Method for determining defect level of glass substrate, computer device and storage medium

Abstract

The present application discloses a method, a computer device and a storage medium for determining the defect level of a glass substrate, which belongs to the technical field of glass substrate defect detection, wherein the method includes S101, collecting an image of a defect-free glass substrate as a reference image, processing the reference image to obtain a first contour line of the defect-free glass substrate; S201, collecting an image of a glass substrate to be detected as a determination image, processing the determination image, and inputting the processed determination image into a glass substrate defect detection model to obtain a second contour line of the glass substrate to be detected and the defect area and defect position in the determination image; S301, based on the first contour line, the second contour line, and the information of the defect area and the defect position, determining the defect level of the glass substrate to be detected. The technical solution provided by the present application can effectively determine the quality of the glass substrate, and accurately classify the defect level of the defective glass substrate, thereby avoiding waste of resources and saving costs.

Description

Technical Field

[0001] The present invention relates to the technical field of glass substrate defect detection, and in particular to a method for determining a defect level of a glass substrate, a computer device and a storage medium. Background Art

[0002] With the development of society, electronic display devices are being updated faster and faster, and the types and sizes of display devices are increasing, and the requirements for display devices are becoming higher and higher. As the main raw material of liquid crystal displays, glass substrates are prone to defects during the production process. The product quality and utilization rate are directly related to the imaging effect of liquid crystal displays and the cost of glass substrate manufacturers.

[0003] In the manufacturing process of glass substrates, defect detection is generally performed based on a glass substrate defect detection model. However, this detection method can only determine whether there are defects in the glass substrate and the type of defects, and cannot classify the defects in the glass substrate. As a result, it is impossible to effectively recycle the defective glass substrates according to the defect level, which not only causes a huge waste of resources, but also seriously restricts the profit margin of the enterprise. Summary of the invention

[0004] One advantage of the present invention is that it provides a method for determining the defect level of a glass substrate, a computer device and a storage medium, wherein the presence or absence of defects and the defect level of a glass substrate to be inspected are determined based on a first contour line of a defect-free glass substrate, a second contour line of a glass substrate to be inspected and corresponding defect areas and defect positions, which can effectively determine the quality of the glass substrate, avoid directly scrapping the defective glass substrate and seriously wasting resources, and perform corresponding operations according to the defect level of the defective glass substrate, thereby achieving maximum recycling of the defective glass substrate, thereby reducing enterprise costs and improving enterprise profitability.

[0005] To achieve at least one of the above advantages of the present invention, in a first aspect, the present invention provides a method for determining a defect level of a glass substrate, comprising the following steps:

[0006] S101, collecting an image of a defect-free glass substrate as a reference image, and processing the reference image to obtain a first contour line of the defect-free glass substrate;

[0007] S201, collecting an image of the glass substrate to be inspected as a determination image, processing the determination image, and inputting the processed determination image into a glass substrate defect detection model to obtain a second contour line of the glass substrate to be inspected and a defect area and defect position existing in the determination image;

[0008] S301 : Determine a defect level of a glass substrate to be inspected based on the first contour line, the second contour line, and information about the defect area and the defect position.

[0009] According to an embodiment of the present invention, in step S101, the reference image is processed to obtain a first contour line of a defect-free glass substrate, specifically:

[0010] Performing grayscale processing on the reference image to obtain a grayscale image, and converting the grayscale image into a binary image;

[0011] Contour extraction is performed based on the binary image to draw the first contour line, where the first contour line is the outer contour line of the defect-free glass substrate.

[0012] According to an embodiment of the present invention, in step S201, the outer contour line of the glass substrate to be inspected is determined based on the determination image;

[0013] Determine the defects existing in the glass substrate to be detected by using the glass substrate defect detection model, and judge whether the defects include internal defects. If they do, perform contour detection on the internal defects to obtain an internal defect contour line, and perform contour approximation processing on the internal defect contour line to generate a closed approximate contour line;

[0014] If the internal defect exists, the second contour line is composed of the approximate contour line and the outer contour line of the glass substrate to be inspected; if the internal defect does not exist, the second contour line is the outer contour line of the glass substrate to be inspected.

[0015] According to an embodiment of the present invention, in step S201, the closed approximate contour line is generated based on a circumscribed rectangle of the internal defect contour line or a minimum circumscribed circle of the internal defect contour line.

[0016] According to an embodiment of the present invention, in step S301, the outer contour line of the glass substrate to be inspected is matched with the first contour line to determine whether the glass substrate to be inspected has an edge defect. If an edge defect exists and the second contour line does not include the approximate contour line, the glass substrate to be inspected is determined to have a slight defect. If no edge defect exists and the second contour line does not include the approximate contour line, the glass substrate to be inspected is determined to have no defect.

[0017] According to an embodiment of the present invention, if the second contour line is composed of the approximate contour line and the outer contour line of the glass substrate to be inspected, the centroid corresponding to the outer contour line of the glass substrate to be inspected is determined, and the shortest distance between the approximate contour line and the centroid is determined;

[0018] The shortest distance is compared with a preset distance. If the shortest distance is smaller than the preset distance, it is determined that the glass substrate to be inspected has a severe defect.

[0019] According to an embodiment of the present invention, if the shortest distance is not less than the preset distance, the glass substrate to be inspected is divided into four sub-plates by a cross with the centroid as the center, and the defect area in each sub-plate is calculated respectively, and the defect area ratio of each sub-plate is calculated based on the defect area;

[0020] Determine the number of sub-boards whose defect area ratio exceeds a preset value, and if the number exceeds two, determine that the glass substrate to be inspected is a severe defect;

[0021] If the number is two, the relative positions of the two sub-plates are determined. If they are adjacent sub-plates, the glass substrate to be inspected is determined to have a moderate defect. If they are diagonal sub-plates, the glass substrate to be inspected is determined to have a severe defect.

[0022] If the number is one, the glass substrate to be inspected is determined to be a medium defect.

[0023] According to an embodiment of the present invention, the method further comprises step S401, applying a corresponding invisible mark on the inspected glass substrate according to the defect level of the glass substrate to be inspected, wherein the invisible mark is a mark identifiable by subsequent workstations.

[0024] In a second aspect, the present application provides a computer device for determining a defect level of a glass substrate, wherein the computer device comprises:

[0025] at least one processor;

[0026] and at least one memory, wherein the memory is connected to the processor signal and the memory stores program instructions, and when the program instructions are executed by the processor, the computer device executes the above-mentioned method for determining the defect level of the glass substrate.

[0027] In a third aspect, the present application provides a storage medium for determining the defect level of a glass substrate, wherein the storage medium stores a computer program, and when the computer program runs on a computer or a processor, the computer or the processor executes the aforementioned method for determining the defect level of a glass substrate.

[0028] These and other objects, features and advantages of the present invention will be fully reflected in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 A schematic flow chart of a method for determining a defect level of a glass substrate according to a preferred embodiment of the present application is shown.

[0030] Figure 2 A schematic diagram showing the approximate outline of a circumscribed rectangle of a preferred embodiment of the present application is shown.

[0031] Figure 3 A schematic diagram showing the approximate contour line of the minimum circumscribed circle of a preferred embodiment of the present application is shown.

[0032] Figure 4 A schematic diagram of the structure of a computer device for determining the defect level of a glass substrate according to a preferred embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be applied to other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0034] Those skilled in the art should understand that, in the disclosure of the specification, the orientation or position relationship indicated by the terms "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. are based on the orientation or position relationship shown in the drawings, which are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operate in a specific orientation. Therefore, the above terms should not be understood as limiting the present invention.

[0035] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0036] As an existing mature technology, the glass substrate defect detection model can generally only detect whether there are defects on the glass substrate and the type of defects, such as edge defects or internal defects, but cannot clearly classify the defect levels of the glass substrate, resulting in the current situation of directly scrapping defective glass substrates. This not only causes a serious waste of resources and is not in line with the long-term development plans of the current domestic and international communities, but also invisibly greatly increases the cost burden of enterprises. If the defective glass substrates can be clearly classified into defect levels, glass substrates with serious defects can be scrapped, and glass substrates with less serious defects, such as glass substrates with mild defects or moderate defects, can be processed accordingly. For example, glass substrates with mild defects can be used on display devices with less demanding local imaging requirements, which can undoubtedly effectively save resources and reduce enterprise costs. Based on this, the present application proposes a method for determining the defect level of a glass substrate, a computer device, and a storage medium.

[0037] refer to Figure 1 A method for determining a defect level of a glass substrate according to a preferred embodiment of the present invention will be described in detail below, wherein the method for determining a defect level of a glass substrate comprises the following steps:

[0038] S101, collecting an image of a defect-free glass substrate as a reference image, and processing the reference image to obtain a first contour line of the defect-free glass substrate;

[0039] S201, collecting an image of the glass substrate to be inspected as a determination image, processing the determination image, and inputting the processed determination image into a glass substrate defect detection model to obtain a second contour line of the glass substrate to be inspected and a defect area and defect position existing in the determination image;

[0040] S301 : Determine a defect level of a glass substrate to be inspected based on the first contour line, the second contour line, and information about the defect area and the defect position.

[0041] More specifically, in step S101, the image of the defect-free glass substrate can be acquired through an image acquisition device, wherein the image acquisition device can be an industrial camera, such as a CCD camera or a CMOS camera, which has higher image stability, higher transmission capability, and higher anti-interference capability than ordinary cameras. In addition, when acquiring images, the images can be shot from multiple angles and multiple directions to avoid blind spots that affect the quality of the acquired images.

[0042] The reference image is a standard image, and the first contour line of the defect-free glass substrate can be obtained by processing the reference image. Since the surface of the defect-free glass substrate has no defects, no defect contour will be generated after processing the reference image.

[0043] In one or more embodiments of the present specification, the reference image is gray-processed to obtain a gray-scale image, and then the gray-scale image is converted into a binary image; contour extraction is performed based on the binary image to draw the first contour line, wherein the first contour line is the outer contour line of the defect-free glass substrate.

[0044] Grayscale image refers to an image that contains only brightness information but no color information. Grayscale processing of the reference image to obtain a grayscale image can be achieved through Python+OpenCV or MATLAB. Binary image refers to an image in which each pixel is black or white. Each pixel of the binary image only needs log2 2 = 1 bit of storage space, while each pixel of a grayscale image requires log2 256 =8 bits of storage space, therefore, binary images require less storage space and have lower requirements on equipment. In addition, binary images can describe contour information more clearly and are easier to extract contours.

[0045] In addition, in the actual production process, the glass substrate is transported along the assembly line and passes through the image acquisition device. The current glass substrate acquired by the image acquisition device is used as the glass substrate to be detected. At the same time, the image of the glass substrate to be detected acquired by the image acquisition device is used as the determination image for detecting whether the glass substrate has defects, wherein the determination image can be one or more images, and then the determination image is grayed and binarized. If there are multiple determination images, the multiple determination images can be image fused. Taking the graying and binarization of the determination image as an example, the grayed and binarized determination image is input into the glass substrate defect detection model to identify the defects in the glass substrate to be detected.

[0046] It is worth noting that when the glass substrate defect detection model detects defects in the glass substrate, it will mark the defects so that the contour of the defects can be detected and the area and location of the defects can be determined.

[0047] In addition, considering that there are many types of glass substrate defects, including scratches, broken edges, bubbles, etc., and the defect contours corresponding to various defects are inconsistent. Complex defect contours increase the difficulty of calculating the defect area, and the defect area surrounded by the defect contour will not only pollute the area within the contour, but also the glass substrate within a certain range outside the defect area with the defect area as the center of the circle cannot be used normally. Therefore, as a preferred embodiment, more specifically, the outer contour of the glass substrate to be detected is determined based on the judgment image;

[0048] Determine the defects existing in the glass substrate to be detected by using the glass substrate defect detection model, and judge whether the defects include internal defects. If they do, perform contour detection on the internal defects to obtain an internal defect contour line, and perform contour approximation processing on the internal defect contour line to generate a closed approximate contour line;

[0049] Among them, if the internal defect exists, the second contour line is composed of the approximate contour line and the outer contour line of the glass substrate to be detected; if the internal defect does not exist, the second contour line is the outer contour line of the glass substrate to be detected, so that the defect level of the glass substrate to be detected can be determined more accurately.

[0050] Further preferably, in step S201, the closed approximate contour line is generated based on a circumscribed rectangle of the internal defect contour line or a minimum circumscribed circle of the internal defect contour line.

[0051] like Figure 2 , is a schematic diagram of the approximate contour line of the circumscribed rectangle provided in one or more embodiments of this specification, wherein the defect contour is an irregular image, firstly, the contour information is selected, its circumscribed rectangle is obtained, and then the minimum vertical boundary rectangle of the contour is calculated, and the code is as follows:

[0052] x, y, w, h = cv2.boundingRect (contour information), where x, y are the coordinates of the upper left point of the rectangle, and w, h are the width and height of the rectangle.

[0053] Draw a bounding rectangle based on the coordinates of the upper left point and the length and width values. The origin of the coordinates is the upper left corner of the image, the right is the positive direction of the x-axis, and the downward is the positive direction of the y-axis. The implementation code is as follows:

[0054] Calculate the bounding rectangle and return the upper left coordinate point, length and width of the rectangle

[0055] x,y,w,h=cv2.boundingRect(cnt)

[0056] Draw a rectangle based on coordinates

[0057] rectangle=cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)

[0058] cv_show('rectangle',rectangle)

[0059] like Figure 3 , is a schematic diagram of the minimum circumscribed circle approximate contour line provided by one or more embodiments of this specification, wherein the code for implementing the minimum circumscribed circle approximate contour line is as follows:

[0060] Returns the center coordinates and radius of the circle

[0061] (x,y),radius=cv2.minEnclosingCircle(cnt)

[0062] Center coordinates

[0063] center=(int(x),int(y))

[0064] radius

[0065] radius = int(radius)

[0066] Draw the minimum circumscribed circle

[0067] circle=cv2.circle(img,center,radius(255,0,0),2)

[0068] cv_show('circle',circle)

[0069] Among them, center is the center of the circle, and radius is the radius of the circle.

[0070] Further preferably, in step S301, the outer contour line of the glass substrate to be inspected is matched with the first contour line to determine whether the glass substrate to be inspected has an edge defect; if an edge defect exists and the second contour line does not include the approximate contour line, the glass substrate to be inspected is determined to have a slight defect; if no edge defect exists and the second contour line does not include the approximate contour line, the glass substrate to be inspected is determined to have no defect.

[0071] That is to say, in the absence of internal defects, it is possible to directly determine whether the glass substrate to be inspected has a slight defect or no defect by whether there is an edge defect. For example, if the glass substrate has defects such as edge collapse and notches, its outer contour line will also be irregular. At this time, the outer contour line of the glass substrate is matched with the first contour line. Since the first contour line is the outer contour line of a defect-free glass substrate, if the outer contour line of the glass substrate can completely overlap with the first contour line, it means that the glass substrate to be inspected is defect-free. If they cannot completely overlap, it means that the glass substrate only has edge defects, so the glass substrate is determined to be a slight defect, and the non-overlapping position is recorded as the edge defect position of the glass substrate to be inspected.

[0072] Different liquid crystal display devices have different requirements for the size of the glass substrate. Taking the mobile phone display screen as an example, there are 5-inch screens, 5.1-inch screens, 5.5-inch screens, 6-inch screens, 6.5-inch screens, etc. If there are defects only on the edge of the glass substrate, the glass substrate can be cut and polished to obtain a relatively small glass substrate. Therefore, when the glass substrate to be tested only has edge defects but no internal defects, the glass substrate to be tested is judged as a slight defect.

[0073] In another case, if the glass substrate to be inspected has internal defects, such as bubbles, scratches, etc., it means that the glass substrate to be inspected has the approximate contour line, that is, the second contour line is composed of the approximate contour line and the outer contour line of the glass substrate to be inspected, then the centroid corresponding to the outer contour line of the glass substrate to be inspected is determined, and the shortest distance between the approximate contour line and the centroid is determined, so as to determine whether there is a defect within a certain range of the center position of the glass substrate;

[0074] Then, the shortest distance is compared with a preset distance. If the shortest distance is smaller than the preset distance, it means that the internal defect of the glass substrate is relatively close to the centroid of the glass substrate to be detected. The centroid is the center position of the glass substrate. If there are defects at the centroid position and / or the peripheral position of the centroid, the glass substrate to be detected is determined to be a severe defect, and the entire glass substrate is basically unusable. It should be noted that in the absence of edge defects, the outer contour line or the approximate contour line of the outer contour of the glass substrate to be detected completely overlaps with the first contour line. At this time, calculating the centroid of the glass substrate to be detected can more accurately determine the center position of the glass substrate. In the presence of edge defects, although the determination of the center position is not very accurate, it can also reflect the center position of the glass substrate to a certain extent, and does not affect the classification of defect levels.

[0075] Regarding the calculation and determination of the centroid, the centroid of the outer contour line may be determined according to the outer contour line of the glass substrate to be inspected, or the centroid of the glass substrate may be determined according to the approximate contour line of the outer contour of the glass substrate to be inspected.

[0076] Further preferably, if the shortest distance is not less than the preset distance, the glass substrate to be inspected is divided into four sub-plates by a cross with the centroid as the center, the defect area in each sub-plate is calculated respectively, and the defect area ratio of each sub-plate is calculated based on the defect area;

[0077] Determine the number of sub-boards whose defect area ratio exceeds a preset value, and if the number exceeds two, determine that the glass substrate to be inspected is a severe defect;

[0078] If the number is two, the relative positions of the two sub-plates are determined. If they are adjacent sub-plates, the glass substrate to be inspected is determined to have a moderate defect. If they are diagonal sub-plates, the glass substrate to be inspected is determined to have a severe defect.

[0079] If the number is one, the glass substrate to be inspected is determined to be a medium defect.

[0080] Further preferably, the method further comprises step S401, applying a corresponding invisible mark on the glass substrate after inspection according to the defect level of the glass substrate to be inspected, wherein the invisible mark is a mark that can be recognized by subsequent stations, such as an invisible QR code. The invisible QR code contains the defect level information of the glass substrate, and the invisible QR code can be recognized by an infrared scanning device to obtain the defect level information corresponding to the glass substrate, wherein the defect-free glass substrate flows directly into the next station, the glass substrate with slight defects can be recycled and trimmed to obtain a glass substrate with a smaller size, and the glass with moderate defects can be obtained by taking the center of mass as the origin and a preset distance as the radius to obtain a circular glass substrate for use in smaller display devices such as watches, and the glass substrate with severe defects is directly scrapped.

[0081] Therefore, the method for determining the defect level of a glass substrate provided in the present application can comprehensively and accurately classify the defect level of a glass substrate from multiple dimensions or multiple angles at the same time, including edge defects, internal defects, the minimum distance between the approximate contour line and the centroid, cross-dividing the glass substrate and determining the defect level by determining the number of sub-panels based on the defect area ratio, etc., or a combination of multiple means, to achieve accurate classification and maximized recycling of defective glass substrates, thereby effectively reducing waste of resources and reducing enterprise costs.

[0082] Secondly, based on the same idea, combined with Figure 4 The present application also provides a computer device for determining a defect level of a glass substrate, wherein the computer device comprises:

[0083] at least one processor;

[0084] and at least one memory, wherein the memory is connected to the processor by signal, generally by communication connection or electrical signal connection, and the memory stores program instructions, and when the program instructions are executed by the processor, the computer device executes the aforementioned method for determining the defect level of the glass substrate.

[0085] On the third aspect, based on the same idea, the present application also provides a storage medium for determining the defect level of a glass substrate, wherein the storage medium stores a computer program, and when the computer program runs on a computer or a processor, the computer or the processor executes the aforementioned method for determining the defect level of a glass substrate.

[0086] It should be understood by those skilled in the art that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The advantages of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

Claims

1. A method for determining a defect level of a glass substrate, characterized in that: The following steps are involved: S101, collecting an image of a defect-free glass substrate as a reference image, and processing the reference image to obtain a first contour line of the defect-free glass substrate; S201, collecting an image of the glass substrate to be inspected as a determination image, processing the determination image, and inputting the processed determination image into a glass substrate defect detection model to obtain a second contour line of the glass substrate to be inspected and a defect area and defect position existing in the determination image; S301, determining a defect level of a glass substrate to be inspected based on the first contour line, the second contour line, and information about the defect area and the defect position; In step S201, the outer contour line of the glass substrate to be inspected is determined based on the determination image; Determine the defects existing in the glass substrate to be detected by using the glass substrate defect detection model, and judge whether the defects include internal defects. If they do, perform contour detection on the internal defects to obtain an internal defect contour line, and perform contour approximation processing on the internal defect contour line to generate a closed approximate contour line; Wherein, if the internal defect exists, the second contour line is composed of the approximate contour line and the outer contour line of the glass substrate to be detected; in step S301, determining the defect level of the glass substrate to be detected includes: if the second contour line is composed of the approximate contour line and the outer contour line of the glass substrate to be detected, determining the centroid corresponding to the outer contour line of the glass substrate to be detected, and determining the shortest distance between the approximate contour line and the centroid, comparing the shortest distance with a preset distance, if the shortest distance is not less than the preset distance, cross-dividing the glass substrate to be detected with the centroid as the center to form four sub-plates, respectively calculating the defect area in each sub-plate, and calculating the defect area ratio of each sub-plate based on the defect area; Determine the number of sub-boards whose defect area ratio exceeds a preset value, and if the number exceeds two, determine that the glass substrate to be inspected is a severe defect; If the number is two, the relative positions of the two sub-plates are determined. If they are adjacent sub-plates, the glass substrate to be inspected is determined to have a moderate defect. If they are diagonal sub-plates, the glass substrate to be inspected is determined to have a severe defect. If the number is one, the glass substrate to be inspected is determined to be a medium defect.

2. The method for determining the defect level of a glass substrate according to claim 1, wherein: In step S101, the reference image is processed to obtain a first contour line of a defect-free glass substrate, specifically: Performing grayscale processing on the reference image to obtain a grayscale image, and converting the grayscale image into a binary image; Contour extraction is performed based on the binary image to draw the first contour line, where the first contour line is the outer contour line of the defect-free glass substrate.

3. The method for determining the defect level of a glass substrate according to claim 1, wherein: In step S201 , if the internal defect does not exist, the second contour line is the outer contour line of the glass substrate to be inspected.

4. The method for determining the defect level of a glass substrate according to claim 3, wherein: In step S201, the closed approximate contour line is generated based on the circumscribed rectangle of the internal defect contour line or the minimum circumscribed circle of the internal defect contour line.

5. The method for determining the defect level of a glass substrate according to claim 3 or 4, characterized in that: In step S301, the outer contour line of the glass substrate to be inspected is matched with the first contour line to determine whether the glass substrate to be inspected has an edge defect. If an edge defect exists and the second contour line does not include the approximate contour line, the glass substrate to be inspected is determined to have a slight defect. If no edge defect exists and the second contour line does not include the approximate contour line, the glass substrate to be inspected is determined to have no defect.

6. The method for determining the defect level of a glass substrate according to claim 5, wherein: In step S301, the shortest distance is compared with the preset distance. If the shortest distance is smaller than the preset distance, it is determined that the glass substrate to be inspected has a severe defect.

7. The method for determining the defect level of a glass substrate according to claim 6, wherein: The method further comprises step S401, applying corresponding invisible marks on the glass substrate after inspection according to the defect level of the glass substrate to be inspected, wherein the invisible marks are marks that can be identified by subsequent workstations.

8. A computer device for determining a defect level of a glass substrate, characterized in that: The computer device comprises: at least one processor; and at least one memory, wherein the memory is connected to the processor signal and the memory stores program instructions, and when the program instructions are executed by the processor, the computer device executes the method for determining the defect level of a glass substrate according to any one of claims 1 to 7.

9. A storage medium for determining a defect level of a glass substrate, characterized in that: The storage medium stores a computer program, and when the computer program runs on a computer or a processor, the computer or the processor executes the method for determining the defect level of a glass substrate according to any one of claims 1 to 7.

Images