AOI detection system and detection method after hot pressing of light guide plate

Abstract

The invention discloses an AOI detection system and detection method after hot pressing of a light guide plate, and relates to the technical field of light guide plate detection, and the AOI detection system comprises an image acquisition module, a gray processing module, a binarization module, a contour extraction module, a reference point setting module, a detection value acquisition module, a threshold acquisition module and a judgment module. The reference point setting module is used for acquiring a detection network point reference point based on a network point contour; the detection value acquisition module is used for acquiring a network point detection value based on a detection network point contour and a detection network point reference point; the threshold value acquisition module is used for acquiring a first qualified threshold value and a second qualified threshold value based on the hot-pressed images of the first number of normal light guide plates; the judgment module is used for judging whether the hot-pressed light guide plate is qualified or not based on the dot detection value, the first qualified threshold value and the second qualified threshold value. The light guide plate detection device and method are used for solving the problem that in an existing light guide plate detection technology, the dot structure cannot be analyzed, and consequently qualified detection of the hot-pressed light guide plate is inaccurate.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of light guide plate detection, in particular to a light guide plate heat pressing line after AOI detection system and method. BACKGROUND

[0002] The main function of the light guide plate is to uniformly distribute the light emitted by the light source to the entire display panel, thereby realizing uniform brightness display. In the manufacturing process of the light guide plate, the heat pressing line process is a common technical means for forming dot structures on the surface of the light guide plate. These dot structures can effectively scatter light and improve the optical performance of the light guide plate. The heat pressing line process needs to accurately control the temperature and pressure. If the temperature and pressure deviate, the obtained dot structure will also deviate, resulting in unqualified light guide plates. The existing light guide plate detection directly detects whether the light guide plate contains scratches, dirt and damage and the like. However, after the heat pressing of the light guide plate, it is also necessary to judge whether the dot structure of the light guide plate is qualified. The detection of the dot structure is different from the detection of scratches, dirt and damage and the like. If the dot structure is unqualified, it will cause the scattered light of the light guide plate to decrease, affecting the normal use of the light guide plate. For example, in the patent application with the publication number CN114881987A, a heat pressing light guide plate defect visualization detection method based on improved YOLOv5 is disclosed. This scheme directly detects whether the light guide plate contains scratches, dirt and damage and the like, and fails to detect the dot structure, resulting in the light guide plate still containing defects. That is, the existing light guide plate detection technology fails to analyze the dot structure, resulting in inaccurate qualified detection after the heat pressing of the light guide plate. SUMMARY

[0003] The present application aims to at least solve one of the technical problems in the prior art. By obtaining a detection dot reference point based on a dot contour, obtaining a dot detection value based on the detection dot contour and the detection dot reference point, obtaining a first qualified threshold and a second qualified threshold based on images of a first number of normal light guide plates after heat pressing, and judging whether the light guide plate is qualified after heat pressing based on the dot detection value, the first qualified threshold and the second qualified threshold, the problem of inaccurate qualified detection after the heat pressing of the light guide plate due to the failure of the existing light guide plate detection technology to analyze the dot structure is solved.

[0004] To achieve the above-mentioned purpose, the present application provides a light guide plate heat pressing line after AOI detection system, comprising: An image acquisition module, a gray scale processing module, a binaryzation module, a contour extraction module, a reference point setting module, a detection value acquisition module, a threshold value acquisition module and a judgment module; The image acquisition module is used to acquire an image after the heat pressing of the light guide plate, which is marked as a heat pressing after image; The grayscale processing module is used to perform grayscale processing on the hot pressed image to obtain a hot pressed grayscale image; The binarization module is used to perform binarization processing on the hot pressed grayscale image to obtain a hot pressed binarized image; The contour extraction module is used to obtain the detection point contour based on the binary image after hot pressing; The reference point setting module is used to obtain the detection dot reference point based on the dot outline; The detection value acquisition module is used to acquire the dot detection value based on the detection dot outline and the detection dot reference point; The threshold acquisition module is used to acquire a first qualified threshold and a second qualified threshold based on a first number of images of normal light guide plates after hot pressing; The judgment module is used to judge whether the light guide plate is qualified after hot pressing based on the dot detection value, the first qualified threshold value and the second qualified threshold value.

[0005] Furthermore, the grayscale processing module is configured with a grayscale processing strategy, and the grayscale processing strategy includes: Obtain the R value, G value, and B value of any pixel point in the image after hot pressing, and mark them as the detected R value, detected G value, and detected B value respectively; calculate the average of the detected R value, detected G value, and detected B value, and mark them as the detected grayscale value; replace the detected R value, detected G value, and detected B value with the detected grayscale value, and represent each pixel point in the image after hot pressing by the corresponding detected grayscale value to obtain the grayscale image after hot pressing.

[0006] Furthermore, the binarization configuration includes a binarization strategy, and the binarization strategy includes: Divide the grayscale values ​​from 0 to 255 into a parts evenly, marked as equal parts; the length of each equal part is 255÷a; the starting value and ending value of each equal part are (255÷a)×b and (255÷a)×(b+1), respectively; where b is a positive integer from 0 to a-1; Get the number of detected gray values ​​in each equally divided part, marked as the number of detections; Draw a histogram with the grayscale value as the X-axis, the number of detections as the Y-axis, and the evenly divided part as the histogram interval, marked as the detection grayscale histogram; The part of the grayscale histogram that is larger than the average number of adjacent detections on the left and right sides is marked as the first target part; Obtain the first target portion with the smallest starting value and mark it as the second target portion; Get the first target part with the largest starting value and mark it as the third target part; Obtain an evenly divided portion with the smallest starting value between the second target portion and the third target portion, and mark it as the fourth target portion; An average value of the start value and the end value of the fourth target part is calculated, and is marked as a dot binary threshold value; In the gray scale image after hot pressing, the detected gray scale value greater than the dot binary threshold value is set as 0, and the detected gray scale value less than or equal to the binary threshold value is set as 255, to obtain a binary image after hot pressing.

[0007] Further, the contour extraction is configured with a contour extraction strategy, and the contour extraction strategy comprises: In the binary image after hot pressing, a pixel point with a detected gray scale value of 0 adjacent to a detected gray scale value of 255 is obtained, and is marked as an initial pixel point; it is judged whether the initial pixel point is surrounded by pixel points with a detected gray scale value of 0, if not, a new initial pixel point is obtained; if yes, the initial pixel point is marked as an edge start pixel point; With a pixel point adjacent to the left side of the edge start pixel point as a start, and with the edge start pixel point as a rotation center, a first pixel point with a detected gray scale value changed from 255 to 0 is searched in a clockwise direction, and is marked as an edge search pixel point; then, a new edge search pixel point is obtained with the edge search pixel point as a rotation center, until the new edge search pixel point is the same as the edge start pixel point, the operation is stopped, and a contour composed of the edge start pixel point and all the edge search pixel points is obtained, and is marked as a detected dot contour.

[0008] Further, the reference point setting is configured with a reference point setting strategy, and the reference point setting strategy comprises: All the detected dot contours in the binary image after hot pressing are obtained; Every same interval on the detected dot contour is drawn to obtain a second number of coordinate points, and the coordinate points are marked as contour coordinate points; The contour coordinate points are sequentially connected along the detected dot contour to obtain line segments, and the line segments are marked as contour connection line segments; An included angle between all adjacent contour connection line segments is obtained, and the included angle is marked as a contour included angle; An average value of the contour included angles is obtained, and the average value is marked as a contour included angle average value; An absolute value of a difference between all the contour included angles and the contour included angle average value is calculated, and the absolute value is marked as a reference difference value; The reference difference values are sorted from small to large, and an intersection point of the contour included angles corresponding to the first four reference difference values is obtained, and the intersection point is marked as a first coordinate point, a second coordinate point, a third coordinate point and a fourth coordinate point respectively.

[0009] Further, the reference point setting module is configured with a reference point setting strategy, and the reference point setting strategy comprises: A line segment is obtained by connecting the first coordinate point and the second coordinate point, and the line segment is marked as a first line segment; a line segment is obtained by connecting the second coordinate point and the third coordinate point, and the line segment is marked as a second line segment; Draw a perpendicular line to the first line segment through the midpoint of the first line segment and mark it as the first perpendicular line; draw a perpendicular line to the second line segment through the midpoint of the second line segment and mark it as the second perpendicular line; Obtain the intersection of the first perpendicular line and the second perpendicular line and mark it as the detection point reference point.

[0010] Furthermore, the detection value acquisition module is configured with a detection value acquisition strategy, and the detection value acquisition strategy includes: Mark the pixels on the detection dot outline as detection outline pixels; Get the distance from the detection dot reference point to the detection contour pixel point, marked as the dot detection value.

[0011] Furthermore, the threshold acquisition module is configured with a threshold acquisition strategy, and the threshold acquisition strategy includes: Marking the first number of normal images of the light guide plates after hot pressing as normal images; obtaining all the dot detection values ​​of each detection dot outline in the normal images and marking them as normal distances; Get the range of normal distances, marked as C1 to Cn; divide the range of fall comparison values ​​evenly into d parts, marked as normal parts; the length of each normal part is (Cn-C1)÷d; the starting value and ending value of each normal part are C1+[(Cn-C1)÷d]×e and C1+[(Cn-C1)÷d]×(e+1), respectively; where e is a positive integer from 0 to d-1; Count the number of each normal part and mark it as the number of normal parts; Sort the number of normal parts from small to large according to the starting value of the normal part to obtain the normal sequence number, which is a positive integer starting from 1; Get the frequency of normal distance, marked as Z; The normal number threshold is calculated as: G = f × (Z ÷ d); where Z is the fall threshold and f is the ratio value from 0 to 1; Determine whether the number of normal parts is less than the normal number threshold according to the normal sequence number from small to large. If not, stop judging directly. If so, delete the number of normal parts and continue judging whether the next number of normal parts is less than the normal number threshold until the number of normal parts is greater than or equal to the normal number threshold. Get the starting value of the normal part corresponding to the number of normal parts on the left at this time and mark it as the first qualified threshold. According to the normal serial number, determine whether the number of normal parts is less than the normal number threshold from large to small. If not, stop judging directly. If so, delete the number of normal parts and continue to judge whether the next number of normal parts is less than the normal number threshold, until the number of normal parts is greater than or equal to the normal number threshold, stop judging; obtain the end value of the normal part corresponding to the number of normal parts on the far right at this time, and mark it as the second qualified threshold.

[0012] Further, the judging module is configured with a judgment strategy, and the judgment strategy comprises: judging whether all the dot detection values are greater than or equal to a first qualified threshold value and less than or equal to a second qualified threshold value, if yes, generating a signal of qualified hot-pressing of the light guide plate, and if no, generating a signal of unqualified hot-pressing of the light guide plate.

[0013] The present application provides a kind of light guide plate hot-pressing line after AOI detection method, comprising the following steps: obtaining the image after light guide plate hot-pressing, marked as hot-pressing after image; The hot-pressing after image is carried out gray processing to obtain hot-pressing after gray image; The hot-pressing gray image is carried out binaryzation processing to obtain hot-pressing after binaryzation image; Based on hot-pressing after binaryzation image, detection dot profile is obtained; Based on dot profile, detection dot reference point is obtained; Based on detection dot profile and detection dot reference point, dot detection value is obtained; Based on the image after hot-pressing of the first number of normal light guide plates, first qualified threshold value and second qualified threshold value are obtained; Based on dot detection value, first qualified threshold value and second qualified threshold value, whether light guide plate is qualified after hot-pressing is judged.

[0014] The present application has the beneficial effects that: the present application obtains detection dot reference point based on dot profile;Obtains dot detection value based on detection dot profile and detection dot reference point;Obtains first qualified threshold value and second qualified threshold value based on the image after hot-pressing of the first number of normal light guide plates;Judges whether light guide plate is qualified after hot-pressing based on dot detection value, first qualified threshold value and second qualified threshold value, and the advantage is that the dot structure is analyzed to improve the accuracy of detection qualified light guide plate; The present application obtains detection dot reference point based on dot profile;Obtains dot detection value based on detection dot profile and detection dot reference point, and the advantage is that the structure of dot can be digitized, which is convenient for judging whether light guide plate is qualified based on dot, and also improves the accuracy of detection qualified light guide plate. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 It is the principle block diagram of the system of the present application; Figure 2 It is the schematic diagram of detection gray histogram of the present application; Figure 3 It is the schematic diagram of profile included angle of the present application; Figure 4 It is the schematic diagram of detection dot reference point of the present application; Figure 5 It is the flow chart of step of the present application. DETAILED DESCRIPTION

[0016] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative effort belong to the scope of protection of the present application.

[0017] Embodiment 1, please refer to Figure 1 As shown in the figure, an AOI detection system for a light guide plate after hot pressing, comprising: an image acquisition module, a gray processing module, a binaryzation module, a contour extraction module, a reference point setting module, a detection value acquisition module, a threshold acquisition module and a judgment module; The image acquisition module is used to acquire the image of the light guide plate after hot pressing, which is marked as the image after hot pressing. When the image is acquired, the light is irradiated from the side to make the screen dots appear, and the background is set to black, so that the screen dots can be more easily distinguished; The gray processing module is used to perform gray processing on the image after hot pressing to obtain the gray image after hot pressing. The gray processing module is configured with a gray processing strategy, and the gray processing strategy comprises: The R value, G value and B value of any one pixel point in the image after hot pressing are acquired, which are respectively marked as the detection R value, detection G value and detection B value. The average value of the detection R value, detection G value and detection B value is calculated and marked as the detection gray value. Each pixel point in the image after hot pressing is represented by the corresponding detection gray value, and the gray image after hot pressing is obtained. In actual application, the R value, G value and B value of any one pixel point in the image after hot pressing are 206, 212 and 224 respectively, the average value of 206, 212 and 224 is calculated as 214, and the detection gray value is 214. The calculation result is kept as an integer.

[0018] The binaryzation module is used to perform binaryzation processing on the hot pressing gray image to obtain the binaryzation image after hot pressing. The binaryzation is configured with a binaryzation strategy, and the binaryzation strategy comprises: The gray values from 0 to 255 are evenly divided into a parts, which are marked as evenly divided parts. The length of each evenly divided part is 255÷a. The starting value and the ending value of each evenly divided part are (255÷a)×b and (255÷a)×(b+1) respectively. Wherein b is a positive integer from 0 to a-1. The evenly divided parts are divided in order to observe the distribution of the detection gray value, for example, a is set to 8. In practical applications, the grayscale values ​​0 to 255 are evenly divided into 8 parts; the length of the 8 equally divided parts is 255÷8; when b is 0, the starting value and ending value of each equally divided part are (255÷8)×0=0 and (255÷8)×(0+1)=31 respectively. The calculation result retains an integer, then one equally divided part is 0 to 31.

[0019] Get the number of detected gray values ​​in each equally divided part, marked as the number of detections; Draw a histogram with the grayscale value as the X-axis, the number of detections as the Y-axis, and the evenly divided part as the histogram interval, marked as the detection grayscale histogram; In practical applications, please refer to Figure 2 As shown, the detection grayscale histogram is drawn.

[0020] The part of the grayscale histogram that is larger than the average number of adjacent detections on the left and right sides is marked as the first target part; Obtain the first target portion with the smallest starting value and mark it as the second target portion; Get the first target part with the largest starting value and mark it as the third target part; Obtain an evenly divided portion with the smallest starting value between the second target portion and the third target portion, and mark it as the fourth target portion; Calculate the average of the starting value and the ending value of the fourth target part, and mark it as the dot binarization threshold; In the grayscale image after hot pressing, the grayscale values ​​detected that are greater than the binarization threshold of the dots are set to 0, and the grayscale values ​​detected that are less than or equal to the binarization threshold are set to 255 to obtain the binarized image after hot pressing. Since the background is black and the refracted light brightness of the dots is high, the grayscale values ​​of some dots are higher than the background, so the binarization operation can be performed. In practical applications, please refer to Figure 2 As shown, the second target part is 63 to 95, the third target part is 191 to 223, and the averaged part with the smallest starting value between the second target part and the third target part is 127 to 159. The average of the starting value and the ending value of the fourth target part is: (127+159)÷2=143; the dot binarization threshold is 143, and the detection grayscale values ​​greater than 143 in the grayscale image after hot pressing are set to 0, and the detection grayscale values ​​less than or equal to 143 are set to 255 to obtain the binarized image after hot pressing.

[0021] The contour extraction module is used to obtain the detection point contour based on the binary image after hot pressing; Contour extraction is configured with a contour extraction strategy, which includes: In the hot-pressing binary image, the pixel point with a detection grayscale value of 0 adjacent to the detection grayscale value of 255 is obtained, and is marked as an initial pixel point; it is judged whether the initial pixel point is surrounded by a pixel point with a detection grayscale value of 0, if not, a new initial pixel point is obtained; if yes, the initial pixel point is marked as an edge starting pixel point; the light guide point is not an isolated pixel point, this method can exclude the isolated pixel point, and improve the identification of the light guide point part; With the pixel point adjacent to the left side of the edge starting pixel point as a starting point, and with the edge starting pixel point as a rotation center, the first pixel point with a detection grayscale value changing from 255 to 0 is searched in a clockwise direction, and is marked as an edge search pixel point; then, with the edge search pixel point as a rotation center, a new edge search pixel point is obtained, until the new edge search pixel point is the same as the edge starting pixel point, the operation is stopped, the contour composed of the edge starting pixel point and all the edge search pixel points is obtained, and is marked as a detection dot contour; a contour search method is used to obtain the contour of each light guide point.

[0022] The reference point setting module is used to obtain a detection dot reference point based on the dot contour; The reference point setting is configured with a reference point setting strategy, and the reference point setting strategy comprises: All detection dot contours in the hot-pressing binary image are obtained; A second number of coordinate points are drawn at every same interval on the detection dot contour, and are marked as contour coordinate points; The contour coordinate points are sequentially connected along the detection dot contour to obtain a line segment, and are marked as a contour connection line segment; The included angles between all adjacent contour connection line segments are obtained, and are marked as contour included angles; The mean value of the contour included angles is calculated, and is marked as a contour included angle mean value; The absolute values of the differences between all the contour included angles and the contour included angle mean value are calculated, and are marked as reference differences; The beneficial effect of the reference difference is that, because the dot of the light guide plate is a circle, the reference difference should be equal at this time, but the actual production is not a completely regular circle, and the dot of the light guide plate has defects, so that the contour included angle is too large or too small, which may be the defective part of the dot of the light guide plate, so that the subsequent detection dot reference point is more accurate.

[0023] The reference differences are sorted from small to large, the intersection points of the contour included angles corresponding to the first four reference differences are obtained, and are respectively marked as a first coordinate point, a second coordinate point, a third coordinate point and a fourth coordinate point; In actual application, please refer to Figure 3 The contour included angles are obtained.

[0024] The reference point setting module is configured with a reference point setting strategy, and the reference point setting strategy comprises: Connecting the first coordinate point and the second coordinate point to obtain a line segment, marked as a first line segment; connecting the second coordinate point and the third coordinate point to obtain a line segment, marked as a second line segment; Drawing a perpendicular line of the first line segment through the midpoint of the first line segment, marked as a first perpendicular line; drawing a perpendicular line of the second line segment through the midpoint of the second line segment, marked as a second perpendicular line; Obtaining the intersection point of the first perpendicular line and the second perpendicular line, marked as a detection net point reference point; the detection net point reference point is a method for obtaining the center of a circle, because the net point of the light guide plate is circular, the detection net point reference point is the center of the net point, and the points of the defective part are excluded through the reference difference, so that the obtained center is more accurate, and the subsequent net point detection value is more valuable for comparison; In actual application, please refer to Figure 4 The detection net point reference point obtained is shown.

[0025] The detection value acquisition module is used for acquiring a net point detection value based on the detection net point contour and the detection net point reference point; The detection value acquisition module is configured with a detection value acquisition strategy, and the detection value acquisition strategy comprises: Marking the pixel points on the detection net point contour as detection contour pixel points; Obtaining the distance from the detection net point reference point to the detection contour pixel points, marked as a net point detection value; the net point detection value is the radius of the net point; if most of the net point detection values are too large, it may be caused by too high temperature and pressure setting; if most of the net point detection values are too small, it may be caused by too low temperature and pressure setting; if a small part of the net point detection values are too large or too small, it may be caused by the incomplete generation of the net point; In actual application, for example, a net point detection value is 0.041 mm.

[0026] The threshold value acquisition module is used for acquiring a first qualified threshold value and a second qualified threshold value based on the images of the first number of normal light guide plates after heat pressing; The threshold value acquisition module is configured with a threshold value acquisition strategy, and the threshold value acquisition strategy comprises: Marking the images of the first number of normal light guide plates after heat pressing as normal images; obtaining all the net point detection values of each detection net point contour in the normal images, marked as normal distances; Obtaining the range of normal distance, marked as C1 to Cn; dividing the range of fall contrast value into d parts, marked as normal part; the length of each normal part is (Cn-C1) ÷ d; the start value and end value of each normal part are C1+[(Cn-C1) ÷ d]×e and C1+[(Cn-C1) ÷ d]×(e+1) respectively; wherein e is a positive integer from 0 to d-1; dividing the normal part is to observe the distribution of normal distance, for example, a is set to 10; In practical application, the range of normal distance is 0.038mm to 0.048mm, and the gray value of 0 to 255 is divided into 10 parts; the length of 10 normal parts is (0.048-0.038) ÷ 10=0.001; when e is 0, the start value and end value of each normal part are 0.038+[(0.048-0.038) ÷ 8]×0=0.038 and 0.038+[(0.048-0.038) ÷ 8]×(1+1)=0.039 respectively, and a normal part is 0.038 to 0.039.

[0027] Counting the number of each normal part, marked as normal part number; Sorting the normal part number according to the start value of the normal part from small to large to obtain the normal sequence number, which is a positive integer starting from 1; Obtaining the frequency of normal distance, marked as Z; Calculating the normal number threshold value as: G=f×(Z ÷ d); wherein Z is the fall division threshold value, and f is a proportion value from 0 to 1; the setting of f is to obtain the normal part with smaller normal part number, so f is set to be small, for example, f is 0.1; In practical application, the frequency of normal distance is 1212, and the normal number threshold value is calculated as: G=0.1×(1212 ÷ 10)=12, and the calculation result is rounded to an integer, so the normal number threshold value is 12 at this time.

[0028] Judging whether the normal part number is less than the normal number threshold value according to the normal sequence number from small to large, if not, directly stopping judging, if yes, deleting the normal part number, continuing to judge whether the next normal part number is less than the normal number threshold value, until the normal part number is greater than or equal to the normal number threshold value to stop judging; obtaining the start value of the normal part corresponding to the leftmost normal part number at this time, marked as the first qualified threshold value; According to the normal sequence number from large to small, it is judged whether the normal part number is less than the normal number threshold value, if not, the judgment is directly stopped, if yes, the normal part number is deleted, the next normal part number is continued to be judged whether it is less than the normal number threshold value, until the normal part number is greater than or equal to the normal number threshold value, the judgment is stopped; the end value of the normal part corresponding to the rightmost normal part number at this time is obtained, which is marked as the second qualified threshold value; this method can delete the normal distance that is too large or too small, and obtain a more accurate normal distance range; In actual application, the normal part numbers are sorted from small to large according to the starting values of the normal parts as 4, 21, …, 32, 10; 4 and 10 less than the number threshold value 12 are deleted, the starting value of the normal part 0.39mm to 0.40mm corresponding to the leftmost 21 after deletion is 0.39mm, then 0.39mm is the first qualified threshold value, the end value of the normal part 0.46mm to 0.47mm corresponding to the leftmost 32 after deletion is 0.47mm, then 0.47mm is the second qualified threshold value.

[0029] The judgment module is configured to judge whether the light guide plate is qualified after heat pressing based on the dot detection value, the first qualified threshold value and the second qualified threshold value; The judgment module is configured with a judgment strategy, and the judgment strategy includes: All dot detection values are judged whether they are greater than or equal to the first qualified threshold value, and at the same time less than or equal to the second qualified threshold value, if yes, a signal that the light guide plate is qualified after heat pressing is generated, if not, a signal that the light guide plate is unqualified after heat pressing is generated; if the dot detection value is less than the first qualified threshold value, it may be caused by too low temperature and pressure setting or dot defect, if the dot detection value is greater than the second qualified threshold value, it may be caused by too high temperature and pressure setting or dot defect; therefore, whether the light guide plate is qualified and In actual application, for example, one dot detection value is 0.041mm, which is greater than the first qualified threshold value 0.39mm, and at the same time less than 0.47mm, then it is a normal distance, if all satisfy, a signal that the light guide plate is qualified after heat pressing is generated.

[0030] Embodiment 2, please refer to Figure 5 As shown in the figure, an AOI detection method for a light guide plate heat pressing line, comprising the following steps: Step S1, obtaining an image after heat pressing of the light guide plate, which is marked as a heat pressed image.

[0031] Step S2, performing gray processing on the heat pressed image to obtain a heat pressed gray image; step S2 includes the following substeps: Step S201, obtaining the R value, the G value and the B value of any one pixel point in the image after hot pressing, and marking them as the detection R value, the detection G value and the detection B value respectively; obtaining the average value of the detection R value, the detection G value and the detection B value, and marking it as the detection gray value; replacing the detection R value, the detection G value and the detection B value with the detection gray value, representing each pixel point in the image after hot pressing by the corresponding detection gray value, and obtaining the gray image after hot pressing.

[0032] Step S3, obtaining the binary image after hot pressing by performing binaryzation processing on the hot pressing gray image; step S3 includes the following substeps: Step S301, evenly dividing the gray value from 0 to 255 into a parts, and marking them as evenly divided parts; the length of each evenly divided part is 255÷a; the starting value and the ending value of each evenly divided part are (255÷a)×b and (255÷a)×(b+1) respectively; wherein b is a positive integer from 0 to a-1; Step S302, obtaining the number of detection gray values in each evenly divided part, and marking it as the detection number; Step S303, drawing a histogram with the gray value as the X axis, the detection number as the Y axis, and the evenly divided part as the histogram interval, and marking it as the detection gray histogram; Step S304, marking the evenly divided part with the detection number greater than that of the adjacent evenly divided parts on the left and right sides as the first target part in the detection gray histogram; Step S305, obtaining the first target part with the minimum starting value, and marking it as the second target part; Step S306, obtaining the first target part with the maximum starting value, and marking it as the third target part; Step S307, obtaining the evenly divided part with the minimum starting value between the second target part and the third target part, and marking it as the fourth target part; Step S308, calculating the average value of the starting value and the ending value of the fourth target part, and marking it as the dot binaryzation threshold value; Step S309, setting the detection gray value greater than the dot binaryzation threshold value as 0 and setting the detection gray value less than or equal to the binaryzation threshold value as 255 in the gray image after hot pressing, and obtaining the binary image after hot pressing.

[0033] Step S4, obtaining the detection dot contour based on the binary image after hot pressing; step S4 includes the following substeps: Step S401, obtaining the pixel point with the detection gray value of 0 adjacent to the detection gray value of 255 in the binary image after hot pressing, and marking it as the initial pixel point; judging whether the initial pixel point contains the pixel point with the detection gray value of 0 around it, if not, obtaining a new initial pixel point; if yes, marking the initial pixel point as the edge starting pixel point; Step S402, taking the pixel point adjacent to the edge starting pixel point on the left as the starting point, taking the edge starting pixel point as the rotation center, rotating in the clockwise direction to search for the first pixel point whose gray value changes from 255 to 0, and marking the pixel point as an edge search pixel point; then taking the edge search pixel point as the rotation center to obtain a new edge search pixel point, until the new edge search pixel point is the same as the edge starting pixel point, stopping the operation, obtaining the contour composed of the edge starting pixel point and all the edge search pixel points, and marking the contour as a detection dot contour.

[0034] Step S5, obtaining a detection dot reference point based on the detection dot contour; step S5 includes the following sub-steps: Step S501, obtaining all the detection dot contours in the binaryzation image after hot pressing; Step S502, drawing second number of coordinate points at every same interval on the detection dot contour, and marking the coordinate points as contour coordinate points; Step S503, connecting the contour coordinate points in sequence along the detection dot contour to obtain line segments, and marking the line segments as contour connection line segments; Step S504, obtaining the included angles between all the adjacent contour connection line segments, and marking the included angles as contour included angles; Step S505, obtaining the mean value of the contour included angles, and marking the mean value as a contour included angle mean value; Step S506, calculating the absolute values of the differences between all the contour included angles and the contour included angle mean value, and marking the absolute values as reference differences; Step S507, sorting the reference differences from small to large, obtaining the intersection points of the contour included angles corresponding to the first four reference differences, and marking the intersection points as a first coordinate point, a second coordinate point, a third coordinate point and a fourth coordinate point respectively; Step S508, connecting the first coordinate point and the second coordinate point to obtain a line segment, and marking the line segment as a first line segment; connecting the second coordinate point and the third coordinate point to obtain a line segment, and marking the line segment as a second line segment; Step S509, drawing a perpendicular line of the first line segment through the midpoint of the first line segment, and marking the perpendicular line as a first perpendicular line; drawing a perpendicular line of the second line segment through the midpoint of the second line segment, and marking the perpendicular line as a second perpendicular line; Step S510, obtaining the intersection point of the first perpendicular line and the second perpendicular line, and marking the intersection point as a detection dot reference point.

[0035] Step S6, obtaining a dot detection value based on the detection dot contour and the detection dot reference point; step S6 includes the following sub-steps: Step S601, marking the pixel points on the detection dot contour as detection contour pixel points; Step S602, obtaining the distance from the detection dot reference point to the detection contour pixel points, and marking the distance as a dot detection value.

[0036] Step S7, obtaining the first qualified threshold and the second qualified threshold based on the images of the first number of normal light guide plates after hot pressing; step S7 includes the following sub-steps: Step S701, marking the images of the first number of normal light guide plates after hot pressing as normal images; obtaining all the dot detection values of each detection dot profile in the normal images, and marking as normal distances; Step S702, obtaining the range of the normal distances, and marking as C1 to Cn; evenly dividing the range of the falling contrast values into d parts, and marking as normal parts; the length of each normal part is (Cn-C1) ÷ d; the starting value and the ending value of each normal part are C1+[(Cn-C1) ÷ d]×e and C1+[(Cn-C1) ÷ d]×(e+1) respectively; wherein e is a positive integer from 0 to d-1; Step S703, counting the number of each normal part, and marking as the number of normal parts; Step S704, sorting the number of normal parts according to the starting values of the normal parts from small to large to obtain a normal sequence number, which is a positive integer starting from 1; Step S705, obtaining the frequency of the normal distances, and marking as Z; Step S706, calculating the normal number threshold as: G=f×(Z÷d); wherein Z is the falling division threshold, and f is a proportion value from 0 to 1; Step S707, judging whether the number of normal parts is less than the normal number threshold according to the normal sequence number from small to large; if not, stopping the judgment directly; if yes, deleting the number of normal parts, continuing to judge whether the next number of normal parts is less than the normal number threshold, until the number of normal parts is greater than or equal to the normal number threshold to stop the judgment; obtaining the starting value of the normal part corresponding to the leftmost number of normal parts at this time, and marking as the first qualified threshold; Step S708, judging whether the number of normal parts is less than the normal number threshold according to the normal sequence number from large to small; if not, stopping the judgment directly; if yes, deleting the number of normal parts, continuing to judge whether the next number of normal parts is less than the normal number threshold, until the number of normal parts is greater than or equal to the normal number threshold to stop the judgment; obtaining the ending value of the normal part corresponding to the rightmost number of normal parts at this time, and marking as the second qualified threshold.

[0037] Step S8, judging whether the light guide plate after hot pressing is qualified based on the dot detection values, the first qualified threshold and the second qualified threshold; step S8 includes the following sub-steps: Step S801, judging whether all the dot detection values are greater than or equal to the first qualified threshold and less than or equal to the second qualified threshold; if yes, generating a signal that the light guide plate after hot pressing is qualified; if not, generating a signal that the light guide plate after hot pressing is unqualified.

[0038] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, a system or a computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (or computer- readable storage media) having computer-usable program code embodied in the medium. The medium can be any available storage media that can be accessed by a computer. By way of example, and not limitation, such computer-usable storage media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other storage medium that can be used to carry or store desired computer program code in the form of instructions or data structures and that can be accessed by a computer. Also, the present application can be embodied in a computer program product that can be traded as goods or merchandise, through the storage medium described above or any other suitable medium. When the computer program code is executed by a computer, a series of instructions or a series of operations is performed. Also, the present application can be embodied in a computer program product that can be traded as goods or merchandise, through the storage medium described above or any other suitable medium. When the computer program code is executed by a computer, a series of instructions or a series of operations is performed. Figure 1 one or more flows and / or blocks Figure 1 one or more blocks or a plurality of blocks.

[0039] In the embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of the units is merely a logical function division. In actual implementation, another division manner can be used. For example, a plurality of units or components can be combined or integrated into another system, or some features can be omitted or not executed. In addition, the coupling or direct coupling or communication connection between the units or components shown or discussed can be indirect coupling or communication connection through some communication interfaces. The coupling or communication connection can be electrical, mechanical or in other forms.

Claims

1. An AOI inspection system for light guide plate after hot pressing line, characterized in that: include: Image acquisition module, grayscale processing module, binarization module, contour extraction module, reference point setting module, detection value acquisition module, threshold acquisition module and judgment module; The image acquisition module is used to acquire an image of the light guide plate after hot pressing, which is marked as the image after hot pressing; The grayscale processing module is used to perform grayscale processing on the hot pressed image to obtain a hot pressed grayscale image; The binarization module is used to perform binarization processing on the hot pressed grayscale image to obtain a hot pressed binarized image; The contour extraction module is used to obtain the detection point contour based on the binary image after hot pressing; The reference point setting module is used to obtain the detection dot reference point based on the dot outline; The detection value acquisition module is used to acquire the dot detection value based on the detection dot outline and the detection dot reference point; The threshold acquisition module is used to acquire a first qualified threshold and a second qualified threshold based on a first number of images of normal light guide plates after hot pressing; The judgment module is used to judge whether the light guide plate is qualified after hot pressing based on the dot detection value, the first qualified threshold value and the second qualified threshold value.

2. The AOI inspection system for light guide plate after hot pressing line according to claim 1, characterized in that: The grayscale processing module is configured with a grayscale processing strategy, and the grayscale processing strategy includes: Obtain the R value, G value, and B value of any pixel point in the image after hot pressing, and mark them as the detected R value, detected G value, and detected B value respectively; calculate the average of the detected R value, detected G value, and detected B value, and mark them as the detected grayscale value; replace the detected R value, detected G value, and detected B value with the detected grayscale value, and represent each pixel point in the image after hot pressing by the corresponding detected grayscale value to obtain the grayscale image after hot pressing.

3. The AOI inspection system for light guide plate after hot pressing line according to claim 2, characterized in that: The binarization configuration includes a binarization strategy, which includes: Divide the grayscale values ​​from 0 to 255 into a parts evenly, marked as equal parts; the length of each equal part is 255÷a; the starting value and ending value of each equal part are (255÷a)×b and (255÷a)×(b+1), respectively; where b is a positive integer from 0 to a-1; Get the number of detected gray values ​​in each equally divided part, marked as the number of detections; Draw a histogram with the grayscale value as the X-axis, the number of detections as the Y-axis, and the evenly divided part as the histogram interval, marked as the detection grayscale histogram; The part of the grayscale histogram that is larger than the average number of adjacent detections on the left and right sides is marked as the first target part; Obtain the first target portion with the smallest starting value and mark it as the second target portion; Get the first target part with the largest starting value and mark it as the third target part; Obtain an evenly divided portion with the smallest starting value between the second target portion and the third target portion, and mark it as the fourth target portion; Calculate the average of the starting value and the ending value of the fourth target part, and mark it as the dot binarization threshold; In the grayscale image after hot pressing, the detection grayscale values ​​greater than the dot binarization threshold are set to 0, and the detection grayscale values ​​less than or equal to the binarization threshold are set to 255 to obtain the binarized image after hot pressing.

4. The AOI inspection system for light guide plate after hot pressing line according to claim 3, characterized in that: The contour extraction is configured with a contour extraction strategy, which includes: In the binary image after hot pressing, obtain the pixel with a detection grayscale value of 0 adjacent to the detection grayscale value of 255 and mark it as the initial pixel; determine whether there are any pixels with a detection grayscale value of 0 around the initial pixel; if not, obtain a new initial pixel; if so, mark the initial pixel as the edge starting pixel; Starting from the pixel adjacent to the left of the edge starting pixel and the edge starting pixel as the rotation center, rotate clockwise to search for the first pixel whose grayscale value changes from 255 to 0, and mark it as the edge search pixel; then use the edge search pixel as the rotation center to obtain a new edge search pixel, and stop the operation when the new edge search pixel is the same as the edge starting pixel. The outline composed of the edge starting pixel and all the edge search pixels is obtained, and marked as the detection dot outline.

5. The AOI inspection system for light guide plate after hot pressing line according to claim 4, characterized in that: The reference point setting configuration includes a reference point setting strategy, and the reference point setting strategy includes: Obtain all the detection point contours in the binary image after hot pressing; Draw a second number of coordinate points at the same intervals on the detection dot contour, marking them as contour coordinate points; Connect the contour coordinate points in sequence along the detection point contour to obtain line segments, which are marked as contour connection segments; Get the angles between all adjacent contour connecting line segments and mark them as contour angles; Calculate the mean of the contour angles and mark it as the mean contour angle; Calculate the absolute value of the difference between all contour angles and the mean contour angle, and mark it as the reference difference; Sort the reference differences from small to large, obtain the intersection points of the contour angles corresponding to the first four reference differences, and mark them as the first coordinate point, the second coordinate point, the third coordinate point, and the fourth coordinate point respectively.

6. The AOI inspection system for light guide plate after hot pressing line according to claim 5, characterized in that: The reference point setting module is configured with a reference point setting strategy, and the reference point setting strategy includes: Connect the first coordinate point and the second coordinate point to obtain a line segment, which is marked as the first line segment; connect the second coordinate point and the third coordinate point to obtain a line segment, which is marked as the second line segment; Draw a perpendicular line to the first line segment through the midpoint of the first line segment and mark it as the first perpendicular line; draw a perpendicular line to the second line segment through the midpoint of the second line segment and mark it as the second perpendicular line; Obtain the intersection of the first perpendicular line and the second perpendicular line and mark it as the detection point reference point.

7. The AOI inspection system for light guide plate after hot pressing line according to claim 6, characterized in that: The detection value acquisition module is configured with a detection value acquisition strategy, and the detection value acquisition strategy includes: Mark the pixels on the detection dot outline as detection outline pixels; Get the distance from the detection dot reference point to the detection contour pixel point, marked as the dot detection value.

8. The AOI inspection system for light guide plate after hot pressing line according to claim 7, characterized in that: The threshold acquisition module is configured with a threshold acquisition strategy, and the threshold acquisition strategy includes: Marking the first number of normal images of the light guide plates after hot pressing as normal images; obtaining all the dot detection values ​​of each detection dot outline in the normal images and marking them as normal distances; Get the range of normal distances, marked as C1 to Cn; divide the range of fall comparison values ​​evenly into d parts, marked as normal parts; the length of each normal part is (Cn-C1)÷d; the starting value and ending value of each normal part are C1+[(Cn-C1)÷d]×e and C1+[(Cn-C1)÷d]×(e+1), respectively; where e is a positive integer from 0 to d-1; Count the number of each normal part and mark it as the number of normal parts; Sort the number of normal parts from small to large according to the starting value of the normal part to obtain the normal sequence number, which is a positive integer starting from 1; Get the frequency of normal distance, marked as Z; The normal number threshold is calculated as: G = f × (Z ÷ d); where Z is the fall threshold and f is the ratio value from 0 to 1; Determine whether the number of normal parts is less than the normal number threshold according to the normal sequence number from small to large. If not, stop judging directly. If so, delete the number of normal parts and continue judging whether the next number of normal parts is less than the normal number threshold until the number of normal parts is greater than or equal to the normal number threshold. Get the starting value of the normal part corresponding to the number of normal parts on the left at this time and mark it as the first qualified threshold. According to the normal serial number, determine whether the number of normal parts is less than the normal number threshold from large to small. If not, stop judging directly. If so, delete the number of normal parts and continue to judge whether the next number of normal parts is less than the normal number threshold, until the number of normal parts is greater than or equal to the normal number threshold, stop judging; obtain the end value of the normal part corresponding to the number of normal parts on the far right at this time, and mark it as the second qualified threshold.

9. The AOI inspection system for light guide plates after hot pressing according to claim 8, characterized in that: The judgment module is configured with a judgment strategy, and the judgment strategy includes: Determine whether all dot detection values ​​are greater than or equal to the first qualified threshold and less than or equal to the second qualified threshold. If so, generate a signal that the light guide plate hot pressing is qualified; if not, generate a signal that the light guide plate hot pressing is unqualified.

10. A light guide plate post-hot pressing line AOI inspection method, applicable to a light guide plate post-hot pressing line AOI inspection system according to any one of claims 1 to 9, characterized in that: The steps include: Obtain an image of the light guide plate after hot pressing, marked as the image after hot pressing; Performing grayscale processing on the hot pressed image to obtain a hot pressed grayscale image; Binarizing the hot pressed grayscale image to obtain a hot pressed binary image; Obtain the detection dot outline based on the binary image after hot pressing; Obtaining detection dot reference points based on dot outlines; Acquire a dot detection value based on a detection dot outline and a detection dot reference point; Acquire a first qualified threshold and a second qualified threshold based on a first number of images of normal light guide plates after hot pressing; Whether the light guide plate is qualified after hot pressing is determined based on the halftone dot detection value, the first qualified threshold value, and the second qualified threshold value.

Images