Light guide plate defect sample enhancement and detection integrated method

Abstract

The application discloses a light guide plate defect sample enhancement and detection integrated method and relates to the technical field of light guide plate detection, which comprises the following steps: marking all the net points based on the front view of the light guide plate; acquiring the same-distance defect features by using the same-distance analysis method; acquiring the adjacent-distance net point analysis method; when the defect detection is performed on the light guide plate, the defect sample area and the influence detection area in the light guide plate are acquired; the application is used to solve the problem that in the existing light guide plate defect sample enhancement and detection method, the net point defect detection in the light guide plate cannot be based on the defect type of the net point, the defect hidden danger caused by the influence of the net point cannot be effectively analyzed, and the defect detection precision is low.

Description

Technical Field

[0001] This invention relates to the field of light guide plate inspection technology, specifically to an integrated method for enhancing and detecting defective light guide plate samples. Background Technology

[0002] A light guide plate is an optical element made of optical-grade acrylic or polycarbonate sheets. Light guide points are engraved on the bottom surface of the sheet through a special process, which transforms point light sources into uniform surface light sources. Its core principle is that light is refracted and diffused multiple times through the light guide points in the sheet and then emitted uniformly from the front. At the same time, light leakage from the bottom is recovered through a reflective sheet to improve light efficiency. Defects of light guide plates mainly include scratches, weld lines, and defects in dot design.

[0003] Existing methods for enhancing and detecting defect samples in light guide plates typically involve preprocessing and segmenting the original image of the light guide plate, then enhancing the defective areas to obtain flawed points, thus achieving detection accuracy. While this improved method automates defect detection through machine vision, it lacks a method for classifying the affected areas of the defective dots within the light guide plate. This results in lower defect detection accuracy because it cannot effectively analyze areas not classified as flawed points when defects exist within the light guide plate, based on the defect type. Furthermore, it fails to effectively classify all areas affected by the same defect. For example, patent application CN111257348A discloses a machine vision-based method for detecting defects in LED light guide plates. This method automates image segmentation and defect classification detection of light guide plates by combining image acquisition and lighting schemes with machine vision. Effective image enhancement and preprocessing methods improve detection accuracy and precision without compromising efficiency. However, other improvements to light guide plate defect sample enhancement and detection methods typically target specific defects within the light guide plate. These methods fail to address the issue of identifying dot defects within the light guide plate. They lack methods for segmenting the affected areas of defective dots, making it impossible to effectively analyze regions affected by the same defect but not classified as defective points due to stable detection parameters during enhancement. This results in low defect detection accuracy and an inability to effectively segment all areas affected by the same defect. Therefore, it is necessary to improve existing light guide plate defect sample enhancement and detection methods. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art by proposing an integrated method for enhancing and detecting defect samples of light guide plates. This method addresses the lack of a detection method for classifying the affected areas of defective dots within the light guide plate. Consequently, when defects exist in the light guide plate's dots, it is impossible to effectively analyze areas affected by the dot defects but not classified as defective points due to the relatively stable detection parameters during enhancement. This results in low defect detection accuracy and the inability to effectively classify all areas affected by the same defect.

[0005] To achieve the above objectives, this application provides an integrated method for enhancing and detecting defect samples in light guide plates, comprising the following steps:

[0006] Based on the front view of the light guide plate, the entrance of the light source and the position of all dots in the light guide plate are obtained, and all dots are marked based on the distance between each dot and the entrance of the light source. The same distance analysis method is used to analyze all marked dots, and the same distance defect characteristics of each dot are obtained based on the analysis results.

[0007] Based on the in-spacing defect characteristics of each dot, the in-spacing defect group of each dot in the light guide plate is obtained, and the adjacent dot analysis method is used to analyze all in-spacing defect groups. Based on the analysis results, the adjacent defect influence characteristics of each dot are obtained.

[0008] When performing defect detection on a light guide plate, the defect sample area and the area affecting detection are obtained within the light guide plate based on the in-situ defect characteristics of each grid point and the adjacent defect influence characteristics of all grid points within all in-situ defect grid groups.

[0009] Furthermore, based on the front view of the light guide plate, the entrance to the light source and the positions of all halftone dots in the light guide plate are obtained, and all halftone dots are marked based on their distance from the entrance to the light source, including:

[0010] Obtain the front view of the light guide plate and denote it as the front light plate view; denote the point corresponding to the entrance of the light source in the front light plate view as the light source point; establish a plane rectangular coordinate system and denote it as the front plate analysis coordinate system, where the units of the X-axis and Y-axis of the front plate analysis coordinate system are both cm; place the front light plate view in the front plate analysis coordinate system, where the light source point in the front light plate view coincides with the origin of the coordinate system.

[0011] The positions of all dots in the light guide plate are obtained based on laser scanning positioning, and the positions of all dots in the light guide plate are marked in the positive plate analysis coordinate system; the distance between each dot and the origin of the coordinate system is obtained and recorded as the optical distance of the dot; for any dot α in the positive plate analysis coordinate system, the dots with the same optical distance as the dot α are recorded as the dots with the same distance as dot α.

[0012] Furthermore, the same-distance analysis method includes:

[0013] Based on the historical usage records of the light guide plate, defects caused by process parameters in the dot matrix of the light guide plate were obtained and denoted as process defect GQ1 to process defect GQ. t ;

[0014] For any process defect GQ u And any dot α in the light guide plate: all dots at the same distance from dot α are recorded as dots to be tested, where u is a positive integer less than or equal to t and greater than or equal to 1; based on the historical usage records of the light guide plate, the light source that passes through the light guide plate the most times is recorded as the passable light source.

[0015] Furthermore, the same-distance analysis method also includes:

[0016] Place dots with good process parameters at the locations of all dots to be tested. With the light source point corresponding to the position inside the light guide plate, pass a passable light source into the light guide plate to obtain the grayscale image corresponding to the front light plate image at this time, and record it as a fully intact grayscale image.

[0017] The pixel ratio corresponding to each test dot in the fully intact grayscale image is obtained by using the dot ratio analysis method, and recorded as the standard ratio of the test dot.

[0018] The dot ratio analysis method includes: recording all pixels covered by the dot to be tested as the standard pixels of the dot to be tested; obtaining the gray values ​​of all standard pixels; recording the mode of all gray values ​​as the standard gray value; recording the number of all standard pixels as t1; recording the number of all standard pixels whose gray values ​​are the standard gray values ​​as t2; and recording the value of t2 divided by t1 as the pixel ratio of the dot to be tested.

[0019] Furthermore, the same-distance analysis method also includes:

[0020] Place GQ samples with manufacturing defects at the locations of all test sites. u The dots are located at the positions of the light source points within the light guide plate. A passable light source is introduced into the light guide plate to obtain the grayscale image corresponding to the front light plate image at this time, and it is recorded as a fully incomplete grayscale image.

[0021] The pixel ratio of each test dot within the fully incomplete grayscale image is obtained using the dot ratio analysis method, and recorded as the full incomplete ratio of the test dot.

[0022] Furthermore, the same-distance analysis method also includes:

[0023] A GQ device with a manufacturing defect was placed at the location of dot α. u The dots are located at the positions of the light source points within the light guide plate. A passable light source is introduced into the light guide plate to obtain the grayscale image corresponding to the front light plate image at this time, and it is recorded as the dot-incomplete grayscale image.

[0024] The pixel ratio of each test dot in the grayscale image with missing dots is obtained by using the dot ratio analysis method, and recorded as the dot ratio of the test dot; the standard ratio of dot α is subtracted from the full missing ratio, and recorded as the missing difference value of dot α.

[0025] For any test point other than point α: when the value of the standard ratio of the test point minus the point defect ratio is less than or equal to the defect difference value, the test point is recorded as a point defect image point.

[0026] Furthermore, the same-distance analysis method also includes:

[0027] In the positive plate analysis coordinate system, the curve obtained by fitting the halftone point α with all the residual image points is denoted as the process defect GQ of halftone point α. u Characteristics of defects at the same distance during the same time;

[0028] Obtain the same-distance defect characteristics of all nodes under all process defects.

[0029] Furthermore, based on the in-spacing defect characteristics of each dot, the in-spacing defect group of each dot within the light guide plate is obtained as follows:

[0030] For any dot α in the light guide plate: all dots corresponding to dot α in the same distance defect characteristics of all process defects are denoted as the same distance defect group of dot α; the adjacent dot analysis method is used to analyze each dot in the same distance defect group, and the adjacent defect influence characteristics of dot α are obtained based on the analysis results.

[0031] Furthermore, the adjacent node analysis method includes:

[0032] For any dot β within the same-distance defect group: when dot β is recorded as a dot within the same-distance defect group of dot α, the process defect of dot α is recorded as the same-distance influence defect of dot β, where dot β can correspond to multiple same-distance influence defects.

[0033] In the front light plate image, with halftone dot β as the center, the point closest to halftone dot β in each direction is recorded as the neighboring point of halftone dot β, and halftone dots in the same distance defect group as halftone dot α are removed from the neighboring points of halftone dot β.

[0034] For any in-situ defect of dot β: place a dot with in-situ defect at the location of dot β, and guide the light source into the light guide plate according to the position of the light source point in the light guide plate. Obtain the grayscale image corresponding to the front light plate image at this time, and record it as the adjacent defective grayscale image.

[0035] The pixel ratio of each neighboring point in the adjacent incomplete grayscale image is obtained by using the dot ratio analysis method, and recorded as the neighboring incomplete ratio of the neighboring point; when the neighboring incomplete ratio of the neighboring point is less than the standard ratio of the neighboring point, the neighboring point is recorded as the neighboring influence point.

[0036] The scatter plot formed by all neighboring influence points and grid point β is denoted as the neighboring influence plot of grid point β;

[0037] Obtain the neighbor effect diagram corresponding to all in-distance defects at point β;

[0038] Obtain the neighbor influence map of all in-spacing defects affecting all points within the in-spacing defect group; for any process defect GQ u All defects with the same distance as the influence are classified as process defects (GQ). u The minimum bounding region of the scatter plot formed by the neighbor influence diagram of the dots in the positive plate analysis coordinate system is denoted as the area of ​​dot α with respect to the process defect GQ. u The area affected by the defect;

[0039] The defect influence area of ​​point α with respect to all process defects is denoted as the adjacent defect influence feature of point α.

[0040] Furthermore, when performing defect detection on the light guide plate, based on the in-situ defect characteristics of each dot and the adjacent defect influence characteristics of all dots within all in-situ defect dot groups, the defect sample area and the area affecting detection within the light guide plate are obtained, including:

[0041] When performing defect detection on the light guide plate, for any halftone dot γ that has been detected: the defect present in halftone dot γ is recorded as the detected defect, the same-distance defect feature of halftone dot γ when the defect is detected is recorded as the main analysis area, and the defect influence area of ​​process defect in the adjacent defect influence feature of halftone dot γ is recorded as the adjacent point influence area.

[0042] The area where the main analysis region intersects with the adjacent point influence region is recorded as the defect sample region when performing γ-detection on the network points, and the area other than the defect sample region in the main analysis region and the adjacent point influence region is recorded as the influence detection region.

[0043] The beneficial effects of this invention are as follows: First, based on the front view of the light guide plate, the entry point of the light source and the position of all dots in the light guide plate are obtained, and all dots are marked. The same-distance analysis method is used to analyze all marked dots, and the same-distance defect features of each dot are obtained based on the analysis results. The advantage of this is that by obtaining the same-distance defect features of each dot in the light guide plate, the mutual influence state of dots in the light guide plate that are at the same distance from the light source entry point when defects exist can be effectively obtained. This allows for the acquisition of other dots that are affected by the dot defects and have the same light distance when dot defects exist. This facilitates the effective framing of areas that are affected by dot defects and have potential defects but are not classified as defect points due to the relatively stable detection parameters when the defect area is enhanced, based on the defect type of the dots in subsequent analysis. This improves the defect detection accuracy.

[0044] This application also obtains the same-distance defect network group of each dot within the light guide plate based on the same-distance defect characteristics of each dot, and analyzes all the same-distance defect network groups using the adjacent dot analysis method, and obtains the adjacent defect influence characteristics of each dot based on the analysis results; finally, when performing defect detection on the light guide plate, the defect sample area and the influence detection area within the light guide plate are obtained based on the same-distance defect characteristics of each dot and the adjacent defect influence characteristics of all dots within all the same-distance defect network groups. The advantage of this is that by obtaining the same-distance defect network group based on the same-distance defect characteristics and further obtaining the adjacent defect influence characteristics, when there is a defect at a dot, based on other dots affected by the dot defect and with the same optical distance, it is possible to further obtain dots that may have potential defects caused by other dots, so that the obtained defect sample area and influence detection area can respectively reflect the area directly affected by the defect dot and the area indirectly affected by the defect dot, thereby avoiding the problem that the detection parameters are relatively stable when the defect location is enhanced, resulting in the area not being classified as a defect point being effectively analyzed, causing low defect detection accuracy and the inability to effectively classify all areas affected by the same defect. Attached Figure Description

[0045] Figure 1 This is a flowchart of the steps of the method of the present invention;

[0046] Figure 2 This is a schematic diagram of the positive plate analysis coordinate system of the present invention;

[0047] Figure 3 This is a schematic diagram of the curves corresponding to the same-distance defect group of the present invention;

[0048] Figure 4 This is a schematic diagram of the neighbor influence diagram of the present invention;

[0049] Figure 5 This is a schematic diagram illustrating the acquisition of the defect-affected area in this invention;

[0050] Figure 6 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0051] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0052] Example 1, please refer to Figure 1 As shown, this application provides an integrated method for enhancing and detecting defect samples in light guide plates, comprising the following steps:

[0053] Step S1: Based on the front view of the light guide plate, obtain the entrance of the light source and the position of all dots in the light guide plate, and mark all dots based on the distance between all dots and the entrance of the light source; use the same distance analysis method to analyze all marked dots, and obtain the same distance defect characteristics of each dot based on the analysis results.

[0054] Step S1 includes: Step S101, obtaining a front view of the light guide plate and recording it as the front light plate view; recording the point corresponding to the entrance of the light source in the front light plate view as the light source point; establishing a plane rectangular coordinate system and recording it as the front plate analysis coordinate system, wherein the units of the X-axis and Y-axis of the front plate analysis coordinate system are both cm; placing the front light plate view in the front plate analysis coordinate system, wherein the light source point in the front light plate view coincides with the origin of the coordinate system.

[0055] In the specific implementation process, the purpose of setting up the positive plate analysis coordinate system is to be able to clearly obtain the position of all dots in the light guide plate. At the same time, when subsequently obtaining the same distance defect features, adjacent distance defect influence features, defect sample areas and influence detection areas, the position of each feature or area corresponding to each feature or area can be obtained more intuitively in the positive plate analysis coordinate system, thereby improving the efficiency of data analysis and the efficiency of defect repair by staff.

[0056] Step S102: Based on laser scanning positioning, obtain the position of all dots in the light guide plate, and mark the position of all dots in the light guide plate in the positive plate analysis coordinate system; obtain the distance between each dot and the origin of the coordinate system, and record it as the optical distance of the dot; for any dot α in the positive plate analysis coordinate system, the dot with the same optical distance as the dot α is recorded as the dot with the same distance as dot α.

[0057] In the specific implementation process, the distance between the dot and the origin of the coordinate system is the straight-line distance between the dot inside the light guide plate and the light source access point.

[0058] Step S103, the same-distance analysis method includes: Step S1031, based on the historical usage records of the light guide plate, obtaining the defects in the light guide plate caused by process parameters, and recording them as process defect GQ1 to process defect GQ respectively. t ;

[0059] In the specific implementation, process defects may include dot scratches, foreign matter contamination, fusion marks, and dot delamination. The specific process defects can be set according to the defects that may exist at the dots in the actual light guide plate, so as to ensure that the subsequent analysis can fit the various defect situations in the actual use of the light guide plate.

[0060] Step S1032, for any process defect GQ u And any dot α in the light guide plate: all dots at the same distance from dot α are recorded as dots to be tested, where u is a positive integer less than or equal to t and greater than or equal to 1; based on the historical usage records of the light guide plate, the light source that passes through the light guide plate the most times is recorded as the passable light source;

[0061] In the specific implementation process, the purpose of selecting the halftone dots at the same distance as the halftone dots to be tested is that, since the distance of the halftone dots at the same distance from the light source entrance is the same as the distance of the halftone dots from the light source entrance, when there is a defect in the halftone dots, the halftone dots at the same distance as the halftone dots with the most similar parameters to the defective halftone dots are easily affected by the defective halftone dots and thus have defects. Therefore, the halftone dots to be tested can be selected as the halftone dots to be analyzed first among all halftone dots.

[0062] The same distance analysis method also includes: step S1033, placing dots with good process parameters at the locations of all dots to be tested, and passing a passable light source into the light guide plate according to the position of the light source point corresponding to the position inside the light guide plate, obtaining the grayscale image corresponding to the front light plate image at this time, and recording it as a fully intact grayscale image.

[0063] Step S1034: Use the dot ratio analysis method to obtain the pixel ratio corresponding to each dot to be tested in the fully intact grayscale image, and record it as the standard ratio of the dot to be tested.

[0064] The dot ratio analysis method includes: step S1035, recording all pixels covered by the dot to be tested as standard pixels of the dot to be tested, obtaining the gray values ​​of all standard pixels, and recording the mode of all gray values ​​as the standard gray value; recording the number of all standard pixels as t1, recording the number of all standard pixels with gray values ​​as the standard gray value as t2, and recording the value of t2 divided by t1 as the pixel ratio of the dot to be tested;

[0065] In a specific implementation process, for example, during a data analysis, the number of standard pixels for the test halftone dot is 256, and the standard grayscale value is 129. Data analysis reveals that among the standard pixels, the number of pixels with a grayscale value of 129 is 224. Therefore, t1 is 256, t2 is 224, and the pixel ratio of the test halftone dot is 0.875. By obtaining the standard ratio, the total defect ratio, and the point defect ratio of the test halftone dot, we can determine the halftone dots affected by the defect of halftone dot α (i.e., the point defect image dots) among all the test halftone dot dots except for halftone dot α when a defect exists. This facilitates the detection of process defects (GQ) at halftone dot α. u At that time, based on all the residual image points, the areas that are affected by the halftone α and have potential defects, but whose detection parameters are relatively stable when the defect is enhanced, are effectively defined.

[0066] Step S1036: Place GQ samples with process defects at the locations of all test points. u The dots are located at the positions of the light source points within the light guide plate. A passable light source is introduced into the light guide plate to obtain the grayscale image corresponding to the front light plate image at this time, and it is recorded as a fully incomplete grayscale image.

[0067] Step S1037: Use the dot ratio analysis method to obtain the pixel ratio corresponding to each dot to be tested in the fully incomplete grayscale image, and record it as the full incomplete ratio of the dot to be tested.

[0068] The same-distance analysis method also includes: step S1038, placing a GQ containing a process defect at the location of dot α. u The dots are located at the positions of the light source points within the light guide plate. A passable light source is introduced into the light guide plate to obtain the grayscale image corresponding to the front light plate image at this time, and it is recorded as the dot-incomplete grayscale image.

[0069] Step S1039: Use the dot ratio analysis method to obtain the pixel ratio corresponding to each dot to be tested in the dot-damaged grayscale image, and record it as the dot-damaged ratio of the dot to be tested; subtract the full-damaged ratio from the standard ratio of dot α, and record it as the dot-damaged difference value of dot α.

[0070] Step S10310: For any halftone dot other than dot α: when the value of the standard ratio of the halftone dot minus the point defect ratio is less than or equal to the defect difference value, the halftone dot to be tested is recorded as a point defect image point.

[0071] In a specific process, for example, during a data analysis, the standard proportion and the total defect proportion of dot α are 0.9 and 0.6, respectively. Calculations show that the defect difference value is 0.3. For any dot other than dot α, the standard proportion and the defect proportion of the dot are 0.95 and 0.8, respectively. The difference between the standard proportion and the defect proportion of the dot is 0.15, indicating that when dot α has a defect, the dot under test is affected by dot α and has some defects. Therefore, the dot under test can be recorded as a dot defect image point, that is, a dot directly affected by the defect of dot α.

[0072] When analyzing the actual situation, if the difference between the standard ratio and the defect ratio of the test point is greater than the defect difference value, it indicates that point α has a defect. If the degree of defect caused by point α is greater than the degree of defect of point α, then the test point has a quality problem and can be directly marked and repaired.

[0073] The same-distance analysis method also includes: step S10311, in the positive plate analysis coordinate system, the curve obtained by fitting the halftone point α with all the point residual image points is denoted as the curve of halftone point α in the process defect GQ. u Characteristics of defects at the same distance during the same time;

[0074] In specific implementation processes, such as during a data analysis, the obtained positive plate analysis coordinate system is as follows: Figure 2 As shown, and Figure 2 The midpoint of all triangles represents the position of all points, and the points at the same distance from point α are... Figure 2 Analysis of TJ1 to TJ6 in the data shows that TJ2, TJ4, TJ5 and TJ6 are the residual image points of dot α under a process defect, and the corresponding defect feature is curve TQ.

[0075] Step S10312: Obtain the same-distance defect features of all dots under all process defects.

[0076] Step S2: Based on the in-spacing defect characteristics of each dot, obtain the in-spacing defect group of each dot in the light guide plate, and use the adjacent dot analysis method to analyze all in-spacing defect groups, and obtain the adjacent defect influence characteristics of each dot based on the analysis results.

[0077] Step S2 includes: Step S201, for any dot α in the light guide plate: all dots corresponding to dot α in the same distance defect characteristics of all process defects are recorded as the same distance defect group of dot α; the adjacent dot analysis method is used to analyze each dot in the same distance defect group, and the adjacent defect influence characteristics of dot α are obtained based on the analysis results.

[0078] The adjacent dot analysis method includes: step S2011, for any dot β in the same distance defect group: when dot β is recorded as a dot in the same distance defect group of dot α, the process defect of dot α is recorded as the same distance influence defect of dot β, wherein dot β can correspond to multiple same distance influence defects.

[0079] Step S2012: In the front light plate image, with halftone dot β as the center, the point closest to halftone dot β in each direction is recorded as the neighboring point of halftone dot β, and halftone dots in the same distance defect group of halftone dot α are removed from the neighboring points of halftone dot β.

[0080] In the specific implementation process, for example, during a data analysis, the location of the same-distance defect group of point α and the location of point β are... Figure 3 From the curve TQ and point β in the diagram, analysis reveals that the neighboring points of point β are points LJ1 to LJ. By calculating the neighboring incompleteness ratio and standard ratio for each neighboring point, we find that points LJ1, LJ2, LJ3, LJ4, LJ7, and LJ8 are the neighboring influence points. Therefore, the neighboring influence diagram for point β is as follows: Figure 4 The scatter plot is shown as a collection of all the solid triangles in the image.

[0081] Step S2013: For any in-spacing influence defect of dot β: Place the dot with in-spacing influence defect at the location of dot β, and pass a passable light source into the light guide plate according to the position of the light source point in the light guide plate, and obtain the grayscale image corresponding to the front light plate image at this time, and record it as the adjacent defective grayscale image.

[0082] Step S2014: Use the dot ratio analysis method to obtain the pixel ratio corresponding to each neighboring point in the neighboring missing grayscale image, and record it as the neighboring missing ratio of the neighboring point; when the neighboring missing ratio of the neighboring point is less than the standard ratio of the neighboring point, the neighboring point is recorded as the neighboring influence point.

[0083] In the specific implementation process, when the proportion of neighboring defects of neighboring points is less than the standard proportion of neighboring points, it indicates that the neighboring points are affected by the network point β and there is a certain defect. Therefore, the influence area of ​​the network point β after being affected by the defect can be restricted by recording the neighboring points as neighboring influence points and obtaining the neighboring influence map formed by all neighboring influence points and network point β.

[0084] Step S2015: Record the scatter plot formed by all neighboring influence points and grid point β as the neighboring influence plot of grid point β;

[0085] Step S2016: Obtain the neighbor influence map corresponding to all in-situ defects at point β;

[0086] Step S2017: Obtain the neighbor influence map of all equally spaced defects within the equally spaced defect group; for any process defect GQu All defects with the same distance as the influence are classified as process defects (GQ). u The minimum bounding region of the scatter plot formed by the neighbor influence diagram of the dots in the positive plate analysis coordinate system is denoted as the area of ​​dot α with respect to the process defect GQ. u The area affected by the defect;

[0087] In specific implementation, for example, during a data analysis, if the analyzed process defect is a weld line, and the neighbor influence diagram of all equally spaced defects that are weld lines is formed by the scatter plot in the positive plate analysis coordinate system, as shown below. Figure 5 As shown, where, Figure 5 The midpoint of all the circles inside is the position of all points in the scatter plot, so the defect-affected area can be set as region QY; by obtaining the defect-affected area, we can obtain the area affected by the dot α when the dot α has a weld line causing a defect; so as to prevent the omission of some areas in the defect-affected area due to the relatively stable detection parameters in actual detection, resulting in insufficient detection of the area affected by the defect of dot α.

[0088] Step S2018: The defect influence area of ​​dot α with respect to all process defects is recorded as the adjacent defect influence feature of dot α.

[0089] Step S3: When performing defect detection on the light guide plate, based on the same-distance defect characteristics of each dot and the adjacent defect influence characteristics of all dots in all same-distance defect dot groups, the defect sample area and the area affecting detection are obtained in the light guide plate.

[0090] Step S3 includes: Step S301, when performing defect detection on the light guide plate, for any halftone dot γ that has been detected: the defect existing in halftone dot γ is recorded as the detected defect, the same-distance defect feature of halftone dot γ when detecting the defect is recorded as the main analysis area, and the defect influence area of ​​process defect in the adjacent defect influence feature of halftone dot γ is recorded as the adjacent point influence area.

[0091] In the specific implementation process, by dividing the main analysis area and the adjacent point influence area, and further obtaining the defect sample area and the influence detection area, it is possible to reflect the areas directly affected by the defect network points and the areas indirectly affected by the defect network points, thereby avoiding the problem that the areas not classified as defect points are not effectively analyzed due to the relatively stable detection parameters when the defect parts are enhanced, resulting in low defect detection accuracy and the inability to effectively divide all areas affected by the same defect.

[0092] Step S302: The area where the main analysis area intersects with the adjacent point influence area is recorded as the defect sample area when detecting the network point γ, and the area other than the defect sample area in the main analysis area and the adjacent point influence area is recorded as the influence detection area.

[0093] Example 2, please refer to Figure 6 As shown, Figure 6 The example illustrates the structure of an electronic device, which may include a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus. The memory stores computer-readable instructions, which the processor can call. When the computer-readable instructions are executed by the processor, steps such as those in the integrated method for enhancing and detecting defect samples in a light guide plate are performed to achieve the following functions: First, based on the front view of the light guide plate, the entry point of the light source and the positions of all dots in the light guide plate are obtained, and all dots are marked based on the distance between each dot and the entry point of the light source; the same-distance analysis method is used to analyze all marked dots, and the same-distance defect characteristics of each dot are obtained based on the analysis results; then, based on the same-distance defect characteristics of each dot, the same-distance defect dot group of each dot in the light guide plate is obtained, and the adjacent dot analysis method is used to analyze all same-distance defect dot groups, and the adjacent defect influence characteristics of each dot are obtained based on the analysis results; finally, when performing defect detection on the light guide plate, the defect sample area and the area affecting detection in the light guide plate are obtained based on the same-distance defect characteristics of each dot and the adjacent defect influence characteristics of all dots in all same-distance defect dot groups.

[0094] Furthermore, when the logical instructions in the aforementioned memory can be implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0095] Example 3: This application also provides a computer program product, which includes a computer program stored on a computer-readable storage medium. The computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the integrated method for enhancing and detecting defect samples of light guide plates provided by the above methods. The method includes: first, based on a front view of the light guide plate, obtaining the entrance of the light source and the positions of all dots in the light guide plate, and marking all dots based on the distance between all dots and the entrance of the light source; analyzing all marked dots using the same-distance analysis method, and obtaining the same-distance defect features of each dot based on the analysis results; then, based on the same-distance defect features of each dot, obtaining the same-distance defect dot group of each dot in the light guide plate, and analyzing all same-distance defect dot groups using the adjacent dot analysis method, and obtaining the adjacent defect influence features of each dot based on the analysis results; finally, when performing defect detection on the light guide plate, obtaining the defect sample area and the influence detection area in the light guide plate based on the same-distance defect features of each dot and the adjacent defect influence features of all dots in all same-distance defect dot groups.

[0096] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it runs the steps of the above-described integrated method for enhancing and detecting defect samples in a light guide plate to achieve the following functions: First, based on a front view of the light guide plate, the entry point of the light source and the positions of all dots in the light guide plate are obtained, and all dots are marked based on the distance between all dots and the entry point of the light source; the same-distance analysis method is used to analyze all marked dots, and the same-distance defect features of each dot are obtained based on the analysis results; then, based on the same-distance defect features of each dot, the same-distance defect dot group of each dot in the light guide plate is obtained, and the adjacent dot analysis method is used to analyze all same-distance defect dot groups, and the adjacent defect influence features of each dot are obtained based on the analysis results; finally, when performing defect detection on the light guide plate, the defect sample area and the area affecting detection in the light guide plate are obtained based on the same-distance defect features of each dot and the adjacent defect influence features of all dots in all same-distance defect dot groups.

[0097] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0098] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0099] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for light guide plate defect sample enhancement and detection integration, characterized in that, The method comprises the following steps: Based on the front view of the light guide plate, the positions of the light source entrance and all the dots in the light guide plate are obtained, and all the dots are marked based on the distances of all the dots from the light source entrance; The same distance analysis method is used to analyze all the marked dots, and the same distance defect characteristics of each dot are obtained based on the analysis results; Based on the same distance defect characteristics of each dot, the same distance defect dot group of each dot in the light guide plate is obtained, and the adjacent distance dot analysis method is used to analyze all the same distance defect dot groups, and the adjacent distance defect influence characteristics of each dot are obtained based on the analysis results; When the defect detection of the light guide plate is performed, the defect sample area and the influence detection area in the light guide plate are obtained based on the same distance defect characteristics of each dot and the adjacent distance defect influence characteristics of all the dots in all the same distance defect dot groups; The same distance analysis method comprises: Based on the historical use record of the light guide plate, defects of the screen dots in the light guide plate caused by process parameters are obtained, and are respectively recorded as process defects GQ1 to process defects GQ t ; For any one process defect GQ u And any one dot a in the light guide plate: record all the same distance dots of dot a as the to-be-tested dots, where u is a positive integer less than or equal to t and greater than or equal to 1; based on the historical use record of the light guide plate, record the light source with the most times of being turned on into the light guide plate as the light source that can be turned on; A dot with good process parameters is placed at the position of each to-be-detected dot, a light source is introduced into the light guide plate from the position corresponding to the light source point in the light guide plate, a gray image corresponding to the front light plate image at this time is obtained, and the gray image is recorded as a full-perfect gray image; The pixel proportion of each to-be-detected dot in the full-perfect gray image is obtained by using the dot proportion analysis method, and the standard proportion of the to-be-detected dot is recorded; The dot proportion analysis method comprises: all the pixel points covered by the to-be-detected dot are recorded as standard pixel points of the to-be-detected dot, the gray values of all the standard pixel points are obtained, and the mode of all the gray values is recorded as a standard gray value; the number of all the standard pixel points is recorded as t1, the number of the standard pixel points with the standard gray value is recorded as t2, and the value of t2 divided by t1 is recorded as the pixel proportion of the to-be-detected dot; A dot with process defect GQ is placed at the position of each test dot u The light source is turned on, and the gray-scale image corresponding to the front light plate image at this time is obtained, and is recorded as a full defect gray-scale image. The pixel proportion of each to-be-detected dot in the full-defect gray image is obtained by using the dot proportion analysis method, and the full-defect proportion of the to-be-detected dot is recorded; Place a web point with process defects GQ at the location of the web point α u corresponding to the location of the light source point in the light guide plate, pass the light source into the light guide plate, obtain the gray image corresponding to the front light plate diagram at this time, and record it as the point defect gray image; The pixel proportion of each to-be-detected dot in the point-defect gray image is obtained by using the dot proportion analysis method, and the point-defect proportion of the to-be-detected dot is recorded; the difference between the standard proportion and the full-defect proportion of the dot α is recorded as the defect difference value of the dot α; For any to-be-detected dot except the dot α: when the difference between the standard proportion and the point-defect proportion of the to-be-detected dot is less than or equal to the defect difference value, the to-be-detected dot is recorded as a point-defect image dot; The curve obtained by fitting the dot a with all the dot residual image points in the positive plate analysis coordinate system is denoted as the same distance defect feature of the dot a at the process defect GQ u time. The same distance defect characteristics of all the dots under all process defects are obtained; Based on the same distance defect characteristics of each dot, the same distance defect dot group of each dot in the light guide plate comprises: For any dot α in the light guide plate: all the dots corresponding to the same distance defect characteristics of the dot α under all process defects are recorded as the same distance defect group of the dot α; the adjacent distance defect influence characteristics of the dot α are obtained by using the adjacent distance dot analysis method to analyze each dot in the same distance defect group based on the analysis results; The adjacent distance dot analysis method comprises: For any dot β in the same distance defect group: when the dot β is recorded as a dot in the same distance defect group of the dot α, the process defect of the dot α is recorded as the same distance influence defect of the dot β, wherein the dot β can correspond to multiple same distance influence defects; In the front light plate diagram, taking the dot β as the center, the point closest to the dot β in each direction is recorded as the adjacent point of the dot β, and the dots in the same distance defect group of the dot α are removed from the adjacent points of the dot β; For any one same distance defect of the dot β, the dot with the same distance defect is placed at the position of the dot β, the position corresponding to the light source point in the light guide plate is found, the light source is turned on, the corresponding gray image of the front light plate diagram at this time is obtained, and the image is recorded as the adjacent defect gray image; The pixel proportion corresponding to each adjacent point in the adjacent defect gray image is obtained by using the dot proportion analysis method, and the proportion is recorded as the adjacent defect proportion of the adjacent point; when the adjacent defect proportion of the adjacent point is less than the standard proportion of the adjacent point, the adjacent point is recorded as the adjacent influence point; The scatter diagram formed by all the adjacent influence points and the dot β is recorded as the adjacent influence diagram of the dot β; The adjacent influence diagrams corresponding to all the same distance defects of the dot β are obtained; obtaining the neighbor influence graph of all the same-distance influence defects of all the dots in the same-distance defect group; for any one process defect GQ u , the neighbor influence graph of all the same-distance influence defects of the dots with the process defect GQ u forms a scatter diagram in the positive plate analysis coordinate system, and the minimum circumscribed area of the scatter diagram is recorded as the defect influence area of the dot α with respect to the process defect GQ u ; The defect influence area of the dot α with respect to all the process defects is recorded as the adjacent distance defect influence feature of the dot α; When the light guide plate is detected for defects, based on the same distance defect feature of each dot and the adjacent distance defect influence feature of all the dots in the same distance defect group, the defect sample area and the influence detection area in the light guide plate are obtained, including: When the light guide plate is detected for defects, for any one dot γ that has been detected for defects: the defect existing in the dot γ is recorded as the detected defect, the same distance defect feature of the dot γ when the detected defect is detected is recorded as the main analysis area, and the defect influence area of the adjacent distance defect influence feature of the dot γ with respect to the process defect is recorded as the adjacent distance point influence area; The area intersected by the main analysis area and the adjacent distance point influence area is recorded as the defect sample area when the dot γ is detected, and the area in the main analysis area and the adjacent distance point influence area except the defect sample area is recorded as the influence detection area.

2. The method of claim 1, wherein the method is characterized by: Based on the front view of the light guide plate, the positions of the light source entrance and all the dots in the light guide plate are obtained, and all the dots are marked based on the distances of the dots to the light source entrance, including: The front view of the light guide plate is obtained and recorded as the front light plate diagram; the point corresponding to the light source entrance in the front light plate diagram is recorded as the light source point; a plane rectangular coordinate system is established and recorded as the front plate analysis coordinate system, wherein the units of the X axis and the Y axis of the front plate analysis coordinate system are cm; the front light plate diagram is placed in the front plate analysis coordinate system, wherein the light source point in the front light plate diagram coincides with the coordinate origin of the front plate analysis coordinate system; The positions of all the dots in the light guide plate are obtained based on laser scanning positioning, and the positions of all the dots in the light guide plate are marked in the front plate analysis coordinate system; the distance between each dot and the coordinate origin is obtained and recorded as the light distance of the dot; for any one dot α in the front plate analysis coordinate system, the dot with the same light distance as the dot α is recorded as the same distance dot of the dot α.

Images