Panel mura defect detection method, system and medium

Abstract

The present invention belongs to the field of defect detection technology and discloses a panel mura defect detection method, system, and medium. The method includes: acquiring a panel image, preprocessing the panel image to obtain a grayscale image; performing wavelet decomposition on the grayscale image based on a wavelet transform to obtain an image in the wavelet domain; enhancing the wavelet domain image based on an adaptive threshold function to obtain an enhanced image in the wavelet domain; converting the enhanced image in the wavelet domain to the spatial domain to obtain a spatial domain image; and post-processing the spatial domain image to obtain a mura defect detection result. The present invention converts the grayscale image to the wavelet domain and then enhances the wavelet domain image using an adaptive threshold function, which can effectively eliminate noise interference; then converts the image from the wavelet domain to the spatial domain and post-processes the spatial domain image to overcome the brightness influence of the image background. Therefore, the detection method of the present invention can effectively improve the accuracy and robustness of mura defect detection.

Description

Technical Field

[0001] The present invention belongs to the technical field of defect detection, and in particular relates to a panel mura defect detection method, system and medium. Background Art

[0002] Mura is a visual defect caused by uneven brightness or color in displays. It is common in LCD, OLED and other screens. It mainly manifests as patchy or linear color differences. The defective area has low contrast with the surrounding area and blurred boundaries. It usually requires tilted viewing angle and is particularly noticeable against a solid color background. Therefore, it can reduce display quality and affect the user experience (such as "yellow spots" or light leakage on the screen).

[0003] There are currently two types of mura detection methods:

[0004] Instrumental testing: Use an imaging photometer (such as the Konica Minolta ProMetric series) or an area photometer (RVS) to quantify brightness differences. However, instrumental testing relies on human perception, which can lead to high errors in the test results due to the high degree of subjectivity.

[0005] Algorithm Analysis: Polynomial surface fitting technology is used to separate background and defect areas and identify low-contrast mura. Due to the wide variety of display panel products, background modeling-based methods have poor robustness and are difficult to handle products with different manufacturing processes and different types of display panels.

[0006] Therefore, existing mura defect detection methods still have at least poor robustness and detection accuracy that needs to be improved. Summary of the Invention

[0007] The present invention aims to provide a panel mura defect detection method, system and medium to solve the problems that existing mura defect detection methods still have at least poor robustness and detection accuracy that needs to be improved.

[0008] In order to achieve the above object, the present invention adopts the following technical solutions:

[0009] In a first aspect, the present invention provides a panel mura defect detection method, the method comprising:

[0010] Acquire a panel image, and preprocess the panel image to obtain a grayscale image;

[0011] Perform wavelet decomposition on the grayscale image based on wavelet transform to obtain an image in wavelet domain;

[0012] The wavelet domain image is enhanced based on the adaptive threshold function to obtain the enhanced image in the wavelet domain;

[0013] Convert the enhanced image in the wavelet domain to the spatial domain to obtain a spatial domain image;

[0014] The spatial domain image is post-processed to obtain the mura defect detection results.

[0015] Preferably, the preprocessing includes at least grayscale conversion processing and median filtering processing.

[0016] Preferably, enhancing the wavelet domain image based on the adaptive threshold function to obtain an enhanced image in the wavelet domain includes:

[0017] Extract detail coefficients of images in wavelet domain;

[0018] The detail coefficient is enhanced based on the adaptive threshold function to obtain the enhanced detail coefficient;

[0019] Based on the enhanced detail coefficients, an enhanced image in the wavelet domain is obtained.

[0020] Preferably, the expression of the adaptive threshold function is:

[0021] ;

[0022] ;

[0023] Where, is the adaptive threshold function, is the threshold, N is the length of the wavelet coefficient of the wavelet transform, is the root mean square error of the wavelet coefficients of the wavelet transform, j is the number of layers of wavelet decomposition of the wavelet transform, is the kth detail coefficient of the jth layer, is an adjustable coefficient, ln() is the natural logarithm function, log 10 () is a logarithmic function with base 10.

[0024] Preferably, the calculation expression of the enhanced detail coefficient is:

[0025] ;

[0026] Where, is the kth detail coefficient of the jth layer, is the enhanced detail coefficient, is the preset coefficient, sgn() is the sign function, is the adaptive threshold function, is the threshold.

[0027] Preferably, post-processing the spatial domain image to obtain mura defect detection results includes:

[0028] Adjusting the grayscale value of the spatial domain image to obtain an adjusted spatial domain image;

[0029] Binarization is performed on the adjusted spatial domain image to obtain a binary image;

[0030] Extract white mura defects and black mura defects from binary images;

[0031] Based on the white value mura defect and the black value mura defect, the mura defect characteristics and their positions are determined, and the mura defect characteristics and their positions are used as the mura defect detection results.

[0032] Preferably, the method further comprises:

[0033] Construct an evaluation function;

[0034] Based on the evaluation function, the mura defect characteristics are evaluated to obtain an evaluation value of the mura defect characteristics;

[0035] Determine whether the evaluation value of the mura defect feature is less than a preset value. If so, remove the mura defect feature.

[0036] Preferably, the expression of the evaluation function is:

[0037] ;

[0038] Where, is the evaluation value of the i-th mura defect feature, is the area of ​​the i-th mura defect feature, is the brightness of the i-th mura defect feature, is the background brightness.

[0039] In a second aspect, the present invention provides a panel mura defect detection system for implementing the above-mentioned panel mura defect detection method, the system comprising:

[0040] An image acquisition module is used to acquire a panel image and pre-process the panel image to obtain a grayscale image;

[0041] A first conversion module is used to perform wavelet decomposition on the grayscale image based on wavelet transform to obtain an image in the wavelet domain;

[0042] An image enhancement module is used to enhance the wavelet domain image based on an adaptive threshold function to obtain an enhanced image in the wavelet domain;

[0043] A second conversion module is used to convert the enhanced image in the wavelet domain into the spatial domain to obtain a spatial domain image;

[0044] The image processing module is used to post-process the spatial domain image to obtain the mura defect detection result.

[0045] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned panel mura defect detection method when executing the computer program.

[0046] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which implements the above-mentioned panel mura defect detection method when executed by a processor.

[0047] Beneficial effects:

[0048] The present invention uses wavelet transform to convert a grayscale image to the wavelet domain, and then uses an adaptive threshold function to enhance the wavelet domain image, which can effectively eliminate noise interference. The image is then converted from the wavelet domain to the spatial domain, and the spatial domain image is post-processed to overcome the brightness influence of the image background. Therefore, the detection method of the present invention can effectively improve the accuracy and robustness of mura defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0050] Figure 1 This is a flow chart of a panel mura defect detection method provided by one embodiment of the present invention;

[0051] Figure 2 This is a block diagram of a panel mura defect detection system provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the present invention will be briefly introduced below in conjunction with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0053] Example 1

[0054] Figure 1 FIG. 1 is a flow chart of a panel mura defect detection method provided by an embodiment of the present invention. Figure 1 As shown, this embodiment provides a panel mura defect detection method, which is run on an intelligent detection device, which can be a PC. The method includes:

[0055] Step S10: Acquire a panel image, and pre-process the panel image to obtain a grayscale image.

[0056] In this embodiment, a CCD camera can be used to capture image data of the display panel, which is then uploaded to the intelligent detection device and stored in the memory of the intelligent detection device. When defect detection is required for the corresponding display panel image data, the corresponding display panel image data is extracted from the memory as a panel image to obtain the panel image. In this embodiment, the intelligent detection device can also perform real-time detection of the display panel. For example, a CCD camera can be used to capture image data of the display panel in real time. After uploading the image data of the display panel to the intelligent detection device, the intelligent detection device can directly perform defect detection on the image data of the display panel, thereby achieving real-time detection of panel mura defects.

[0057] In this embodiment, the preprocessing includes but is not limited to: grayscale conversion processing and median filtering processing.

[0058] Among them, gray-level transformation is the basic technology of digital image processing. By converting color images into single-channel grayscale images, it can achieve effective extraction of brightness information and subsequent processing optimization.

[0059] Median filtering is a nonlinear signal processing technique based on sorting statistics. Its core algorithm replaces the grayscale value of a target pixel in an image with the median of the grayscale values ​​of all pixels within its neighborhood window. Compared to linear filtering (such as mean filtering), its nonlinear nature enables it to achieve a better balance between noise suppression and edge preservation.

[0060] Step S20: performing wavelet decomposition on the grayscale image based on wavelet transform to obtain an image in the wavelet domain.

[0061] In this embodiment, the wavelet transform (WT) is a new transform analysis method that inherits and develops the localized concept of the short-time Fourier transform (STFT), while overcoming shortcomings such as the invariance of window size with frequency. It provides a frequency-dependent "time-frequency" window, making it an ideal tool for signal time-frequency analysis and processing. Its key features include its ability to highlight specific aspects of a problem through transformation, localized analysis of time (space) and frequency, and the gradual multi-scale refinement of signals (functions) through scaling and translation operations, ultimately achieving time subdivision at high frequencies and frequency subdivision at low frequencies. It automatically adapts to the requirements of time-frequency signal analysis, allowing for precise focus on any detail of the signal.

[0062] After decomposing a grayscale image through wavelet transform, wavelet coefficients are obtained. These wavelet coefficients reflect the energy distribution characteristics of the grayscale image at multiple scales (frequency domain) and multiple locations (time / space domain). The scale dimension corresponds to different frequency components. Low-scale (high-frequency) coefficients (detail coefficients) reflect signal mutations or details, while high-scale (low-frequency) coefficients (approximation coefficients) characterize signal trends or overall characteristics.

[0063] Step S30: enhancing the wavelet domain image based on the adaptive threshold function to obtain an enhanced image in the wavelet domain.

[0064] In this embodiment, since wavelet transforms contain noise, denoising and enhancing the wavelet domain image is necessary. Noise signals are generally random, so their variance is often unknown. Therefore, a threshold must be estimated during the denoising process. Samples are selected using a suitable method, and then a threshold is estimated and selected, retaining coefficients exceeding this threshold. Commonly used threshold estimation methods include: fixed threshold, adaptive threshold based on unbiased likelihood estimation, and heuristic threshold.

[0065] In this embodiment, the core of wavelet domain image denoising is the setting of the threshold and threshold function. The threshold and threshold function directly affect the quality and accuracy of wavelet domain image denoising. For example, if the threshold is set too high, the useful signal will be filtered as noise; if it is set too low, the noise filtering will not be thorough enough. Therefore, this embodiment implements wavelet domain image denoising through the following steps:

[0066] Step S301: extracting detail coefficients of the image in the wavelet domain; in this embodiment, low-scale coefficients are extracted from the multi-scale (frequency domain) wavelet coefficients in step S20, and the low-scale coefficients are the detail coefficients.

[0067] Step S302: enhancing the detail coefficient based on the adaptive threshold function to obtain the enhanced detail coefficient.

[0068] In this embodiment, the expression of the adaptive threshold function is:

[0069] ;

[0070] ;

[0071] Where, is the adaptive threshold function, is the threshold, N is the length of the wavelet coefficient of the wavelet transform, is the root mean square error of the wavelet coefficients of the wavelet transform, j is the number of layers of wavelet decomposition of the wavelet transform, is the kth detail coefficient of the jth layer, is an adjustable coefficient, ln() is the natural logarithm function, log 10 () is a logarithmic function with base 10; the value range of the adjustable coefficient is: ∈(0,1).

[0072] In this embodiment, the above threshold , which can filter out more noise and improve the accuracy of absence detection.

[0073] As a further optimization of this embodiment, the calculation expression of the enhanced detail coefficient is:

[0074] ;

[0075] Where, is the kth detail coefficient of the jth layer, is the enhanced detail coefficient, is the preset coefficient, sgn() is the sign function, is the adaptive threshold function, is the threshold, where the preset coefficient The value range of is: ∈[0,1].

[0076] In this embodiment, the calculation function of the enhanced detail coefficient can achieve the following: Continuous and without interruption.

[0077] Moreover, the calculation function of the enhanced detail coefficient will not allow the detail coefficient to be directly taken as zero, which can retain more useful detail coefficients and thus improve the subsequent defect detection accuracy.

[0078] Secondly, you can also adjust the adjustable coefficient , and then make the value of F adjustable, which can make the value of detail coefficient larger, and also adjust the preset coefficient , which can make the algorithm adapt to the denoising of different products and improve the robustness of the algorithm.

[0079] Step S303: obtaining an enhanced image in the wavelet domain based on the enhanced detail coefficients. In this embodiment, the wavelet domain image corresponding to the enhanced detail coefficients is used as the enhanced image in the wavelet domain.

[0080] Step S40: converting the enhanced image in the wavelet domain to the spatial domain to obtain a spatial domain image; in this embodiment, the inverse transform of the wavelet transform is used to convert the wavelet domain to the spatial domain to achieve reconstruction of the spatial domain image.

[0081] Step S50: post-processing the spatial domain image to obtain a mura defect detection result.

[0082] In this embodiment, the spatial domain image is post-processed to obtain mura defect detection results, including:

[0083] Step S501: adjusting the grayscale value of the spatial domain image to obtain an adjusted spatial domain image; at this time, the adjusted spatial domain image contains mura defects, wherein the grayscale value of the spatial domain image includes two types of mura defects, namely white mura defects and black mura defects.

[0084] In this embodiment, the function expression of the adjusted spatial domain image is:

[0085] ;

[0086] Where, is the grayscale value of the adjusted spatial domain image, is the coordinate of the grayscale value, is the grayscale value of the white mura defect, is the grayscale value of the black mura defect.

[0087] in, ;

[0088] ;

[0089] Where, For spatial domain images in coordinates The gray value at The background grayscale offset corresponding to the white mura defect is usually set to the median of the image grayscale range, such as 128. The background grayscale offset corresponding to the black mura defect is usually set to the highest value of the image grayscale range, such as 255. n is the number of bits of the spatial domain image.

[0090] Step S502: binarizing the adjusted spatial domain image to obtain a binary image, thereby distinguishing the mura defect from the background.

[0091] Step S503 : extracting white mura defects and black mura defects from the binary image. The white mura defects are white mura defects, and the black mura defects are black mura defects.

[0092] Step S504 : determining mura defect characteristics and positions based on the white value mura defect and the black value mura defect, and using the mura defect characteristics and positions as mura defect detection results.

[0093] In this embodiment, morphological processing, such as disconnection processing, is performed on the binary image to reduce the influence of background noise and determine the location of the mura defect feature. The size of the radius structure element of the disconnection processing needs to be adjusted according to the size of the mura defect.

[0094] As a further optimization of this embodiment, the method further includes:

[0095] Step a10: constructing an evaluation function; wherein the evaluation function is mainly constructed based on parameters such as the area of ​​the mura defect, the brightness of the defect, and the background brightness.

[0096] Step a20: Evaluate the mura defect feature based on the evaluation function to obtain an evaluation value of the mura defect feature.

[0097] Step a30: determining whether the evaluation value of the mura defect feature is less than a preset value; if so, removing the mura defect feature.

[0098] Therefore, the expression of the evaluation function is:

[0099] ;

[0100] Where, is the evaluation value of the i-th mura defect feature, is the area of ​​the i-th mura defect feature, is the brightness of the i-th mura defect feature, is the background brightness.

[0101] In this embodiment, when the evaluation value of any mura defect characteristic is less than a preset value, it indicates that the severity of the mura defect is relatively low. In this case, the human eye cannot detect the severity of the mura defect, and such products can be classified as medium- or low-grade products. If the mura defect characteristic exceeds the preset value, it indicates that the severity of the mura defect is relatively severe, and such products are classified as unqualified products. Products without mura defect characteristics are classified as high-grade qualified products, thereby achieving product grading.

[0102] The present invention uses wavelet transform to convert a grayscale image to the wavelet domain, and then uses an adaptive threshold function to enhance the wavelet domain image, which can effectively eliminate noise interference. The image is then converted from the wavelet domain to the spatial domain, and the spatial domain image is post-processed to overcome the brightness influence of the image background. Therefore, the detection method of the present invention can effectively improve the accuracy and robustness of mura defect detection.

[0103] Example 2

[0104] Figure 2 FIG. 1 is a block diagram of a panel mura defect detection system provided by an embodiment of the present invention. Figure 2 As shown, this embodiment provides a panel mura defect detection system for implementing the panel mura defect detection method in embodiment 1, and the system includes:

[0105] An image acquisition module is used to acquire a panel image and pre-process the panel image to obtain a grayscale image;

[0106] A first conversion module is used to perform wavelet decomposition on the grayscale image based on wavelet transform to obtain an image in the wavelet domain;

[0107] An image enhancement module is used to enhance the wavelet domain image based on an adaptive threshold function to obtain an enhanced image in the wavelet domain;

[0108] A second conversion module is used to convert the enhanced image in the wavelet domain into the spatial domain to obtain a spatial domain image;

[0109] The image processing module is used to post-process the spatial domain image to obtain the mura defect detection result.

[0110] This embodiment further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the panel mura defect detection method in the first embodiment is implemented.

[0111] This embodiment further provides a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the panel mura defect detection method in the first embodiment is implemented.

[0112] The present invention uses wavelet transform to convert a grayscale image to the wavelet domain, and then uses an adaptive threshold function to enhance the wavelet domain image, which can effectively eliminate noise interference. The image is then converted from the wavelet domain to the spatial domain, and the spatial domain image is post-processed to overcome the brightness influence of the image background. Therefore, the detection method of the present invention can effectively improve the accuracy and robustness of mura defect detection.

[0113] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or boxes.

[0115] The above are merely embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A panel mura defect detection method, characterized in that: The method comprises: Acquire a panel image, and preprocess the panel image to obtain a grayscale image; Perform wavelet decomposition on the grayscale image based on wavelet transform to obtain an image in wavelet domain; The wavelet domain image is enhanced based on an adaptive threshold function to obtain an enhanced image in the wavelet domain, including: extracting detail coefficients of the wavelet domain image; enhancing the detail coefficients based on the adaptive threshold function to obtain enhanced detail coefficients; the expression of the adaptive threshold function is: ； ； Where, is the adaptive threshold function, is the threshold, N is the length of the wavelet coefficient of the wavelet transform, is the root mean square error of the wavelet coefficients of the wavelet transform, j is the number of layers of wavelet decomposition of the wavelet transform, is the kth detail coefficient of the jth layer, is an adjustable coefficient, ln() is the natural logarithm function, log 10 () is a logarithmic function with base 10; the calculation expression of the enhanced detail coefficient is: ； Where, is the kth detail coefficient of the jth layer, is the enhanced detail coefficient, is the preset coefficient, sgn() is the sign function, is the adaptive threshold function, is the threshold; based on the enhanced detail coefficient, the enhanced image in the wavelet domain is obtained; Convert the enhanced image in the wavelet domain to the spatial domain to obtain a spatial domain image; The spatial domain image is post-processed to obtain the mura defect detection results.

2. The panel mura defect detection method according to claim 1, characterized in that: The preprocessing at least includes: grayscale conversion processing and median filtering processing.

3. The panel mura defect detection method according to claim 1, characterized in that: Post-process the spatial domain image to obtain mura defect detection results, including: Adjusting the grayscale value of the spatial domain image to obtain an adjusted spatial domain image; Binarization is performed on the adjusted spatial domain image to obtain a binary image; Extract white mura defects and black mura defects from binary images; Based on the white value mura defect and the black value mura defect, the mura defect characteristics and their positions are determined, and the mura defect characteristics and their positions are used as the mura defect detection results.

4. The panel mura defect detection method according to claim 1, characterized in that: The method further comprises: Construct an evaluation function; Based on the evaluation function, the mura defect characteristics are evaluated to obtain an evaluation value of the mura defect characteristics; Determine whether the evaluation value of the mura defect feature is less than a preset value. If so, remove the mura defect feature.

5. The panel mura defect detection method according to claim 4, characterized in that: The expression of the evaluation function is: ； Where, is the evaluation value of the i-th mura defect feature, is the area of ​​the i-th mura defect feature, is the brightness of the i-th mura defect feature, is the background brightness.

6. A panel mura defect detection system, used to implement the panel mura defect detection method according to any one of claims 1 to 5, characterized in that: The system comprises: An image acquisition module is used to acquire a panel image and pre-process the panel image to obtain a grayscale image; A first conversion module is used to perform wavelet decomposition on the grayscale image based on wavelet transform to obtain an image in the wavelet domain; The image enhancement module is used to enhance the wavelet domain image based on the adaptive threshold function to obtain an enhanced image in the wavelet domain, including: extracting the detail coefficients of the wavelet domain image; enhancing the detail coefficients based on the adaptive threshold function to obtain the enhanced detail coefficients; the expression of the adaptive threshold function is: ； ； Where, is the adaptive threshold function, is the threshold, N is the length of the wavelet coefficient of the wavelet transform, is the root mean square error of the wavelet coefficients of the wavelet transform, j is the number of layers of wavelet decomposition of the wavelet transform, is the kth detail coefficient of the jth layer, is an adjustable coefficient, ln() is the natural logarithm function, log 10 () is a logarithmic function with base 10; the calculation expression of the enhanced detail coefficient is: ； Where, is the kth detail coefficient of the jth layer, is the enhanced detail coefficient, is the preset coefficient, sgn() is the sign function, is the adaptive threshold function, is the threshold; based on the enhanced detail coefficient, the enhanced image in the wavelet domain is obtained; A second conversion module is used to convert the enhanced image in the wavelet domain into the spatial domain to obtain a spatial domain image; The image processing module is used to post-process the spatial domain image to obtain the mura defect detection result.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the panel mura defect detection method according to any one of claims 1 to 5 is implemented.

Images