first G value and a first B value, converting the first color value into a first channel component value, the first channel component value is a first tristimulus value, and converting the first channel component into a first lightness value, a first red to green axis value and a first yellow to blue axis value according to the CIELAB color space.

3. A method for detecting color difference of a liquid crystal display screen as claimed in claim 1, characterized in that: The step S2 includes the following sub-steps: Step S21, extracting feature quantities of the preprocessed image to be detected, the feature quantities including edge feature quantities, shape feature quantities and size feature quantities, calling an image database, inputting the feature quantities into the image database, matching images corresponding to the feature quantities, and setting the images corresponding to the feature quantities as standard images; Step S22, extracting the second color value of the standard image, converting the second color value into a second channel component, converting the second channel component into a second lightness value, a second red to green axis value, and a second yellow to blue axis value, the second color value includes a second R value, a second G value, and a second B value, converting the second color value into a second channel component value, the second channel component value is a second tristimulus value, and converting the second channel component into a second lightness value, a second red to green axis value, and a second yellow to blue axis value according to the CIELAB color space.

4. A method for detecting color difference of a liquid crystal display screen as claimed in claim 1, characterized in that: The step S3 includes the following sub-steps: Step S31, obtaining a first lightness value, a first red-to-green axis value, a first yellow-to-blue axis value, a second lightness value, a second red-to-green axis value, and a second yellow-to-blue axis value, and calculating a first color difference between the image to be detected and the standard image according to a color difference formula; Step S32, obtaining historical interference factors, historical first color difference and historical actual color difference, and constructing a color difference compensation model according to the historical interference factors. The construction logic of the color difference compensation model includes: Calculate the difference between the historical first color difference and the historical actual color difference, set the difference as the color difference compensation value, the historical interference factors include the historical light brightness and the historical detection distance, take the color difference compensation value as the dependent variable, take the historical light brightness and the historical detection distance as the independent variables, perform multiple regression analysis, and obtain the color difference compensation model; Step S33, calculating the compensated color difference according to the color difference compensation model, performing weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference.

5. A method for detecting color difference of a liquid crystal display screen as claimed in claim 1, characterized in that: The calculation expression of the chromatic aberration compensation model is: Among them, S is the color difference compensation value, d i is the i-th interference factor, C i is the coefficient corresponding to the i-th interference factor, and n is the number of interference factors.

6. A method for detecting color difference of a liquid crystal display screen as claimed in claim 1, characterized in that: The step S4 includes the following sub-steps: Step S41, taking the historical light illuminance and the historical detection distance, the second brightness value, the second red-to-green axis value, the second yellow-to-blue axis value and the second color difference as a sample set, and dividing the sample set into a test set and a training set according to a certain ratio; Step S42, training a machine learning model for predicting the second color difference, wherein the input of the machine learning model is the historical interference factor, the second brightness value, the second red to green axis value, and the second yellow to blue axis value, and the output is the second color difference, and testing the machine learning model until the accuracy reaches the first accuracy threshold and the testing is stopped.

7. A method for detecting color difference of a liquid crystal display screen as claimed in claim 6, characterized in that: The machine learning model uses the predicted second color difference as an output, the actual second color difference as a training target, and minimizes the difference between the predicted second color difference and the actual second color difference as a training standard.

8. A color difference detection system for a liquid crystal display screen, characterized in that: It includes an acquisition module, a calculation module, a compensation module and a training module; The acquisition module is used to acquire an image to be detected, preprocess the image to be detected, extract a first color value of the preprocessed image to be detected, convert the first color value into a first channel component value, convert the first channel component into a first brightness value, a first red to green axis value, and a first yellow to blue axis value, acquire a standard image, extract a second color value of the standard image, convert the second color value into a second channel component, and convert the second channel component into a second brightness value, a second red to green axis value, and a second yellow to blue axis value; The calculation module is used to calculate the first color difference between the image to be detected and the standard image according to the color difference formula; The compensation module is used to obtain historical interference factors, construct a color difference compensation model according to the historical interference factors, calculate a color difference compensation value according to the color difference compensation model, and perform weighted calculation on the first color difference and the color difference compensation value to obtain a second color difference; The training module is used to train a machine learning model for predicting the second color difference, the output of the machine learning model is the second color difference, and test the machine learning model.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for detecting color difference of a liquid crystal display screen described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for detecting color difference of a liquid crystal display screen according to any one of claims 1 to 7 is implemented.

Images