Material defect detection method, device, equipment and storage medium
By setting defect filtering rules in the re-inspection operation interface, images of scrapped defective PCB printed circuit boards are automatically screened out, solving the problem of low efficiency in manual re-inspection and achieving efficient and accurate defect detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI GANTU NETWORK TECHNOLOGY CO LTD
- Filing Date
- 2023-10-11
- Publication Date
- 2026-07-21
Smart Images
Figure CN117358629B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of image display, and in particular to a method, apparatus, equipment and storage medium for detecting material defects. Background Technology
[0002] In the integrated circuit industry, machine tools are mainly used to perform optical inspection and defect detection analysis on the produced PCB printed circuit boards and product materials. Defect detection is mainly achieved by scanning the material image with a line scan camera above the machine, and then using computer equipment to analyze the image to determine the defect points. In order to maintain a certain yield rate, the defective materials that are screened out must be manually re-inspected and confirmed, and the final decision is made on whether to scrap or reprocess them.
[0003] However, in actual production lines, the precision settings dictate that material defects are frequent and a certain false positive rate is unavoidable. This highlights the importance of manual re-inspection. However, a single material board may yield several or even dozens of defective images. Requiring all of these to manual re-inspection would significantly impact inspection efficiency and require substantial additional manpower. Summary of the Invention
[0004] This application provides a method, apparatus, equipment, and storage medium for detecting material defects, which solves the problem that a large number of defect images requiring re-inspection affect the efficiency of re-inspection.
[0005] On one hand, this application provides a method for detecting material defects, the method comprising:
[0006] The re-inspection operation interface displays a panoramic material display area, a defect image display area, and defect setting controls. The panoramic material display area displays a real-time scan image of the material plate scanned by a line scan camera. The panoramic material image contains several particle arrays. The defect image display area is used to display defect images of defect points detected from the target particle area. The defect image is determined by the line scan camera scanning the material and the detection machine.
[0007] In response to receiving a click operation on the defect setting control, a defect setting interface is displayed, and a defect filtering rule for the target defect type is set on the defect setting interface according to the instruction; the defect filtering rule is used to determine the target particles containing scrap defect points.
[0008] In response to receiving a re-inspection command for the panoramic view of materials, the defect image is acquired, and scrap images containing target particles with scrap defects are automatically filtered out according to the defect filtering rules. The filtered target defect images are then displayed in the defect image display area.
[0009] On the other hand, this application provides a material defect detection device, the device comprising:
[0010] The first display module is used to display the re-inspection operation interface, which displays a panoramic material display area, a defect image display area, and defect setting controls. The panoramic material display area displays a real-time scan image of the material plate scanned by a line scan camera. The panoramic material image contains several particle arrays. The defect image display area is used to display defect images of defect points detected from the target particle area. The defect images are determined by the line scan camera scanning the material and the detection machine.
[0011] The second display module is used to respond to a click operation on the defect setting control, display the defect setting interface, and set the defect filtering rules for the target defect type on the defect setting interface according to the instructions; the defect filtering rules are used to determine the target particles containing scrap defect points.
[0012] The third display module is used to respond to the received instruction for re-inspection of the panoramic view of the material, acquire the defect image, automatically filter out the scrap image containing the target particles with scrap defect points according to the defect filtering rules, and display the filtered target defect image in the defect image display area.
[0013] In another aspect, this application provides a computer device including a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the material defect detection method described above.
[0014] In another aspect, this application provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the material defect detection method described above.
[0015] The beneficial effects of the technical solution provided in this application embodiment include at least the following: setting a defect setting control in the traditional re-inspection operation page, which allows quick access to the defect setting interface, and setting defect filtering rules to block scrap images of target particles with scrap defects or reaching scrap standards in the panoramic material image. In this way, the target defect images that have been filtered out and need to be re-inspected are displayed in the defect image display area. This operation method of creating new filtering rules, combined with the visual page, can greatly improve the operation efficiency of re-inspectors. The filtered scrap images will not affect the actual false inspection rate and greatly reduce the re-inspection workload of re-inspectors. Attached Figure Description
[0016] Figure 1 This is a schematic diagram of the detection and display system for the material defect detection method provided in this application;
[0017] Figure 2 This is a flowchart of the material defect detection method provided in the embodiments of this application;
[0018] Figure 3 This is a schematic diagram of the re-inspection operation interface provided in the embodiments of this application;
[0019] Figure 4 This is a schematic diagram of the defect setting interface provided in an embodiment of this application;
[0020] Figure 5 This is a schematic diagram of the interface for creating a new defect filtering rule in the defect settings interface;
[0021] Figure 6 This is a schematic diagram of the interface for generating prompts and outline annotations in the defect image display area;
[0022] Figure 7 A schematic diagram of the material defect detection device provided in an embodiment of this application is shown;
[0023] Figure 8 This is a structural block diagram of a computer device provided in an exemplary embodiment of this application. Detailed Implementation
[0024] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.
[0025] In this article, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.
[0026] Figure 1 This is a schematic diagram of the detection and display system for the material defect detection method provided in this application. The system includes a computer, a detection machine, a line scanner, and a material plate. The material plate is located on the detection machine, and the line scanner scans the material from above, transmitting the scanned image to the computer for defect detection. The computer is operated by a re-inspector, and its interface is a re-inspection operation interface. The re-inspection operation interface displays the defect images identified by the machine's initial inspection. These defect images require a second re-inspection by the re-inspector, specifically confirming the defects of each pcs of PNL particles on the material plate.
[0027] Figure 2 This is a flowchart of a material defect detection method provided in an embodiment of this application, which includes the following steps:
[0028] Step 101: Display the re-inspection operation interface, which includes a panoramic material display area, a defect image display area, and defect setting controls.
[0029] refer to Figure 3 As shown, the re-inspection operation interface 300 is a screen displayed on the computer interface. The panoramic material display area 310 and the defect image display area 320 are located in two areas of this interface, such as the left and right sides or the top and bottom sides. The panoramic material display area 310 displays a real-time scan image of the material board scanned by a line scan camera, that is, the image transmitted by the line scan camera to the computer side. The panoramic material image is the PNL material board, which contains several PCS particle arrays 311. The specific number and position of the particles are determined according to actual production. The "defect points" detected in this solution are the flaws on the PCS particles.
[0030] The computer is responsible for processing the panoramic material map, including extracting all PCS particle images, performing defect detection and analysis, and obtaining defect images. For example, if a PCS particle image contains multiple defect points, a corresponding number of defect images will be captured and transmitted to the computer. The defect image display area 320 is used to display the defect images for review by inspectors. The problem is that when there are too many defect images requiring review, relying on inspectors for review will severely impact review efficiency.
[0031] The defect setting control 330 is a setting button set in the re-inspection operation interface 300. This control is used to directly call up the defect setting interface in the re-inspection operation interface 300.
[0032] Step 102: In response to receiving a click operation on the defect setting control, display the defect setting interface, and set the defect filtering rules for the target defect type in the defect setting interface according to the instructions.
[0033] like Figure 4 As shown, when the re-inspector clicks the defect setting control, the defect setting interface 400 will be displayed on the computer monitor. This interface is used to set defect filtering rules to reduce the number of defect images handled by the re-inspector, thereby improving the re-inspection efficiency.
[0034] Defect filtering rules can be determined by the re-inspector based on the actual PNL material boards produced and the type of defects. They can also be set in conjunction with the number of defects and the defect severity level. For example, PCS particles with a high number of defects, where the defects are irreparable or would severely impact performance even after repair, can be filtered out, meaning a portion of the images deemed unusable can be removed. This reduces the re-inspection workload for the re-inspector and improves efficiency to some extent. Of course, for those PCS particles where a single defect reaches the scrap level, they can be directly scrapped.
[0035] Step 103: In response to receiving the instruction to re-inspect the panoramic view of the material, acquire the defect image, automatically filter out the scrap image containing the target particle with the scrap defect point according to the defect filtering rules, and display the filtered target defect image in the defect image display area.
[0036] When the re-inspector sets and enables the defect filtering rule, the system will retrieve all defect images based on the re-inspection operation instructions of the material panorama. At this time, the defect images will contain defect images of scrap particles (if any meet the conditions). Then, the system will filter the scrap images containing the target particles with scrap defect points according to the enabled defect filtering rule. The remaining images are the target defect images that need to be re-inspected and displayed by the re-inspector.
[0037] In summary, this solution incorporates a defect setting control within the traditional re-inspection operation page. This control allows for quick navigation to the defect setting interface, where defect filtering rules can be set to filter out scrap images of target particles with scrap defects or those meeting scrap standards in the panoramic material image. The defect image display area then shows the filtered images of the target defects that require re-inspection. This method of creating new filtering rules, combined with a visual interface, significantly improves the efficiency of re-inspectors. The filtered scrap images do not affect the actual false positive rate and substantially reduce the amount of re-inspection work required.
[0038] In some possible embodiments, the defect settings interface 400 also displays a defect configuration list 410 and a new rule control 420. The defect settings list 410 displays all established defect filtering rules, such as... Figure 4 It includes four newly created filter rules, and the specific filtering content can be set according to actual needs. Each defect filter rule has a direct defect reporting checkbox 411, which is used to select the target defect filter rule. For example, for the first filter rule, when this checkbox is checked, the defect rule for "circuit board damage" will be enabled.
[0039] The new rule control 420 is located above the defect settings list 410 and is displayed as a pop-up window, while the defect settings list 410 is covered by a mask layer. Alternatively, in some embodiments, the entire page can be displayed directly. The purpose is to add new defect filtering rules to the defect configuration list 410. For example, if a reviewer wants to add and enable the defect filtering rule for "circuit board crack" in the list, they can do so by clicking the "New Rule" control.
[0040] See Figure 4 and Figure 5 As shown, when the computer device receives a click operation on the New Rule control 420, a New Rule interface 500 is generated on the Defect Settings interface 400. The New Rule interface 500 includes at least one of the following: a Defect Code input box, a Defect Name input box, a Material LOT field input box, a Defect Level selection box, and a Rule Start / Stop control. The input boxes in this pop-up interface correspond to the contents in the Defect Settings list 410. The Defect Code, or ID number, is used for subsequent defect identification; the Defect Name is a manually defined defect type, such as "Text Missing," "Component Missing," and "Foreign Object Missing." The LOT field is used to define the PNL material board; different LOT fields represent different materials because the defect level and defect attributes of some of the same defects may differ on two different PNL boards. The Defect Level selection box is used to input or select the defect level, such as "Level 1 Defect," "Level 2 Defect," and "Level 3 Defect," etc. Different levels indicate different levels of danger. It can also be parameterized; a danger level of 90% indicates a high defect risk, and 10% indicates a low defect risk. The defect severity level is a threshold condition used to determine whether an image should be filtered for scrap. For example, if it is set to 90% or Level 1, then once a defective image reaches this value or level, it will be classified as a scrap image and the scrap particles will be identified.
[0041] In some embodiments, this threshold condition can be determined using the confidence score of a defect point during image recognition by a computer device. Confidence score represents the accuracy or certainty of identifying the defect point. The inspection machine generates a confidence score for the identification of the target defect point during the defect identification process. For example, a 90% confidence score for identifying a "missing text" defect indicates that the machine has a high degree of confidence in identifying the defect. In scenarios where large datasets are continuously trained, the accuracy of machine recognition is relatively reliable. When the confidence score for identifying a "broken circuit board" defect is 98%, it can be determined that the circuit board definitely has this fault, and this fault is a scrap fault, so no manual re-inspection is required. Only for defects with low confidence scores is manual intervention required for re-inspection. Based on this description, a confidence score threshold can be set in the defect severity level column. When the read confidence score exceeds this threshold, and the LOT field and defect type match correctly, the PCS particle is designated as a scrap particle.
[0042] The defect attribute describes whether the defect is a scrap defect or a repairable defect. Repairable defects can be overcome through re-inspection and secondary remelting. The rule start / stop control is used to directly enable or disable the filtering rule.
[0043] After the inspector enters the corresponding rule information and related parameters in the new rule interface, the computer saves the new rule according to the instructions and adds it to the defect configuration list.
[0044] In some possible embodiments, the process of automatically filtering out scrapped images containing target particles with scrapped defect points according to defect filtering rules can be implemented using the following procedure:
[0045] S1, acquire the defect image and read the defect label in the image. The defect label is used to record the defect type and target particle number of the defect point identified by the machine.
[0046] The defect label is generated by the computer after extracting the PCS array image from the panoramic material map and performing image recognition. The defect label records the type of defect identified in the defect image and may also include the aforementioned defect point confidence value. It's important to note that the defect image is a small image obtained by identifying and extracting from a single PCS image. When defect points are dense and of different types, multiple small defect images will be generated from a single PCS image. Furthermore, the label also records the PCS particle number, as the PCS in the panoramic material map are numbered, and this is included here for subsequent location display.
[0047] S2, obtain the target defect types corresponding to all enabled defect filtering rules in the defect configuration list, and match them with the defect types recorded in the defect labels in the defect image;
[0048] This step involves identifying the enabled filtering rules after acquiring the defect image. Furthermore, the LOT field of this filtering rule and the defect type (ID) also need to be matched.
[0049] S3, in response to inconsistent matching results, store the defect image in the display list for display in the defect image display area;
[0050] Inconsistent matching results indicate that the defective points in the defective image do not meet the scrapping standard and are temporarily stored in the display list. The images displayed in the defective image display area are read and displayed from this list. Whether the images stored in the list at this time can be displayed in the defective image display area will be determined uniformly by PCS number after all images have been matched.
[0051] S4, in response to the matching result being consistent, mark the target particle corresponding to the defective image as a scrap particle, and locate all scrap images of the scrap particle from the display list according to the particle number, and filter them out;
[0052] If the matching results are consistent, it means that the image contains defective points, which means that the corresponding target PCS particles are defective particles, and can be directly processed as NG.
[0053] Because scrap images represent defect images of scrapped wafers, these include defect images containing scrapped defect points as well as defect images containing non-scrapped defect points. For example, a PCS (Precast Concrete Segment) chip may contain three defect points: defect points 1 and 2 represent ordinary defect points, and defect point 3 represents a scrapped defect point, resulting in three corresponding defect images. When the system first detects defect points 1 and 2, these two defect point images are temporarily stored in the display list. When defect point 3 is matched, and the PCS is determined to be a scrapped chip, the two temporarily stored images need to be retrieved from the list and filtered out. Backtracking removal is based on the PCS number in the label.
[0054] Of course, in the case of matching defect point 1 first and then defect point 3, the defective particle will be marked after it is determined, and then directly filtered according to the PCS number when reading defect point 2 later.
[0055] S5, in response to the completion of defect image matching, will identify all images in the display list as target defect images.
[0056] Processes S3 and S4 will filter out all defective images that meet the filtering rules. Finally, the images remaining in the display list are the target defective images that can be displayed in the display list.
[0057] In some embodiments, when displaying a target defect image in the defect image display area, the position in the panoramic material map can also be determined based on the particle number corresponding to the target defect image. Because the panoramic material map contains all PCS arrays, while the defect image display area can only display one or a small number of defect images at a time, even if the PCS number is displayed in the image, the inspector still needs to find the position in the array based on the number to better control the overall production quality of the PNL board. Based on this idea, this application can mark the outline of the target defect particle in the panoramic material map when the inspector selects the target defect image in the defect image display area, and mark it using a crosshair positioning marker. Specifically, as shown in Figure 3, the positioning is determined based on the PCS number, or pixel coordinates are added to the defect label and marked according to the coordinates.
[0058] As mentioned earlier, when a PCS (Printed Circuit Board) contains a small number of repairable defects, it can be reworked without affecting the circuit board's functionality or appearance. However, when a PCS contains a large number of defects, repairing all of them may compromise functional integrity and overall appearance, hindering product sales. Therefore, this application can also statistically analyze defects that do not include scrapped defective particles. When the number does not exceed a threshold, the corresponding defect images are moved to a display list. Once the number of defects exceeds the threshold, even if there are no scrapped defective particles, the PCS is still listed as scrapped, and all defect images of that particle are filtered out. This operation can further reduce the workload of re-inspectors and improve re-inspection efficiency.
[0059] Based on the above description, in some special cases, a PNL material board may contain only scrap defect points. That is, the defect image identified by the computer, after being filtered by defect filtering rules, does not contain any target defect images that meet the display conditions. For the re-inspector, the panoramic material image contains scrap particles, but they do not know where these particles are located. To address this problem, such as... Figure 6 As shown, in some embodiments, a prompt can be generated in the defect image display area to indicate that the particle image contains only scrap defects. For example, displaying the text "This material only contains scrap defects and no repairable defects!" indicates that there are no defect images requiring manual re-inspection when the re-inspector sees this text. Furthermore, for screened scrap particles, their outlines are marked in the panoramic material image to facilitate the re-inspector's location. Of course, if the re-inspector needs to inspect scrap defects, they can... Figure 4 The filtering rules are disabled in the middle, so that all identified defect images can be traversed within the defect display area.
[0060] In summary, this solution constructs different defect filtering rules by using the confidence scores of defect points in defect images to filter out scrap particle images with high defect detection confidence. This significantly improves the efficiency of re-inspection personnel without significantly affecting detection accuracy.
[0061] Figure 7 This paper shows a schematic diagram of the structure of a material defect detection device provided in an embodiment of this application. The device includes:
[0062] The first display module 710 is used to display a re-inspection operation interface, which displays a panoramic material display area, a defect image display area, and defect setting controls. The panoramic material display area displays a real-time scan image of the material plate scanned by a line scan camera. The panoramic material image contains several particle arrays. The defect image display area is used to display defect images of defect points detected from the target particle area. The defect images are determined by the line scan camera scanning the material and the detection machine.
[0063] The second display module 720 is used to display a defect setting interface in response to receiving a click operation on the defect setting control, and to set a defect filtering rule for the target defect type on the defect setting interface according to the instruction; the defect filtering rule is used to determine the target particles containing scrap defect points.
[0064] The third display module 730 is used to respond to receiving a re-inspection operation command for the panoramic view of the material, acquire the defect image, automatically filter out the scrap image containing the target particles with scrap defect points according to the defect filtering rules, and display the filtered target defect image in the defect image display area.
[0065] Furthermore, this application also provides a computer device, the computer device including a processor and a memory, the memory storing at least one instruction, at least one program, code set or instruction set, the at least one instruction, the at least one program, the code set or instruction set being loaded and executed by the processor to implement the material defect detection method described above.
[0066] Furthermore, this application also provides a computer-readable storage medium storing at least one instruction, at least one program, code set, or instruction set, wherein the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by a processor to implement the material defect detection method described above.
[0067] The material defect detection device provided in this application embodiment can be applied to the material defect detection method provided in the above embodiment. For relevant details, please refer to the above method embodiment. The implementation principle and technical effect are similar, and will not be repeated here.
[0068] It should be noted that the material defect detection device provided in this embodiment is only illustrated by the above-described division of functional modules / units during gauge operation. In practical applications, the above functions can be assigned to different functional modules / units as needed, that is, the internal structure of the material defect detection device can be divided into different functional modules / units to complete all or part of the functions described above. Furthermore, the implementation method of the material defect detection method provided in the above-described method embodiments and the implementation method of the material defect detection device provided in this embodiment belong to the same concept. The specific implementation process of the material defect detection device provided in this embodiment is detailed in the above-described method embodiments and will not be repeated here.
[0069] Figure 8This illustration shows a structural block diagram of a computer device provided in an exemplary embodiment of this application. The device includes desktop computers, laptops, handheld computers, and cloud servers. This computer device may include, but is not limited to, a processor and memory. The processor and memory can be connected via a bus or other means. The processor may be a Central Processing Unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, graphics processing units (GPUs), embedded neural network processing units (NPUs) or other dedicated deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.
[0070] The processor may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 1701 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content required to be displayed on the screen. In some embodiments, the processor may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.
[0071] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the above embodiments of this application. The processor executes various functional applications and data processing by running the non-transitory software programs, instructions, and modules stored in the memory, thereby implementing the methods in the above embodiments. The memory may include a program storage area and a data storage area, wherein the program storage area may store the operating system and at least one application program required for a function; the data storage area may store data created by the processor, etc. Furthermore, the memory may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0072] In some embodiments, the computer device may also optionally include: a peripheral device interface and at least one peripheral device. The processor, memory, and peripheral device interface can be connected via a bus or signal lines. Each peripheral device can be connected to the peripheral device interface via a bus, signal lines, or a circuit board. Specifically, the peripheral device includes at least one of: a radio frequency circuit, a display screen, and a keyboard.
[0073] Peripheral device interfaces can be used to connect at least one I / O (Input / Output) related peripheral device to the processor and memory. In some embodiments, the processor, memory, and peripheral device interface are integrated on the same chip or circuit board; in some other embodiments, any one or two of the processor, memory, and peripheral device interface can be implemented on separate chips or circuit boards, which is not limited in this embodiment.
[0074] The display screen is used to display the UI (User Interface). This UI can include graphics, text, icons, videos, and any combination thereof. When the display screen is a touch screen, it also has the ability to collect touch signals on or above the surface of the display. These touch signals can be input as control signals to a processor for processing. In this case, the display screen can also be used to provide virtual buttons and / or a virtual keyboard, also known as soft buttons and / or a soft keyboard. In some embodiments, there can be one display screen, located on the front panel of the computer device; in other embodiments, there can be at least two display screens, respectively located on different surfaces of the computer device or in a folded design; in still other embodiments, the display screen can be a flexible display screen, located on a curved or folded surface of the computer device. Furthermore, the display screen can be configured as a non-rectangular, irregular shape, i.e., a non-rectangular screen. The display screen can be made of materials such as LCD (Liquid Crystal Display) and OLED (Organic Light-Emitting Diode).
[0075] A power supply is used to power the various components in a computer device. The power supply can be alternating current (AC), direct current (DC), a disposable battery, or a rechargeable battery. When the power supply includes a rechargeable battery, the rechargeable battery can be a wired rechargeable battery or a wireless rechargeable battery. A wired rechargeable battery is charged via a wired connection, while a wireless rechargeable battery is charged via a wireless coil. The rechargeable battery can also be used to support fast charging technology.
[0076] Those skilled in the art will understand that Figure 8 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 use different component arrangements.
[0077] This application also discloses a computer-readable storage medium. Specifically, the computer-readable storage medium is used to store a computer program, which, when executed by a processor, implements the methods described in the above-described method embodiments. Those skilled in the art will understand that implementing all or part of the processes in the methods described above can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above-described method embodiments. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.
[0078] This specific embodiment is merely an explanation of the present invention and is not intended to limit the invention. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of the claims of the present invention.
Claims
1. A method for detecting material defects, characterized in that, The method includes: The re-inspection operation interface displays a panoramic material display area, a defect image display area, and defect setting controls. The panoramic material display area shows a real-time scan image of the material plate scanned by a line scan camera. This real-time scan image is a panoramic material image containing several particle arrays. The defect image display area is used to display defect images of defect points detected from the target particle area. The defect images are determined by the line scan camera scanning the material and the detection machine. In response to receiving a click operation on the defect setting control, a defect setting interface is displayed, and a defect filtering rule for the target defect type is set on the defect setting interface according to the instruction; the defect filtering rule is used to determine the target particles containing scrap defect points. In response to receiving a re-inspection command for the material panorama, the system acquires the defect image, automatically filters out scrap images containing target particles with scrap defect points according to the defect filtering rules, and displays the filtered target defect images in the defect image display area; the scrap image contains defect images with both scrap defect points and non-scrap defect points; specifically, the system acquires the defect image and reads the defect tags in the image, the defect tags being used to record the defect type and target particle number of the defect point identified by the machine; it acquires all target defect types corresponding to the enabled defect filtering rules in the defect configuration list and matches them with the defect types recorded in the defect tags of the defect image; In response to inconsistent matching results, the defective image is stored in a display list for display in the defective image display area; in response to consistent matching results, the target particle to which the defective image belongs is marked as a scrap particle, and all scrap images contained in the scrap particle are located from the display list according to the particle number, and all scrap images contained in the scrap particle are filtered out; all images remaining after filtering are the target defective images.
2. The method according to claim 1, characterized in that, The defect settings interface displays a defect configuration list and a new rule control; the defect configuration list displays all established defect filtering rules, and each defect filtering rule has a direct defect reporting checkbox to select the target defect filtering rule; The new rule control is used to add new defect filtering rules to the defect configuration list.
3. The method according to claim 2, characterized in that, The step of setting the defect filtering rules for the target defect type in the defect setting interface according to the instructions includes: In response to receiving a click operation on the new rule control, a new rule interface is generated on the defect settings interface. The new rule interface includes a defect code input box, a defect name input box, a material LOT field input box, a defect level selection box, and a rule start / stop control. In response to the input of corresponding rule information in the new rule interface, the new rule is saved and added to the defect configuration list.
4. The method according to claim 1, characterized in that, When displaying the target defect image in the defect image display area, the position in the panoramic material map is determined according to the particle number corresponding to the target defect image; The outline of the target defective particles is marked in the panoramic material map, and the marking is displayed using crosshair locators.
5. The method according to claim 3, characterized in that, The inspection machine generates a confidence level for identifying target defect points during the defect identification process; the defect level selection box is used to set a confidence threshold for identifying scrapped defect points. When the confidence level of a defect recorded in a defect image exceeds the confidence threshold, it is identified as a scrapped defect point.
6. The method according to claim 1, characterized in that, When the particle array in the panoramic material image contains only scrap defect points, a prompt is generated in the defect image display area to indicate that the particle image contains only scrap defect points. The outlines of target particles containing scrap defects are marked and displayed in the panoramic material map.
7. A material defect detection device, characterized in that, The device includes: The first display module is used to display the re-inspection operation interface, which displays a panoramic material display area, a defect image display area, and defect setting controls. The panoramic material display area displays a real-time scan image of the material plate scanned by a line scan camera. This real-time scan image is a panoramic material image containing several particle arrays. The defect image display area is used to display defect images of defect points detected from the target particle area. The defect images are determined by the line scan camera scanning the material and the detection machine identifying them. The second display module is used to respond to a click operation on the defect setting control, display the defect setting interface, and set the defect filtering rules for the target defect type on the defect setting interface according to the instructions; the defect filtering rules are used to determine the target particles containing scrap defect points. The third display module is used to respond to a received instruction to re-inspect the panoramic view of the material, acquire the defect image, automatically filter out scrap images containing target particles with scrap defect points according to the defect filtering rules, and display the filtered target defect images in the defect image display area; the scrap image contains defect images with scrap defect points and non-scrap defect points; specifically, it acquires the defect image and reads the defect label in the image, the defect label is used to record the defect type and target particle number of the defect point identified by the machine; it acquires all target defect types corresponding to the enabled defect filtering rules in the defect configuration list and matches them with the defect types recorded in the defect labels in the defect image; In response to inconsistent matching results, the defective image is stored in a display list for display in the defective image display area; in response to consistent matching results, the target particle to which the defective image belongs is marked as a scrap particle, and all scrap images contained in the scrap particle are located from the display list according to the particle number, and all scrap images contained in the scrap particle are filtered out; all images remaining after filtering are the target defective images.
8. A computer device, characterized in that, The computer device includes a processor and a memory, the memory storing at least one program, which is loaded and executed by the processor to implement the material defect detection method as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that, The readable storage medium stores at least one program, which is loaded and executed by a processor to implement the material defect detection method as described in any one of claims 1 to 6.