A panel process absence detection method, system, device and storage medium

Abstract

The application provides a panel process missing detection method, system, device and storage medium, relates to the technical field of defect detection, and the method flow is: a standard template is acquired based on a normal panel image, and a to-be-matched template is acquired based on a panel image to be detected; a plurality of template detection boxes are set based on the standard template, and a plurality of matching detection boxes corresponding to the plurality of template detection boxes are acquired based on the to-be-matched template; a plurality of pixel detection total values are acquired based on the plurality of template detection boxes, and a plurality of pixel matching total values are acquired based on the plurality of matching detection boxes; and the corresponding pixel detection total values and the pixel matching total values are selected based on the size and position of the template detection boxes and the matching detection boxes to comprehensively detect the panel process missing. The application adopts the template matching and comprehensive detection mode to accurately detect the process missing, solves the problems that the process missing type defect is difficult to recognize features and the existing target detection model cannot effectively detect.

Description

Technical Field

[0001] This invention relates to the field of defect detection technology, and more specifically, to a method, system, device, and storage medium for detecting defects in panel manufacturing processes. Background Technology

[0002] Panel factories generate numerous defects during panel production. However, the entire panel manufacturing process is complex and has a long production cycle, often requiring considerable time from substrate preparation to final processing. Therefore, defects generated at each stage of the process must be constantly monitored to prevent them from flowing into the next process and reducing yield. Among these defects, process defects are a particularly serious one, directly leading to panel scrapping if they exist.

[0003] Traditional methods for detecting process defects involve using AOI (Automatic Optical Inspection) instruments to capture images of panel products, followed by manual defect assessment. If a process defect is found, the panel is repaired. However, this reliance on manual image analysis is susceptible to variations in experience and mental state, leading to a high misjudgment rate and relatively high labor costs. Therefore, many panel manufacturers have begun introducing automated defect detection and classification systems to replace manual inspection. However, these systems typically employ deep learning-based object detection algorithms as their core. These supervised learning algorithms are highly dependent on the quality of the training set samples. Process defects may not have obvious features, and the difference between the defective area and the surrounding normal background may be small, making it easy for the model to miss detections. Summary of the Invention

[0004] This invention provides a method, system, device, and storage medium for detecting defects in panel manufacturing processes, which solves the problem of missed detections in panel manufacturing process defect detection.

[0005] In a first aspect, embodiments of the present invention provide a method for detecting defects in panel manufacturing processes, the method flow being as follows:

[0006] A standard template is obtained based on a normal panel image, and a template to be matched is obtained based on the panel image to be detected.

[0007] Several template detection boxes are set based on a standard template, and several matching detection boxes corresponding to the template detection boxes are obtained based on the template to be matched.

[0008] The total value of a number of pixels is obtained based on a number of template detection boxes, and the total value of a number of pixels is obtained based on a number of matching detection boxes;

[0009] Based on the size and position of the template detection box and the matching detection box, the corresponding pixel detection total value and pixel matching total value are selected to comprehensively detect panel process defects.

[0010] In the above embodiments, the present invention uses template matching and comprehensive detection to accurately detect process defects, which solves the problem that existing target detection models are unable to effectively detect process defect identification features.

[0011] As one of the optional implementation methods of this application, the process of setting several template detection boxes based on a standard template is as follows:

[0012] A primary inspection frame is set based on a standard template, and the primary inspection frame contains all elements of the process.

[0013] A secondary detection frame is set based on the annotation template, and the secondary detection frame contains some elements of the process.

[0014] A three-level detection frame is set based on the annotation template, and the three-level detection frame contains some elements of the process.

[0015] As some optional embodiments of this application, the number of secondary detection frames is greater than the number of primary detection frames, and the size of the secondary detection frames is smaller than the size of the primary detection frames; the number of tertiary detection frames is equal to the number of primary detection frames, and the size of the tertiary detection frames is smaller than the size of the primary detection frames.

[0016] In the above embodiments, by setting the size, quantity, and dimensions of the detection frames, comprehensive detection with different accuracies and speeds can be achieved.

[0017] As some optional implementations of this application, the process of obtaining several matching detection boxes corresponding to several template detection boxes based on the template to be matched is as follows:

[0018] Based on the template to be matched, obtain the first-level matching box corresponding to the first-level detection box. The size and number of the first-level matching box are the same as the size and number of the first-level detection box.

[0019] Based on the template to be matched, obtain the secondary matching box corresponding to the secondary detection box. The size and number of the secondary matching box are the same as the size and number of the secondary detection box.

[0020] Based on the template to be matched, obtain the third-level matching boxes corresponding to the third-level detection boxes. The size and number of the third-level matching boxes are the same as the size and number of the third-level detection boxes.

[0021] In the above embodiments, the size of the first-level detection box and the corresponding first-level matching box is relatively the largest and the number is one; the size of the second-level detection box and the corresponding second-level matching box is relatively small and the number is three; the size of the third-level detection box and the corresponding third-level matching box is relatively the smallest and the number is one.

[0022] As some optional implementations of this application, the process of obtaining a total pixel detection value based on a number of template detection boxes and obtaining a total pixel matching value based on a number of matching detection boxes is as follows:

[0023] Obtain the corresponding first-level detection pixel matrix, second-level detection pixel matrix, and third-level detection pixel matrix based on the first-level detection box, second-level detection box, and third-level detection box;

[0024] The pixel values ​​corresponding to all coordinate points in the first-level detection pixel matrix, the second-level detection pixel matrix, and the third-level detection pixel matrix are added together to obtain the total pixel value of the first-level detection, the total pixel value of the second-level detection, and the total pixel value of the third-level detection.

[0025] Obtain the corresponding first-level matching pixel matrix, second-level matching pixel matrix, and third-level matching pixel matrix based on the first-level matching box, second-level matching box, and third-level matching box;

[0026] The pixel values ​​of all coordinates in the first-level matching pixel matrix, the second-level matching pixel matrix, and the third-level matching pixel matrix are added together to obtain the total pixel value of the first-level matching pixel matrix, the total pixel value of the second-level matching pixel matrix, and the total pixel value of the third-level matching pixel matrix.

[0027] In the above embodiments, the total pixel value and coordinate point information can be accurately obtained based on the pixel matrix.

[0028] As some optional implementations of this application, the process for comprehensively detecting panel process defects by selecting the corresponding pixel detection total value and pixel matching total value based on the size and position of the template detection box and the matching detection box is as follows:

[0029] First-level pixel difference determination is performed based on the total value of first-level detected pixels and the total value of first-level matched pixels. If the first-level pixel difference determination result is less than the first-level threshold, then second-level pixel difference determination is performed based on the total value of several second-level detected pixels and the total value of several second-level matched pixels. Otherwise, the panel manufacturing process is determined to be defective.

[0030] If the result of the second-level pixel difference determination is less than the second-level threshold, then a sliding self-matching determination is performed based on the total value of the third-level matched pixels and the total value of the third-level detected pixels; otherwise, the panel process is determined to be defective.

[0031] If all sliding self-matching judgment results are less than the level 3 threshold, the panel process is determined to be complete; otherwise, the panel process is determined to be missing.

[0032] As some optional embodiments of this application, the calculation process for the first-level pixel difference determination result, the second-level pixel difference determination result, and the sliding self-matching determination result is as follows:

[0033] Calculate the difference between the total value of first-level detected pixels and the total value of first-level matched pixels to obtain the first-level pixel difference determination result;

[0034] According to the different positions of several secondary detection boxes and several secondary matching boxes, different weight values ​​are assigned to the corresponding total value of secondary detection pixels and total value of secondary matching pixels. Based on the different weight values, the difference between several total values ​​of secondary detection pixels and several total values ​​of secondary matching pixels is calculated to obtain the secondary pixel difference judgment result.

[0035] The difference between the total value of several third-level detected pixels and the total value of third-level matched pixels is calculated by sliding self-matching to obtain the sliding self-matching judgment result.

[0036] In the above embodiments, the panel is initially detected for process defects using a first-level detection box and a first-level matching box. If the difference is greater than the first-level threshold, it indicates a large-area process defect. This initial detection allows for a simple and quick determination. However, for small-area process defects, the initial detection cannot detect them properly, resulting in missed detections. Therefore, the panel is further detected for process defects using a second-level detection box and a second-level matching box. If the difference is greater than the second-level threshold, it indicates a small-area defect at the second-level matching box location. This further detection allows for a more accurate determination. However, the detection speed is slower than the initial detection, and the determination result is only valid for the second-level matching box location because the coverage area of ​​the second-level matching box is limited. For small-area defects outside the second-level matching box location, further detection cannot detect them properly, resulting in missed detections. Therefore, the panel is then subjected to sliding self-matching detection for process defects using a third-level detection box and a third-level matching box. If the difference is less than the third-level threshold, it indicates a small-area defect. This sliding self-matching detection allows for an accurate determination, but the detection speed is slower than the initial and further detection.

[0037] In a second aspect, the present invention provides a panel manufacturing process defect detection system, characterized in that the system comprises:

[0038] The template acquisition unit acquires a standard template based on a normal panel image and acquires a template to be matched based on the panel image to be detected.

[0039] The target detection unit sets up several template detection boxes based on a standard template, and obtains several matching detection boxes corresponding to the several template detection boxes based on the template to be matched.

[0040] A pixel detection unit, wherein the pixel detection unit obtains a total pixel detection value based on a number of template detection boxes, and obtains a total pixel matching value based on a number of matching detection boxes;

[0041] The comprehensive detection unit performs comprehensive detection of panel process defects based on the size and position of the template detection frame and the matching detection frame, and selects the corresponding pixel detection total value and pixel matching total value.

[0042] In a third aspect, the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor performing the panel process defect detection method.

[0043] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the panel process defect detection method.

[0044] The beneficial effects of the present invention are as follows: The present invention uses template matching and comprehensive detection to accurately detect process defects, which solves the problem that existing target detection models are unable to effectively detect process defect identification features. Attached Figure Description

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram of the computer device structure of the hardware operating environment described in the embodiments of the present invention;

[0047] Figure 2 This is a flowchart of the panel manufacturing process defect detection method described in the embodiments of the present invention;

[0048] Figure 3 This is a schematic diagram of the first-level detection box and the first-level matching box according to an embodiment of the present invention;

[0049] Figure 4 This is a horizontal schematic diagram of the secondary detection box and the secondary matching box according to an embodiment of the present invention;

[0050] Figure 5 This is a vertical schematic diagram of the three-level detection box and the three-level matching box as described in the embodiment of the present invention;

[0051] Figure 6This is a structural block diagram of the panel manufacturing process defect detection system described in an embodiment of the present invention. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0053] In the panel manufacturing process, the entire production process of panel products is complex and the production cycle is long. It often takes a long time from the substrate to the completion of production. Therefore, defects generated in each process stage need to be monitored at all times to prevent defects from flowing into the next process and causing a decrease in yield.

[0054] To address the issue of missed detections in panel manufacturing process defect detection, this application provides a method, system, device, and storage medium for panel manufacturing process defect detection. Before introducing the specific technical solutions of this application, the hardware operating environment involved in the embodiments of this application will be described first.

[0055] Please see Figure 1 , Figure 1 This is a schematic diagram of the computer device structure of the hardware operating environment involved in the embodiments of this application.

[0056] like Figure 1 As shown, the computer device may include: a processor, such as a central processing unit (CPU), a communication bus, a user interface, a network interface, and memory. The communication bus is used to enable communication between these components. The user interface may include a display screen and an input unit such as a keyboard; optionally, the user interface may also include a standard wired interface or a wireless interface. The network interface may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The memory may be high-speed random access memory (RAM) or stable non-volatile memory (NVM), such as a disk drive; optionally, the memory may also be a storage device independent of the aforementioned processor.

[0057] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the computer device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0058] like Figure 1 As shown, a memory, as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and electronic programs.

[0059] exist Figure 1 In the computer device shown, the network interface is mainly used for data communication with the network server; the user interface is mainly used for data interaction with the user; the processor and memory in the computer device of this application can be set in the computer device, and the computer device calls the panel process defect detection system stored in the memory through the processor and executes the panel process defect detection method provided in the embodiment of this application.

[0060] Based on the hardware environment of the foregoing embodiments, embodiments of this application provide a method for detecting defects in panel manufacturing processes. Please refer to [link to relevant documentation]. Figure 2 , Figure 2 This is a flowchart of a panel manufacturing process defect detection method, which includes the following steps:

[0061] (1) Obtain a standard template based on a normal panel image, and obtain a template to be matched based on the panel image to be detected.

[0062] In this embodiment of the invention, since the lines on the panel surface are mostly repeated, both the standard template and the template to be matched contain at least one periodic element of the lines, that is, the line features of the standard template and the template to be matched can represent the overall line features of the product.

[0063] Several template detection frames with different shapes, sizes and positions are set on the surface of a standard template, and several matching detection frames with corresponding shapes, sizes and positions are obtained on the surface of the template to be matched.

[0064] In the embodiments of the present invention, please refer to Figure 3 , Figure 4 , Figure 5 , Figure 3 This is a schematic diagram of the first-level detection box and the first-level matching box. Figure 4 This is a horizontal schematic diagram of the secondary detection box and the secondary matching box. Figure 5 The diagram below shows a vertical representation of the three-level detection box and the three-level matching box. The process of setting up several template detection boxes based on the standard template is as follows:

[0065] (2.1) Set up a primary inspection frame based on a standard template, wherein the primary inspection frame contains all elements of the process;

[0066] (2.2) Set up a secondary inspection box based on the annotation template, wherein the secondary inspection box contains some elements of the process;

[0067] (2.3) Set up a three-level detection frame based on the annotation template. The three-level detection frame contains some elements of the process.

[0068] Specifically, the number of secondary detection frames is greater than the number of primary detection frames, and the size of the secondary detection frames is smaller than the size of the primary detection frames; the number of tertiary detection frames is equal to the number of primary detection frames, and the size of the tertiary detection frames is smaller than the size of the primary detection frames. Preferably, there is one primary detection frame, which includes the corresponding line of the process; there are three secondary detection frames, which are arranged side by side at different positions on the corresponding line of the process; and there is one tertiary detection frame, which is located at the top, bottom, left, or right side of the corresponding line of the process.

[0069] In this embodiment of the invention, the process of obtaining several matching detection boxes corresponding to several template detection boxes based on the template to be matched is as follows:

[0070] (2.3) Obtain the first-level detection boxes corresponding to the first-level detection boxes based on the template to be matched, wherein the size and number of the first-level matching boxes are the same as the size and number of the first-level detection boxes;

[0071] (2.4) Obtain the secondary matching boxes corresponding to the secondary detection boxes based on the template to be matched, wherein the size and number of the secondary matching boxes are the same as the size and number of the secondary detection boxes;

[0072] (2.5) Obtain the third-level matching box corresponding to the third-level detection box based on the template to be matched. The size and number of the third-level matching box are the same as the size and number of the third-level detection box.

[0073] Accordingly, there is one first-level matching box, three second-level matching boxes, and one third-level matching box.

[0074] (3) Obtain the total value of several pixel detections based on several template detection boxes, and obtain the total value of several pixel matching based on several matching detection boxes.

[0075] In this embodiment of the invention, the process for obtaining the total detection value of several pixels and the total matching value of several pixels is as follows:

[0076] (3.1) Obtain the corresponding first-level detection pixel matrix, second-level detection pixel matrix and third-level detection pixel matrix based on the first-level detection box, second-level detection box and third-level detection box;

[0077] (3.2) Sum the pixel values ​​corresponding to all coordinate points in the first-level detection pixel matrix, the second-level detection pixel matrix, and the third-level detection pixel matrix respectively to obtain the total value L of the first-level detection pixels. 11 Total pixel value L for secondary detection 12 L 13 L 14 And the total pixel value L of the three-level detection 15,

[0078] (3.3) Obtain the corresponding first-level matching pixel matrix, second-level matching pixel matrix, and third-level matching pixel matrix based on the first-level matching box, second-level matching box, and third-level matching box;

[0079] (3.4) Sum the pixel values ​​of all coordinates in the first-level matching pixel matrix, the second-level matching pixel matrix, and the third-level matching pixel matrix respectively to obtain the total value L of the first-level matching pixels. 21 Secondary matching pixel total value L 22 L 23 L 24 and the total pixel value L of the three-level matching 25 .

[0080] At the same time, by comparing the first-level detection pixel matrix, the second-level detection pixel matrix, and the third-level detection pixel matrix with the first-level matching pixel matrix, the second-level matching pixel matrix, and the third-level matching pixel matrix, detailed information on the location of process defects can be obtained.

[0081] (4) Based on the size and position of the template detection box and the matching detection box, select the corresponding pixel detection total value and pixel matching total value to perform comprehensive detection of panel process defects.

[0082] In this embodiment of the invention, the process for comprehensive detection of panel manufacturing defects is as follows:

[0083] (4.1) Based on the total value L of the first-level detection pixels 11 Total value of matching pixels L at level 1 21 Perform a first-level pixel difference determination. If the first-level pixel difference determination result is less than the first-level threshold T1, then the second-level detected pixel total value L is used. 12 L 13 L 14 and the total value of matching pixels in the second level L 22 L 23 L 24 Perform secondary pixel difference determination; otherwise, determine panel manufacturing process defects.

[0084] (4.2) If the result of the second-level pixel difference determination is less than the second-level threshold T2, then based on the total value L of the third-level matching pixels... 15 and the total pixel value L of the three-level detection 25 Perform a sliding self-matching judgment; otherwise, determine that the panel manufacturing process is missing.

[0085] (4.3) If the sliding self-matching judgment results are all less than the third-level threshold T3, the panel process is determined to be complete; otherwise, the panel process is determined to be missing.

[0086] Specifically, the calculation process for the first-level pixel difference determination result, the second-level pixel difference determination result, and the sliding self-matching determination result is as follows:

[0087] (4.11) Calculate the total value L of the first-level detected pixels. 11 Total value of matching pixels L at level 1 21 The difference D11 between them is used to obtain the first-level pixel difference determination result;

[0088] (4.12) According to the different positions of several secondary detection boxes and several secondary matching boxes, assign the corresponding total value L of secondary detection pixels. 12 L 13 L 14 and the total value of matching pixels in the second level L 22 L 23 L 24 Different weight values ​​α1, α2, and α3 are assigned, and the total value L of several secondary detection pixels is calculated based on the different weight values ​​α1, α2, and α3. 12 L 13 L 14 and the total value L of several secondary matching pixels 22 L 23 L 24 The difference D between them 21 The calculation formula is as follows: This is used to obtain the second-level pixel difference determination result.

[0089] D 21 =α1(L 12 -L 22 )+α2(L 13 -L 23 )+α3(L 14 -L 24 )

[0090] Since the process patterns corresponding to the secondary detection boxes and secondary matching boxes at different locations are different, the detection accuracy can be improved by assigning different weight values ​​α1, α2, and α3. That is, higher weights are assigned to the locations covered by more process patterns, and lower weights are assigned to the locations covered by fewer process patterns. Specifically, the weight values ​​α1, α2, and α3 are set according to the actual process patterns and the positions of the primary matching boxes, secondary matching boxes, and tertiary matching boxes.

[0091] (4.13) Calculate the total value L of the three-level detected pixels using a sliding self-matching method. 15 The total pixel value L of the third-level matching 25 The difference D between them 31 In order to obtain the sliding self-matching determination result;

[0092] The sliding self-matching method is based on a three-level detection box and its corresponding three-level matching box, moving in a specified direction with a fixed step size M. For example, ... Figure 5 The three-level detection boxes and their corresponding three-level matching boxes set in the image are then moved to the right with a fixed step size M; and the total value L of the three-level detection pixels corresponding to the three-level detection boxes and the three-level matching boxes is obtained. 15 Total pixel value L for three-level matching 25 The difference D between them 31 This is to obtain the sliding self-matching determination result.

[0093] In summary, this invention first performs preliminary detection of process defects on the panel using a primary detection frame and a primary matching frame, at which point the difference D is... 11 If the value is greater than the primary threshold T1, it indicates a large-area process defect. This initial detection allows for a simple and quick determination. However, for some small-area process defects, the initial detection cannot detect them properly, and there will still be missed detections. Therefore, a secondary detection box and a secondary matching box are used to further detect process defects on the panel. At this point, the difference D is... 21 If the value is greater than the secondary threshold T2, it indicates that there is a small area of ​​missing data at the secondary matching box location. Further detection can provide a more accurate determination, but the detection speed is slower than the initial detection, and the determination result is only valid for the secondary matching box location. This is because the coverage area of ​​the secondary matching box is limited; for small areas of missing data outside the secondary matching box location, further detection cannot detect them properly, resulting in missed detections. Therefore, a third-level detection box and a third-level matching box are used to perform process defect sliding self-matching detection on the panel. As long as a difference D exists... 31 If the value is less than the third-level threshold T3, it indicates the existence of a small-scale defect. This can be accurately determined by sliding self-matching detection, but the detection speed is slower than the initial detection and further detection. Therefore, this invention can prevent missed detections and achieve rapid detection by comprehensively detecting defects in the panel manufacturing process. Furthermore, the threshold can be adjusted and the detection steps can be selected according to the actual situation, making it highly adaptable.

[0094] Furthermore, in one embodiment, based on the same inventive concept as the foregoing embodiments, this embodiment of the invention provides a panel manufacturing process defect detection system, which corresponds one-to-one with the method described in Embodiment 1. Please refer to [link / reference]. Figure 6 , Figure 6 This is a structural block diagram of a panel manufacturing process defect detection system, the system comprising:

[0095] The template acquisition unit acquires a standard template based on a normal panel image and acquires a template to be matched based on the panel image to be detected.

[0096] The target detection unit sets up several template detection boxes based on a standard template, and obtains several matching detection boxes corresponding to the several template detection boxes based on the template to be matched.

[0097] A pixel detection unit, wherein the pixel detection unit obtains a total pixel detection value based on a number of template detection boxes, and obtains a total pixel matching value based on a number of matching detection boxes;

[0098] The comprehensive detection unit performs comprehensive detection of panel process defects based on the size and position of the template detection frame and the matching detection frame, and selects the corresponding pixel detection total value and pixel matching total value.

[0099] It should be noted that each unit in the panel process defect detection system in this embodiment corresponds one-to-one with each step in the panel process defect detection method in the aforementioned embodiment. Therefore, the specific implementation method and the technical effects achieved in this embodiment can be referred to the implementation method of the aforementioned panel process defect detection method, and will not be repeated here.

[0100] Furthermore, in one embodiment, this application also provides a computer device, the computer device including a processor, a memory, and a computer program stored in the memory, the computer program being executed by the processor to implement the methods in the foregoing embodiments.

[0101] In addition, in one embodiment, this application also provides a computer storage medium storing a computer program that is executed by a processor to implement the methods described in the foregoing embodiments.

[0102] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0103] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0104] As an example, executable instructions may, but do not necessarily, correspond to files in a file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborating files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0105] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0106] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0107] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0108] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a multimedia terminal device (which may be a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0109] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for detecting defects in panel manufacturing processes, characterized in that, The method flow is as follows: A standard template is obtained based on a normal panel image, and a template to be matched is obtained based on the panel image to be detected. Several template detection boxes are set based on a standard template, and several matching detection boxes corresponding to the template detection boxes are obtained based on the template to be matched. The process of setting up several template detection boxes based on standard templates is as follows: A primary inspection frame is set based on a standard template, and the primary inspection frame contains all elements of the process. A secondary inspection frame is set based on a standard template, and the secondary inspection frame contains some elements of the process. A three-level inspection frame is set based on a standard template, and the three-level inspection frame includes some elements of the process. The process of obtaining several matching detection boxes corresponding to several template detection boxes based on the template to be matched is as follows: Based on the template to be matched, obtain the first-level matching box corresponding to the first-level detection box. The size and number of the first-level matching box are the same as the size and number of the first-level detection box. Based on the template to be matched, obtain the secondary matching box corresponding to the secondary detection box. The size and number of the secondary matching box are the same as the size and number of the secondary detection box. Based on the template to be matched, obtain the third-level matching boxes corresponding to the third-level detection boxes. The size and number of the third-level matching boxes are the same as the size and number of the third-level detection boxes. The system obtains a total pixel detection value based on several template detection boxes, and a total pixel matching value based on several matching detection boxes, including: Obtain the corresponding first-level detection pixel matrix, second-level detection pixel matrix, and third-level detection pixel matrix based on the first-level detection box, second-level detection box, and third-level detection box; The pixel values ​​corresponding to all coordinate points in the first-level detection pixel matrix, the second-level detection pixel matrix, and the third-level detection pixel matrix are added together to obtain the total pixel value of the first-level detection, the total pixel value of the second-level detection, and the total pixel value of the third-level detection. Obtain the corresponding first-level matching pixel matrix, second-level matching pixel matrix, and third-level matching pixel matrix based on the first-level matching box, second-level matching box, and third-level matching box; The pixel values ​​of all coordinates in the first-level matching pixel matrix, the second-level matching pixel matrix, and the third-level matching pixel matrix are added together to obtain the total pixel value of the first-level matching pixel matrix, the total pixel value of the second-level matching pixel matrix, and the total pixel value of the third-level matching pixel matrix, respectively. Based on the size and position of the template detection box and the matching detection box, the corresponding pixel detection total value and pixel matching total value are selected to comprehensively detect panel process defects, including: First-level pixel difference determination is performed based on the total value of first-level detected pixels and the total value of first-level matched pixels. If the first-level pixel difference determination result is less than the first-level threshold, then second-level pixel difference determination is performed based on the total value of several second-level detected pixels and the total value of several second-level matched pixels. Otherwise, the panel manufacturing process is determined to be defective. If the result of the second-level pixel difference determination is less than the second-level threshold, then a sliding self-matching determination is performed based on the total value of the third-level matched pixels and the total value of the third-level detected pixels; otherwise, the panel process is determined to be defective. If all sliding self-matching judgment results are less than the level 3 threshold, the panel process is determined to be complete; otherwise, the panel process is determined to be missing. The calculation process for the first-level pixel difference determination result, the second-level pixel difference determination result, and the sliding self-matching determination result is as follows: Calculate the difference between the total value of first-level detected pixels and the total value of first-level matched pixels to obtain the first-level pixel difference determination result; According to the different positions of several secondary detection boxes and several secondary matching boxes, different weight values ​​are assigned to the corresponding total value of secondary detection pixels and total value of secondary matching pixels. Based on the different weight values, the difference between several total values ​​of secondary detection pixels and several total values ​​of secondary matching pixels is calculated to obtain the secondary pixel difference judgment result. The difference between the total value of several third-level detected pixels and the total value of third-level matched pixels is calculated by sliding self-matching to obtain the sliding self-matching judgment result.

2. The panel manufacturing process defect detection method according to claim 1, characterized in that, The number of secondary detection frames is greater than the number of primary detection frames, and the size of the secondary detection frames is smaller than the size of the primary detection frames; the number of tertiary detection frames is equal to the number of primary detection frames, and the size of the tertiary detection frames is smaller than the size of the secondary detection frames.

3. A panel manufacturing process defect detection system for implementing the method of claim 1, characterized in that, The system includes: The template acquisition unit acquires a standard template based on a normal panel image and acquires a template to be matched based on the panel image to be detected. The target detection unit sets up several template detection boxes based on a standard template, and obtains several matching detection boxes corresponding to the several template detection boxes based on the template to be matched. A pixel detection unit, wherein the pixel detection unit obtains a total pixel detection value based on a number of template detection boxes, and obtains a total pixel matching value based on a number of matching detection boxes; The comprehensive detection unit performs comprehensive detection of panel process defects based on the size and position of the template detection frame and the matching detection frame, and selects the corresponding pixel detection total value and pixel matching total value.

4. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements a panel manufacturing process defect detection method as described in any one of claims 1-2.

5. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the panel manufacturing process defect detection method according to any one of claims 1-2.

Images