Defect detection system

Abstract

The utility model discloses a defect detection system. The defect detection system comprises a line light source, imaging equipment and control equipment, the line light source is arranged on the first surface side of a to-be-detected sheet, and the to-be-detected sheet is a light-transmitting sheet; the central normal of the linear light source intersects with the plane where the to-be-detected sheet is located, and the included angle between the central normal of the linear light source and the plane where the to-be-detected sheet is located is a first preset acute angle; the imaging equipment is arranged on the second face side of the to-be-detected sheet, and the central normal of the imaging equipment intersects with the plane where the to-be-detected sheet is located; the intersection area of the light emitted by the line light source and the plane where the to-be-detected sheet is located is configured in the view area of the imaging equipment; the control device communicates with the imaging device and is used for receiving a sheet image, sent by the imaging device, of the to-be-detected sheet. According to the utility model, defect images with distinction degree can be generated, the defect detection precision of the light-transmitting sheet is improved, and the defect type detection range is expanded.

Description

Technical Field

[0001] This application relates to the field of defect detection technology, and in particular to a defect detection system. Background Technology

[0002] Currently, defect detection in translucent sheets is typically based on direct-transmission light sources. These sources transmit light perpendicularly through the sheet, and by acquiring images of the sheet under this perpendicular transmission, the type of defect is detected based on the grayscale values ​​of the pixels in the image. Defects in translucent sheets are generally categorized as crystal points, black spots, impurities, and scratches. However, the types of defects detectable using direct-transmission light source imaging are limited; typically, only black spots and impurities can be detected, and even then, differentiation between them is not possible. Utility Model Content

[0003] This application provides a defect detection system that can solve the problem of difficulty in detecting defect types in light-transmitting sheets. By setting the angle between the center normal of the line light source and the plane where the sheet to be detected is located as a preset acute angle, the optical characteristics of different types of defects are highlighted, generating defect images with discriminative power, improving the defect detection accuracy of light-transmitting sheets, and expanding the defect type detection range.

[0004] In a first aspect, embodiments of this application provide a defect detection system, which includes a line light source, an imaging device, and a control device;

[0005] The linear light source is disposed on the first side of the sheet to be tested, and the sheet to be tested is a light-transmitting sheet; the central normal of the linear light source intersects the plane on which the sheet to be tested is located, and the angle between the central normal of the linear light source and the plane on which the sheet to be tested is located is a first preset acute angle;

[0006] The imaging device is disposed on the second side of the sheet to be tested, and the central normal of the imaging device intersects the plane on which the sheet to be tested is located; the intersection area of ​​the light emitted by the line light source and the plane on which the sheet to be tested is located is within the field of view of the imaging device;

[0007] The control device communicates with the imaging device and is used to receive sheet images of the sheet to be inspected sent by the imaging device.

[0008] Furthermore, the first preset acute angle is greater than 45°.

[0009] Furthermore, the value range of the first preset acute angle is (50°, 70°).

[0010] Furthermore, the center normal of the imaging device is perpendicular to the plane of the sheet to be tested.

[0011] Furthermore, the line light source extends along a first direction, which is parallel to the plane of the sheet to be tested.

[0012] Furthermore, the center normal of the line light source and the center normal of the imaging device intersect at the same point on the plane where the sheet to be tested is located.

[0013] Furthermore, the line light source extends along a first direction, and the sheet to be tested extends along a second direction, which is perpendicular to the first direction.

[0014] Furthermore, the line light source extends along the first direction, and the sheet to be tested extends along the second direction, the angle between the second direction and the first direction being a second preset acute angle.

[0015] Furthermore, the value range of the second preset acute angle is (30°, 60°).

[0016] Furthermore, the line light source extends along a first direction, and a light diffusion device is provided in the line light source to diffuse the light emitted by the line light source along the first direction so that the light distribution in the first direction is uniform.

[0017] The technical solution provided in this application embodiment includes a defect detection system comprising a line light source, an imaging device, and a control device. The line light source is disposed on a first side of the sheet to be inspected, and the sheet to be inspected is a light-transmitting sheet. The central normal of the line light source intersects the plane of the sheet to be inspected, and the angle between the central normal of the line light source and the plane of the sheet to be inspected is a first preset acute angle. The imaging device is disposed on a second side of the sheet to be inspected, and the central normal of the imaging device intersects the plane of the sheet to be inspected. The intersection area between the light emitted by the line light source and the plane of the sheet to be inspected is configured within the field of view of the imaging device. The control device communicates with the imaging device and is used to receive the sheet image of the sheet to be inspected sent by the imaging device. The technical solution provided in this application can solve the problem of difficulty in detecting defect types in light-transmitting sheets. By setting the angle between the central normal of the line light source and the plane of the sheet to be inspected to a preset acute angle, the optical characteristics of different types of defects are highlighted, generating defect images with discriminative power, improving the defect detection accuracy of light-transmitting sheets, and expanding the defect type detection range. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of this utility model, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this utility model. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the defect detection system provided in Embodiment 1 of this application;

[0020] Figure 2 This is a schematic diagram of the configuration of the defect detection system provided in Embodiment 2 of this application;

[0021] Figure 3 This is a bottom view schematic diagram of the positional relationship between the sheet to be tested and the line light source provided in Embodiment 2 of this application;

[0022] Figure 4 This is a schematic diagram of defect type imaging provided in an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of the configuration of the defect detection system provided in Embodiment 3 of this application;

[0024] Figure 6 This is a bottom view schematic diagram of the positional relationship between the sheet to be tested and the line light source provided in Embodiment 3 of this application. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. 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 should fall within the protection scope of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this utility model are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the utility model described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1This is a schematic diagram of a defect detection system provided in Embodiment 1 of the present invention. This embodiment is applicable to defect detection scenarios of transparent, semi-transparent and other thin film materials. The defect detection system can be implemented by software and / or hardware.

[0029] like Figure 1 As shown, the defect detection system 100 includes a line light source 110, an imaging device 120, and a control device 130;

[0030] The linear light source 110 is disposed on the first side of the sheet to be tested, and the sheet to be tested is a light-transmitting sheet; the central normal of the linear light source 110 intersects the plane on which the sheet to be tested is located, and the angle between the central normal of the linear light source 110 and the plane on which the sheet to be tested is located is a first preset acute angle;

[0031] The imaging device 120 is disposed on the second side of the sheet to be tested, and the central normal of the imaging device 120 intersects the plane on which the sheet to be tested is located; the intersection area of ​​the light emitted by the line light source 110 and the plane on which the sheet to be tested is located is disposed within the field of view of the imaging device 120.

[0032] The control device 130 communicates with the imaging device 120 and is used to receive the sheet image of the sheet to be tested sent by the imaging device 120.

[0033] In this solution, the defect detection system 100 is used to detect defects in a light-transmitting sheet. The defect detection system 100 may include a line light source 110, an imaging device 120, and a control device 130. The line light source 110 is disposed on the first surface of the sheet to be inspected, and is used to illuminate the first surface of the sheet at a preset incident angle. Therefore, the central normal of the line light source 110 intersects the plane of the sheet to be inspected, and the angle between the central normal of the line light source and the plane of the sheet to be inspected is a first preset acute angle. The line light source is extended along a first direction, and the sheet to be inspected is extended along a second direction. The second direction can be perpendicular to the first direction or form a preset angle with the first direction.

[0034] Understandably, since the sheet to be tested is a translucent sheet, when the line light source 110 illuminates the first surface of the sheet to be tested at a preset incident angle, a light band area will appear on the second surface of the sheet to be tested. The preset incident angle and the first preset acute angle are complementary angles. The imaging device 120 is disposed on the second surface of the sheet to be tested and is used to image the light band area presented on the second surface of the sheet to be tested. The central normal of the imaging device 120 intersects the plane of the sheet to be tested, and the intersection area between the light emitted by the line light source 110 and the plane of the sheet to be tested is configured within the field of view of the imaging device 120, so that the imaging device 120 can completely image the light band area. The control device 130 can communicate with the imaging device 120 to receive the sheet image of the sheet to be tested sent by the imaging device 120. The control device 130 can also communicate with the line light source 110 to control the emission of light by the line light source 110. Specifically, the control device 130 can control parameters such as the time, angle, and intensity of the light emitted by the line light source 110.

[0035] Optionally, the first preset acute angle is greater than 45°.

[0036] As is easily understood, defects in translucent sheets typically result in uneven areas such as bumps and pits on the surface. When the light emitted by the line light source 110 enters the sheet to be inspected at an acute angle, the uneven areas are prone to refraction and scattering. This leads to more reflected light from the uneven areas than from the smooth areas. The increased reflected light causes the uneven areas to appear with higher grayscale values ​​in the sheet image, thus enhancing the image contrast between defective and non-defective areas. Compared to a direct-transmission line light source, this method can more accurately detect and identify defects. A smaller incident angle allows the light to penetrate the translucent material more easily, achieving a more pronounced imaging effect. Therefore, the preset incident angle can typically be less than 45°, and the first preset acute angle can be greater than 45°.

[0037] Preferably, the value range of the first preset acute angle is (50°, 70°).

[0038] Understandably, the smaller the incident angle, the closer the incident light is to the normal, resulting in a more direct-transmission effect for the sheet image and poorer defect feature differentiation. Therefore, the incident angle is usually greater than 20° to achieve a low-angle transmission effect. The larger the incident angle, the closer the incident light is to the plane of the sheet being inspected, resulting in lower transmittance. However, when the incident angle is below 40°, the rate of transmittance reduction is relatively small. When the incident angle is greater than 40°, the rate of transmittance reduction increases significantly with increasing incident angle. When the incident angle is greater than 60°, the transmittance decreases sharply. Therefore, the preferred angle range for the preset incident angle can be set to (20°, 40°), and the range for the first preset acute angle can be set to (50°, 70°).

[0039] Optionally, the center normal of the imaging device 120 may be perpendicular to the plane of the sheet to be tested.

[0040] The center normal of the imaging device 120 can be perpendicular to the plane of the sheet to be inspected, allowing the imaging device 120 to perform orthophoto imaging on the light band area. Compared to oblique imaging, orthophoto imaging of the sheet can have higher resolution and clearer defect details. At the same time, compared to oblique imaging, orthophoto imaging by the imaging device 120 can have a larger image acquisition field of view, improving defect detection efficiency.

[0041] In this embodiment, the line light source 110 can extend along a first direction, which can be parallel to the plane of the sheet to be tested.

[0042] Understandably, different optical path distances cause differences in light intensity when the light reaches the sheet to be inspected. These differences in light intensity lead to grayscale errors in the light band area during imaging, which can easily affect the accuracy of defect detection. Therefore, keeping the extension direction of the line light source parallel to the plane of the sheet to be inspected ensures that the light emitted by the line light source 110 reaches the sheet at the same distance, avoiding grayscale errors in the sheet image and improving the reliability of defect detection.

[0043] In one feasible embodiment, the central normal of the line light source 110 intersects the central normal of the imaging device 120 at the same point on the plane where the sheet to be tested is located.

[0044] The central normal of the line light source 110 intersects the central normal of the imaging device 120 at the same point on the plane where the sheet to be tested is located, which can make the light band area located in the center of the field of view of the imaging device 120, ensuring clear imaging of the light band area.

[0045] In a preferred embodiment, the line light source 110 extends along a first direction, and the line light source 110 is provided with a light diffusion device for diffusing the light emitted by the line light source 110 along the first direction so that the light distribution in the first direction is uniform.

[0046] The light-diffusing device can be an optical device with a micro-uneven structure, such as a diffusion film. The light-diffusing device can be used to uniformly scatter light, reduce light spots and brightness unevenness, thereby improving the uniformity of the displayed image. The light-diffusing device in the line light source 110 can diffuse the light emitted by the line light source 110 along the extension direction of the line light source 110, avoiding imaging errors caused by uneven light distribution along the extension direction of the light source, and ensuring the reliability of imaging in the light band area.

[0047] After receiving a detection signal from the sheet to be inspected, the control device 130 controls the line light source 110 to emit light, illuminating the first surface of the sheet at a preset incident angle. Simultaneously, the control device 120 images the light band area presented on the second surface of the sheet, thereby acquiring an image of the sheet. The detection signal can be a signal indicating the sheet is in position or a signal to start defect detection. In a specific example, the sheet to be inspected can be a light-transmitting roll, and the detection signal can be a signal to activate the defect detection line of the light-transmitting roll.

[0048] Because sheet images generated under low-angle transmission conditions can enhance the contrast between defective and non-defective areas, a higher detection probability and accuracy for translucent sheet defect types can be achieved based on these images. Specifically, the control device 130 can perform defect detection on the sheet image according to a preset defect detection algorithm to obtain the defect detection results for the sheet to be detected. These defect detection results may include information such as the number of defects, defect identifiers, defect locations, and defect types.

[0049] The control device 130 can identify defects in the sheet to be inspected based on the grayscale features of the defects presented in the sheet image, and obtain the defect detection result of the sheet to be inspected. The grayscale features can include a range of grayscale values ​​for defects, which can be used to represent the range of grayscale values ​​presented by defects in the sheet image. There can be one or more grayscale value ranges for defects, and these ranges can include grayscale value ranges matching various defect types, such as crystal points, black spots, impurities, and scratches. The control device 130 can sequentially match the grayscale values ​​of each pixel in the sheet image with the grayscale value ranges of the defects, filter out pixels whose grayscale values ​​belong to the defect grayscale value ranges, and then determine the defect detection result based on the distribution of pixels whose grayscale values ​​belong to the defect grayscale value ranges in the sheet image.

[0050] In another feasible approach, the control device 130 can pre-acquire a sheet sample dataset, which may include multiple sets of sheet samples. Each set of sheet samples includes a sheet sample image and defect detection results matching the sheet sample images. The control device 130 can pre-build a defect detection network based on a convolutional neural network, using the sheet sample images as input and the defect detection results matching the sheet sample images as supervision to train the defect detection network and obtain a defect detection model that meets the detection requirements. The control device 130 can input the sheet image of the sheet to be detected into the pre-trained defect detection model to obtain the defect detection results of the sheet to be detected.

[0051] The technical solution provided in this application embodiment includes a defect detection system comprising a line light source, an imaging device, and a control device. The line light source is disposed on a first side of the sheet to be inspected, and the sheet to be inspected is a light-transmitting sheet. The central normal of the line light source intersects the plane of the sheet to be inspected, and the angle between the central normal of the line light source and the plane of the sheet to be inspected is a first preset acute angle. The imaging device is disposed on a second side of the sheet to be inspected, and the central normal of the imaging device intersects the plane of the sheet to be inspected. The intersection area between the light emitted by the line light source and the plane of the sheet to be inspected is configured within the field of view of the imaging device. The control device communicates with the imaging device and is used to receive the sheet image of the sheet to be inspected sent by the imaging device. The technical solution provided in this application can solve the problem of difficulty in detecting defect types in light-transmitting sheets. By setting the angle between the central normal of the line light source and the plane of the sheet to be inspected to a preset acute angle, the optical characteristics of different types of defects are highlighted, generating defect images with discriminative power, improving the defect detection accuracy of light-transmitting sheets, and expanding the defect type detection range.

[0052] Example 2

[0053] This embodiment refines the positional relationship between the line light source and the sheet to be tested, based on the above embodiment.

[0054] In this embodiment, the line light source 110 extends along a first direction, and the sheet to be tested extends along a second direction, which is perpendicular to the first direction.

[0055] Figure 2 This is a schematic diagram of the configuration of the defect detection system provided in Embodiment 2 of this application. Figure 3 This is a bottom view schematic diagram of the positional relationship between the sheet to be tested and the line light source provided in Embodiment 2 of this application. In a specific example, the configuration of the line light source 110, the sheet to be tested, and the imaging device 120 can be as follows: Figure 2 As shown, the positional relationship between the line light source 110 and the sheet to be tested can be as follows: Figure 3 As shown. A line light source 110 is disposed on the first side of the sheet to be tested, and the central normal of the line light source 110 intersects the plane of the sheet to be tested; an imaging device 120 is disposed on the second side of the sheet to be tested, and the central normal of the imaging device 120 is perpendicular to the plane of the sheet to be tested; the angle between the central normal of the line light source 110 and the central normal of the imaging device 120 is an acute angle α; the central normal of the line light source 110 and the central normal of the imaging device 120 intersect at the same point on the plane of the sheet to be tested; the line light source 110 extends along a first direction, and the sheet to be tested extends along a second direction, which is perpendicular to the first direction.

[0056] To improve defect detection efficiency, the control device 130 can locate defect positions based on the grayscale values ​​of each pixel in the sheet image and a preset reference grayscale range, and extract the distribution areas of each defect from the sheet image. The reference grayscale range is the grayscale value range of pixels in the defect-free sheet image. The control device 130 can also pre-acquire a defect detection model, which can be obtained by training object detection models such as YOLO, Faster R-CNN, and SSD using sheet sample images marked with defect distribution areas. The control device 130 identifies the distribution areas of defects from the sheet image based on the defect detection model. Specifically, the distribution areas of defects can be represented by regular-shaped detection boxes such as rectangles or circles, or by irregular-shaped borders based on the contours of the defect boundaries.

[0057] After identifying each defect in the sheet image, the control device 130 can sequentially take each defect in the sheet image as a target defect, take the distribution area of ​​the target defect as a target area, and then determine the defect type of the target defect based on the image features within the target area.

[0058] In this scheme, the defect types include crystal points, black spots, and impurities. Figure 4 This is a schematic diagram of defect type imaging provided in the embodiments of this application. Defects such as crystal points and black spots are three-dimensional defects. Crystal point defects have a nodular appearance. Crystal points do not absorb light, and light is easily refracted and scattered in the crystal point defect area. Therefore, as... Figure 4 As shown, crystal point defect areas are easily illuminated. Compared to defect-free areas, the grayscale value of pixels in crystal point defect areas is higher, and they typically appear white in sheet images. Black point defect areas usually include the black point itself and the transparent area surrounding it. The black point is opaque and absorbs light that shines on it, while the transparent area around the black point is prone to refraction and scattering. For example... Figure 4 As shown, compared to defect-free areas, pixels at black spots have lower grayscale values ​​and appear black in the sheet image, while pixels in the transparent areas surrounding the black spots have higher grayscale values ​​and typically appear white in the sheet image. Therefore, as... Figure 4 As shown, the black spot defect area contains both black and white areas. Impurity defect areas absorb light; compared to defect-free areas, the pixels in impurity defect areas have lower grayscale values ​​and appear black in the sheet image.

[0059] Based on the grayscale characteristics of crystal points, black spots, and impurity defects in the sheet image, the control device 130 can preset a first grayscale threshold to represent the upper limit of the grayscale value of pixels that visually appear black in the sheet image. The control device 130 can compare the grayscale value of each pixel in the target area with the first grayscale threshold to determine whether there are any pixels in the target area with a grayscale value less than the first grayscale threshold. If so, it is determined that the target area has the first grayscale feature; otherwise, it is determined that the target area does not have the first grayscale feature.

[0060] Due to interference from the external environment, a small number of interfering pixels may appear in the sheet image. To more reliably determine whether a first grayscale feature exists in the target area, the control device 130 can count the number of pixels with grayscale values ​​less than the first grayscale threshold based on the comparison between the grayscale values ​​of each pixel in the target area and the first grayscale threshold. If the number of pixels reaches a preset threshold, it is determined that the first grayscale feature exists in the target area; if the number of pixels does not reach the preset threshold, it is determined that the first grayscale feature does not exist in the target area, and the pixels with grayscale values ​​less than the first grayscale threshold are interfering pixels caused by environmental factors.

[0061] The control device 130 can preset a second grayscale threshold to represent the lower limit of the grayscale value of pixels that visually appear white in the sheet image. The control device 130 can compare the grayscale value of each pixel in the target area with the second grayscale threshold to determine whether there are any pixels in the target area with a grayscale value greater than the second grayscale threshold. If so, it is determined that the target area has a second grayscale feature; if not, it is determined that the target area does not have a second grayscale feature.

[0062] Due to interference from the external environment, a small number of interfering pixels may appear in the sheet image. To more reliably determine whether a second grayscale feature exists in the target area, the control device 130 can count the number of pixels with grayscale values ​​greater than the second grayscale threshold based on the comparison between the grayscale value of each pixel in the target area and the second grayscale threshold. If the number of pixels reaches a preset threshold, it is determined that a second grayscale feature exists in the target area; if the number of pixels does not reach the preset threshold, it is determined that a second grayscale feature does not exist in the target area, and the pixels with grayscale values ​​greater than the second grayscale threshold are interfering pixels caused by environmental factors.

[0063] Understandably, the first grayscale feature determination result can be whether a first grayscale feature exists within the target area, and the second grayscale feature determination result can be whether a second grayscale feature exists within the target area. The control device 130 can determine the defect type of the target defect based on whether the first grayscale feature and the second grayscale feature exist within the target area.

[0064] Specifically, if the target area possesses a first grayscale feature but lacks a second grayscale feature, the target defect is determined to be an impurity defect, characterized by the presence of black areas without white areas within the target area. If the target area possesses both a first and second grayscale feature, the target defect is determined to be a black spot defect, characterized by the presence of both black and white areas within the target area. If the target area lacks both a first and second grayscale feature, the target defect is determined to be a crystal point defect, characterized by the presence of white areas without black areas within the target area.

[0065] This embodiment can distinguish defect types based on the grayscale characteristics of the image of defects under low-angle transmission conditions. The defect detection method is simple and fast, which is conducive to achieving accurate defect classification and ensuring the reliability and accuracy of defect detection of light-transmitting sheets.

[0066] Example 3

[0067] This embodiment refines the positional relationship between the line light source and the sheet to be tested, based on the above embodiment.

[0068] In this embodiment, the line light source 110 extends along a first direction, and the sheet to be tested extends along a second direction. The angle between the second direction and the first direction is a second preset acute angle.

[0069] Since scratches are defects generated during the movement of the sheet being inspected, light rays perpendicular to the direction of movement are easily deflected. Therefore, they can be displayed in the sheet image as follows: Figure 4 The white linear defect is shown. The line light source 110 typically has a diffusion film along its extension direction to diffuse the light in the first direction, ensuring uniform light distribution in that direction. However, because scratch defects are usually narrow and fine, and the light distribution of the line light source is uniform along its extension direction, the image of the scratch defect in the sheet image is not significantly different from that of the defect-free area, making identification difficult.

[0070] Figure 5 This is a schematic diagram of the configuration of the defect detection system provided in Embodiment 3 of this application. Figure 6 This is a bottom view schematic diagram illustrating the positional relationship between the sheet to be tested and the line light source provided in Embodiment 3 of this application. In this solution, the configuration of the line light source 110, the sheet to be tested, and the imaging device 120 can be as follows: Figure 5 As shown, the positional relationship between the sheet to be tested and the line light source can be as follows: Figure 6As shown. A line light source 110 is disposed on the first side of the sheet to be tested, and the central normal of the line light source 110 intersects the plane on which the sheet to be tested is located; an imaging device 120 is disposed on the second side of the sheet to be tested, and the central normal of the imaging device 120 is perpendicular to the plane on which the sheet to be tested is located; the angle between the central normal of the line light source 110 and the central normal of the imaging device 120 is an acute angle α; the line light source 110 extends along a first direction, and the sheet to be tested extends along a second direction, and the angle between the second direction and the first direction is a preset acute angle.

[0071] This solution allows light rays perpendicular to the extension direction of the line light source 110 to irradiate the scratch defect by forming a preset acute angle with the extension direction of the sheet to be inspected. This provides more light rays to irradiate the scratch defect, making the light refraction characteristics of the scratch defect more obvious, thereby increasing the difference between the scratch defect and the defect-free area.

[0072] In a preferred embodiment, the value range of the second preset acute angle is (30°, 60°).

[0073] Understandably, the included angle range (30°, 60°) is the middle range of the acute angle range (0°, 90°). The included angle range of (30°, 60°) can ensure that more light rays perpendicular to the extension direction of the line light source 110 participate in the illumination of the sheet to be tested, thereby highlighting the light refraction characteristics of the scratch defects.

[0074] In this scheme, the defect types include crystal points, black spots, impurities, and scratches.

[0075] To improve defect detection efficiency, the control device 130 can locate defect positions based on the grayscale values ​​of each pixel in the sheet image and a preset reference grayscale range, and extract the distribution areas of each defect from the sheet image. The reference grayscale range is the grayscale value range of pixels in the defect-free sheet image. The control device 130 can also pre-acquire a defect detection model, which can be obtained by training object detection models such as YOLO, Faster R-CNN, and SSD using sheet sample images marked with defect distribution areas. The control device 130 identifies the distribution areas of defects from the sheet image based on the defect detection model. Specifically, the distribution areas of defects can be represented by regular-shaped detection boxes such as rectangles or circles, or by irregular-shaped borders based on the contours of the defect boundaries.

[0076] After identifying each defect in the sheet image, the control device 130 can sequentially treat each defect in the sheet image as a target defect and the distribution area of ​​the target defects as a target region. Then, based on the image features within the target region, it can determine the defect type of the target defect. The control device 130 can preset a first grayscale threshold to represent the upper limit of the grayscale value of pixels that visually appear black in the sheet image. The control device 130 can compare the grayscale value of each pixel within the target region with the first grayscale threshold to determine whether there are any pixels within the target region with a grayscale value less than the first grayscale threshold. If such a pixel exists, it is determined that the target region possesses a first grayscale feature; otherwise, it is determined that the target region does not possess a first grayscale feature.

[0077] Due to interference from the external environment, a small number of interfering pixels may appear in the sheet image. To more reliably determine whether a first grayscale feature exists in the target area, the control device 130 compares the grayscale value of each pixel in the target area with a first grayscale threshold and counts the number of pixels with grayscale values ​​less than the first grayscale threshold. If the number of pixels reaches a preset threshold, it is determined that the target area has a first grayscale feature; if the number of pixels does not reach the preset threshold, it is determined that the target area does not have a first grayscale feature, and the pixels with grayscale values ​​less than the first grayscale threshold are interfering pixels caused by environmental factors.

[0078] The control device 130 can preset a second grayscale threshold to represent the lower limit of the grayscale value of pixels that visually appear white in the sheet image. The control device 130 can compare the grayscale value of each pixel in the target area with the second grayscale threshold to determine whether there are any pixels in the target area with a grayscale value greater than the second grayscale threshold. If so, it is determined that the target area has a second grayscale feature; if not, it is determined that the target area does not have a second grayscale feature.

[0079] Due to interference from the external environment, a small number of interfering pixels may appear in the sheet image. To more reliably determine whether a second grayscale feature exists in the target area, the control device 130 compares the grayscale value of each pixel in the target area with a second grayscale threshold and counts the number of pixels with grayscale values ​​greater than the second grayscale threshold. If the number of pixels reaches a preset threshold, it is determined that a second grayscale feature exists in the target area; if the number of pixels does not reach the preset threshold, it is determined that a second grayscale feature does not exist in the target area, and the pixels with grayscale values ​​greater than the second grayscale threshold are interfering pixels caused by environmental factors. It can be understood that the first grayscale feature determination result can be whether a first grayscale feature exists in the target area, and the second grayscale feature determination result can be whether a second grayscale feature exists in the target area. The control device 130 can determine the defect type of the target defect based on whether a first grayscale feature and a second grayscale feature exist in the target area.

[0080] Specifically, if the target area possesses a first grayscale feature but lacks a second grayscale feature, the target defect is determined to be an impurity defect, characterized by the presence of black areas without white areas within the target area. If the target area possesses both a first and second grayscale feature, the target defect is determined to be a black spot defect, characterized by the presence of both black and white areas within the target area. If the target area lacks both a first and second grayscale feature, the target defect is determined to be a crystal point defect or a scratch defect, characterized by the presence of white areas without black areas within the target area.

[0081] Understandably, since both crystal point defects and scratch defects exhibit secondary grayscale characteristics, it is difficult to distinguish between them solely based on the grayscale characteristics of the defect distribution area. Control device 130 can determine whether there are multiple types of the target defect in the sheet under inspection, such as a crystal point or a scratch, based on the defect type of each defect in the defect detection results. If multiple types of the target defect exist, proceed to step S340; otherwise, proceed to step S350.

[0082] If the defect type of the target defect is not unique, the control device 130 can acquire the descriptive information of the target area based on the shape characteristics of the target area. The descriptive information of the target area may include the center position, boundary position, and distance from the center to the boundary of the target area; the shape characteristics of the target area may include its length, width, area, and aspect ratio.

[0083] The control device 130 can identify target defects with non-unique defect types based on the shape characteristics of the target area, thereby correcting the defect type of the target defect to make it unique. For example, the control device can further determine the defect type of a target defect, such as a crystal point or a scratch, based on the length of the target area. If the length of the target area is greater than or equal to a preset length threshold, the defect type of the target defect is determined to be a scratch; if the length of the target area is less than the preset length threshold, the defect type of the target defect is determined to be a crystal point.

[0084] In one feasible solution, the shape feature includes the aspect ratio of the target region; if the defect type of the target defect is a crystal point or a scratch, the aspect ratio of the target region is determined; if the aspect ratio of the target region is greater than or equal to a preset ratio threshold, the defect type of the target defect is determined to be a scratch; if the aspect ratio of the target region is less than the preset ratio threshold, the defect type of the target defect is determined to be a crystal point.

[0085] The above scheme further judges target defects with non-unique defect types based on the aspect ratio of the target area. The aspect ratio can characterize the differences in defect distribution areas, which is conducive to achieving accurate classification of defect types and ensuring the reliability of defect classification.

[0086] This embodiment highlights the light refraction characteristics of scratch defects by making the extension direction of the line light source form a preset acute angle with the extension direction of the sheet to be inspected. When unique defect type determination cannot be achieved based on grayscale features, this solution utilizes the shape characteristics of the defect distribution area to achieve accurate defect classification, improving the defect detection accuracy of translucent sheets and expanding the defect type detection range.

[0087] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the appended claims.

Claims

1. A defect detection system, characterized in that, The defect detection system includes a line light source, an imaging device, and a control device; The linear light source is disposed on the first side of the sheet to be tested, and the sheet to be tested is a light-transmitting sheet; the central normal of the linear light source intersects the plane on which the sheet to be tested is located, and the angle between the central normal of the linear light source and the plane on which the sheet to be tested is located is a first preset acute angle; The imaging device is disposed on the second side of the sheet to be tested, and the central normal of the imaging device intersects the plane on which the sheet to be tested is located; the intersection area of ​​the light emitted by the line light source and the plane on which the sheet to be tested is located is within the field of view of the imaging device; The control device communicates with the imaging device and is used to receive sheet images of the sheet to be inspected sent by the imaging device.

2. The defect detection system according to claim 1, characterized in that, The first preset acute angle is greater than 45°.

3. The defect detection system according to claim 2, characterized in that, The first preset acute angle has a range of (50°, 70°).

4. The defect detection system according to claim 1, characterized in that, The center normal of the imaging device is perpendicular to the plane of the sheet to be tested.

5. The defect detection system according to claim 1, characterized in that, The linear light source extends along a first direction, which is parallel to the plane of the sheet to be tested.

6. The defect detection system according to claim 1, characterized in that, The center normal of the line light source and the center normal of the imaging device intersect at the same point on the plane where the sheet to be tested is located.

7. The defect detection system according to claim 1, characterized in that, The linear light source extends along a first direction, and the sheet to be tested extends along a second direction, which is perpendicular to the first direction.

8. The defect detection system according to claim 1, characterized in that, The linear light source extends along a first direction, and the sheet to be tested extends along a second direction, wherein the angle between the second direction and the first direction is a second preset acute angle.

9. The defect detection system according to claim 8, characterized in that, The second preset acute angle has a range of (30°, 60°).

10. The defect detection system according to claim 1, characterized in that, The line light source extends along a first direction, and a light diffusion device is provided in the line light source to diffuse the light emitted by the line light source along the first direction so that the light distribution in the first direction is uniform.

Images