A method, system, device, and storage medium for detecting defects in component pins.
By using deep learning and image processing technologies, the problems of low efficiency and low accuracy in component pin defect detection have been solved, enabling rapid and accurate detection of pin defects and improving the reliability and flexibility of automated quality inspection.
Patent Information
- Application Number
- CN202410856728.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-28
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2044-06-28
AI Technical Summary
Existing technologies suffer from low efficiency, low accuracy, and missed detection of component pin defects, especially posing safety hazards during manual sampling inspections.
By employing deep learning and image processing technologies, pin deformation, width, and length values are obtained through pin positioning, pixel processing, and contour extraction. Combined with threshold judgment, pin defect detection is achieved.
It enables rapid and accurate detection of component pin defects, improves detection efficiency and accuracy, reduces the missed detection rate, and enhances the reliability and flexibility of automated quality inspection.
Smart Images

Figure CN118822975B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of component defect detection technology, and more specifically, to a method, system, device, and storage medium for detecting component pin defects. Background Technology
[0002] The manufacturing process of industrial circuit boards is complex and cumbersome, and various product defects can easily be introduced during the manufacturing process. As essential components of industrial circuit boards, component defects can directly cause serious problems such as short circuits and explosions. In particular, the leads of electronic components, as the direct medium for connection to the industrial circuit board, are susceptible to defects such as bending or crossing if these defects are not detected, potentially leading to serious consequences such as component insertion failure or reversed connections. Furthermore, the length and width of the leads can serve as important reference information for detecting mixed components.
[0003] In the component quality inspection process, facing a huge number of component quality inspection tasks, the industry can only adopt manual sampling inspection for batch quality assessment. Since manual sampling inspection is greatly affected by personal and environmental factors, especially for the quality inspection of component pins, there are problems of low efficiency, low accuracy, and missed detection. This also means that there are certain safety hazards to subsequent equipment assembly. Therefore, how to detect defects in component pins is the foundation for realizing automated quality inspection, which can further improve the reliability and flexibility of automated quality inspection. Summary of the Invention
[0004] To address the issues of low efficiency, low accuracy, and missed detection in existing component pin defect detection methods, this invention provides a component pin defect detection method, system, device, and storage medium.
[0005] In a first aspect, embodiments of the present invention provide a method for detecting defects in component pins, the method comprising the following steps:
[0006] Perform pin positioning processing on the component image to obtain a pin positioning box containing the component pin image;
[0007] Perform pixel processing and contour extraction on the pin positioning box to obtain a set of pin contours containing pin contour information;
[0008] The wrapping area and convex hull area of the pin are obtained based on the pin profile set, and the ratio of the wrapping area and convex hull area of the pin is calculated to obtain the degree of pin deformation.
[0009] The perimeter of the region corresponding to the preset sampling length is obtained based on the pin profile set, and the width value of the pin is obtained by subtracting the region perimeter from the sampling length.
[0010] The pin perimeter is obtained from the pin profile set, and the pin length is obtained by subtracting the pin perimeter from the pin width.
[0011] The component pin defect detection is performed based on the pin's engineering parameters to obtain the component pin defect detection results. The pin's engineering parameters include the degree of pin deformation, width value, and length value.
[0012] In the above embodiments, the present invention first accurately obtains a set of pin contours containing component pin coordinate information based on deep learning technology and image processing technology. Then, it quickly obtains the number, deformation degree, width value and length value of the pins based on image processing technology and engineering processing technology. Finally, it realizes the detection of pin defects based on the threshold determination of the number, deformation degree, width value and length value of the pins. That is, based on deep learning technology and image processing technology, and combined with the structure of the component, the pin defect determination is performed, realizing accurate pin detection and engineering parameter determination.
[0013] As some optional embodiments of this application, the process of performing pin positioning processing on the component image to obtain a pin positioning frame containing the component pin image is as follows:
[0014] The component image is input into the pin selection model to obtain pin location information, wherein the pin selection model is a deep learning network model after model training;
[0015] The component image is cropped based on the pin positioning information to obtain a pin positioning box containing the component pin image.
[0016] In the above embodiments, the pin screening model trained by the present invention can quickly and accurately locate the pins of the component images to be detected.
[0017] As some optional embodiments of this application, the process of performing pixel processing and contour extraction processing on the pin positioning frame to obtain a pin contour set containing pin contour information is as follows:
[0018] The pin positioning frame is converted to grayscale to obtain a grayscale image of the pin positioning frame;
[0019] The grayscale image of the pin positioning frame is subjected to binarization segmentation to obtain the binarized image of the pin positioning frame;
[0020] Contour extraction processing is performed on the binarized image of the pin positioning box to obtain a set of pin contours containing pin contour information.
[0021] In the above embodiments, the present invention can quickly and accurately obtain a set of pin contours containing pin contour coordinate information through pixel processing and contour extraction processing.
[0022] As some optional embodiments of this application, the formula for calculating the degree of deformation of the pin is as follows:
[0023] deformDegree=CA / A
[0024] Where deformDegree represents the degree of pin deformation, A represents the pin's wrapping area, and CA represents the pin's convex hull area.
[0025] As some optional implementations of this application, the process of obtaining the perimeter of the region corresponding to the preset sampling length based on the pin profile set, and subtracting the region perimeter from the sampling length to obtain the pin width value is as follows:
[0026] A preset sampling length is used, and the pin profile set is segmented into regions based on the sampling length to obtain a subset of pin profiles within the sampling length range;
[0027] The perimeter of the region is obtained based on a subset of the pin profile within the sampling length range, and the width of the pin is obtained by subtracting the perimeter of the region from the sampling length.
[0028] As some optional embodiments of this application, the formula for calculating the width value of the pin is as follows:
[0029] w=9C P -2*x) / 2
[0030] Where w represents the pin width, C P denoted by , where x represents the perimeter of the region and , where x represents the sampling length.
[0031] As some optional embodiments of this application, the formula for calculating the length value of the pin is as follows:
[0032] I = (C i -2*w) / 2
[0033] Where I represents the pin length, C i The value w represents the pin's outline perimeter, and w represents the pin's width.
[0034] As some optional embodiments of this application, the engineering parameters of the pins also include the total number of pin profiles, which is the number of pin profile sets.
[0035] In a second aspect, the present invention provides a component pin defect detection system, the system comprising:
[0036] A pin positioning frame acquisition unit is used to perform pin positioning processing on a component image to obtain a pin positioning frame containing the component pin image.
[0037] A contour set acquisition unit is used to perform pixel processing and contour extraction processing on the pin positioning box to obtain a pin contour set containing pin contour information.
[0038] The deformation degree acquisition unit obtains the wrapping area and convex hull area of the pin based on the pin contour set, and performs a ratio calculation on the wrapping area and convex hull area of the pin to obtain the deformation degree of the pin.
[0039] The pin width acquisition unit obtains the perimeter of the region corresponding to the preset sampling length based on the pin profile set, and performs a subtraction operation on the region perimeter and the sampling length to obtain the pin width value.
[0040] A pin length acquisition unit obtains the pin outline perimeter based on a pin outline set, and performs a subtraction operation between the pin outline perimeter and the pin width value to obtain the pin length value.
[0041] A pin defect detection unit performs pin defect detection on components based on the pin's engineering parameters to obtain the pin defect detection results. The pin's engineering parameters include the degree of pin deformation, width value, and length 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 component pin 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 component pin defect detection method.
[0044] The beneficial effects of this invention are as follows: First, based on deep learning technology and image processing technology, this invention accurately obtains a set of pin contours containing component pin coordinate information. Then, based on image processing technology and engineering processing technology, it quickly obtains the number, degree of deformation, width value, and length value of the pins. Finally, based on the threshold determination of the number, degree of deformation, width value, and length value of the pins, it realizes the detection of pin defects, which solves the problem of pin crossing and bending degree being difficult to detect during component production. 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 of 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 component pin defect detection method described in the embodiments of the present invention;
[0048] Figure 3 This is a schematic diagram of the structure of the wrapping region and the convex hull region of the component pins according to an embodiment of the present invention;
[0049] Figure 4 This is a structural block diagram of the component pin defect detection system described in an embodiment of the present invention. Detailed Implementation
[0050] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.
[0051] To address the problems of low efficiency, low accuracy, and missed detection in existing component pin defect detection methods, this invention provides a component pin defect detection method, system, device, and storage medium. Before introducing the specific technical solutions of this application, the hardware operating environment involved in the embodiments of this application will be described first.
[0052] 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 the present invention.
[0053] like Figure 1As 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 be a 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 storage device; optionally, the memory may also be a storage device independent of the aforementioned processor.
[0054] 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.
[0055] like Figure 1 As shown, a memory, as a storage medium, may include an operating system module, a network communication module, a user interface module, and a data storage module.
[0056] 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 a component pin defect detection system stored in the data storage module through the processor, and executes a component pin defect detection method provided in the embodiment of this application.
[0057] Based on the hardware environment of the foregoing embodiments, embodiments of this application provide a method for detecting component pin defects. Please refer to [link to relevant documentation]. Figure 2 , Figure 2 The flowchart of the component pin defect detection method is as follows:
[0058] (1) Perform pin positioning processing on the component image to obtain a pin positioning frame containing the component pin image.
[0059] In this embodiment of the invention, the process for pin positioning of component images is as follows:
[0060] (1.1) Input the image of the component to be detected into the pin screening model to obtain pin location information, wherein the pin screening model is a deep learning network model after model training, and the deep learning network model includes, but is not limited to, a CNN model.
[0061] (1.2) Based on the pin positioning information, the component image is cropped to obtain a pin positioning frame containing the component pin image.
[0062] Specifically, the model training process for the pin selection model is as follows:
[0063] (1.11) Collect historical component images and label the component images with pins, i.e., label the pins with the target box.
[0064] (1.12) Input the component images after pin labeling into the deep learning network model for image feature extraction and iterative training to obtain the pin selection model.
[0065] Specifically, the present invention first trains the pin selection model, and then performs pin positioning based on the trained pin selection model to realize the detection and output of pin positioning information.
[0066] (2) Perform pixel processing and contour extraction on the pin positioning frame to obtain a set of pin contours containing pin contour information.
[0067] In this embodiment of the invention, the process of pixel processing and contour extraction for the pin positioning frame is as follows:
[0068] (2.1) Perform grayscale processing on the pin positioning frame to obtain a grayscale image of the pin positioning frame.
[0069] (2.2) A preset binarization segmentation threshold is set, and the grayscale image of the pin positioning box is binarized and segmented according to the binarization segmentation threshold to obtain a binarized image of the pin positioning box. The binarization segmentation threshold can be set according to the actual situation, and the present invention does not limit it.
[0070] (2.3) Perform contour extraction processing on the binarized image of the pin positioning box to obtain a set of pin contours containing pin contour information. The set of pin contours containing pin contour information is a set of coordinates of the pin contours, and one pin corresponds to one set of pin contours.
[0071] Specifically, this invention can quickly and accurately obtain a set of pin contours containing pin contour coordinate information through pixel processing and contour extraction processing.
[0072] (3) Verify the total number of pins based on the number of pin profile sets to obtain the total number of pin profiles. That is, if the number of pin profile sets is 1, then the total number of pin profiles is also 1.
[0073] (4) Obtain the wrapping area and convex hull area of the pin based on the pin profile set, and perform a ratio calculation on the wrapping area and convex hull area of the pin to obtain the degree of pin deformation.
[0074] Please see Figure 3 , Figure 3 This is a schematic diagram of the wrapping region and convex hull region of a component pin. The wrapping region of the pin represents the area surrounded by the actual outline of the pin, and the convex hull region of the pin represents the sum of the area enclosed by the actual outline of the pin and the area formed by the straight line segment between the two endpoints and the area enclosed by the actual outline of the pin.
[0075] In this embodiment of the invention, the formula for calculating the degree of deformation of the pin is as follows:
[0076] deformDegree=A / CA
[0077] Where deformDegree represents the degree of pin deformation, A represents the pin's wrapping area, and CA represents the pin's convex hull area.
[0078] (5) Obtain the perimeter of the region corresponding to the preset sampling length based on the pin profile set, and perform a subtraction operation between the region perimeter and the sampling length to obtain the pin width value.
[0079] In this embodiment of the invention, the process of subtracting the region perimeter and the sampling length is as follows:
[0080] (5.1) A preset sampling length is used, and the pin contour set is segmented based on the sampling length to obtain a subset of pin contours within the sampling length range. This invention obtains several pixels near the left side of the image from each pin contour set according to the sampling length, thereby forming a corresponding subset of pin contours. Specifically, the sampling length can be set according to actual conditions, and this embodiment of the invention does not impose any limitations on it.
[0081] (5.2) Obtain the perimeter of the region based on the pin profile subset within the sampling length range, and perform a subtraction operation between the region perimeter and the sampling length to obtain the pin width value.
[0082] In this embodiment of the invention, the formula for calculating the width value of the pin is as follows:
[0083] w = (C P -2*x) / 2
[0084] Where w represents the pin width, CP denoted by , where x represents the perimeter of the region and , where x represents the sampling length.
[0085] (6) Obtain the pin profile perimeter based on the pin profile set, and perform a subtraction operation between the pin profile perimeter and the pin width value to obtain the pin length value.
[0086] In this embodiment of the invention, the formula for calculating the length of the pin is as follows:
[0087] I = (C i -2*w) / 2
[0088] Where I represents the pin length, C i The value w represents the pin's outline perimeter, and w represents the pin's width.
[0089] (7) Based on the pin engineering parameters, pin defects are detected in the components to obtain the pin defect detection results. The pin engineering parameters include, but are not limited to, the total number of pin outlines, the degree of pin deformation, the pin width, and the pin length. Specifically, if the total number of pin outlines is 1, it indicates defects such as missing pins or pin crossings; if the degree of pin deformation is greater than a threshold, it indicates pin bending defects; if the pin width or pin length is greater than or less than the upper or lower threshold, it indicates mixed materials. The thresholds corresponding to the degree of deformation, width, and length can be set according to actual conditions, and this embodiment of the invention does not impose any restrictions on this.
[0090] In summary, this invention first accurately obtains a set of pin outlines containing component pin coordinate information based on deep learning and image processing technologies. Then, it quickly obtains the number, deformation degree, width, and length of the pins based on image processing and engineering processing technologies. Finally, it detects pin defects based on threshold determination of the number, deformation degree, width, and length of the pins, thus solving the problem of difficulty in detecting pin crossing and bending during component manufacturing.
[0091] Furthermore, in one embodiment, based on the same inventive concept as the foregoing embodiments, this embodiment of the invention provides a component pin defect detection system. Please refer to [link to relevant documentation]. Figure 4 , Figure 4 The diagram below shows the system block diagram of the component pin defect detection system. The system corresponds one-to-one with the method described in Embodiment 1. The system includes:
[0092] A pin positioning frame acquisition unit is used to perform pin positioning processing on a component image to obtain a pin positioning frame including the component pin image.
[0093] A contour set acquisition unit is used to perform pixel processing and contour extraction processing on the pin positioning box to obtain a pin contour set containing pin contour information.
[0094] The total number of contours acquisition unit verifies the total number of pins based on the number of pin contour sets to obtain the total number of pin contours.
[0095] The deformation degree acquisition unit obtains the wrapping area and convex hull area of the pin based on the pin contour set, and performs a ratio calculation on the wrapping area and convex hull area of the pin to obtain the deformation degree of the pin.
[0096] The pin width acquisition unit obtains the perimeter of the region corresponding to the preset sampling length based on the pin profile set, and performs a subtraction operation on the region perimeter and the sampling length to obtain the pin width value.
[0097] The pin length acquisition unit is based on the pin profile set of the pin profile perimeter, and performs a subtraction operation on the pin profile perimeter and the width value representing the pin width to obtain the pin length value.
[0098] A pin defect detection unit performs pin defect detection on components based on the number of pins, the degree of deformation, the width of the pins, and the length of the pins, in order to obtain the pin defect detection results of the components.
[0099] It should be noted that each unit in the component pin defect detection system in this embodiment corresponds one-to-one with each step in the component pin 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 component pin 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 component pins, characterized in that, The method includes the following steps: Perform pin positioning processing on the component image to obtain a pin positioning box containing the component pin image; Pixel processing and contour extraction are performed on the pin positioning box to obtain a set of pin contours containing pin contour information; The wrapping area and convex hull area of the pin are obtained based on the pin profile set, and the ratio of the wrapping area and convex hull area of the pin is calculated to obtain the degree of pin deformation. The formula for calculating the degree of deformation of the pin is as follows: deformDegree=A / CA; Where deformDegree represents the degree of pin deformation, A represents the pin's wrapping area, and CA represents the pin's convex hull area; The perimeter of the region corresponding to the preset sampling length is obtained based on the pin profile set, and the width value of the pin is obtained by subtracting the region perimeter from the sampling length. include: A preset sampling length is used, and the pin profile set is segmented into regions based on the sampling length to obtain a subset of pin profiles within the sampling length range; The perimeter of the region is obtained based on a subset of the pin profile within the sampling length range, and the width of the pin is obtained by subtracting the perimeter of the region from the sampling length. The formula for calculating the width of the pin is as follows: w=(C P -2*x) / 2; Where w represents the pin width, C P The region perimeter is represented by x, and the sampling length is represented by x. The pin profile perimeter is obtained based on the pin profile set, and the pin profile perimeter and pin width value are subtracted to obtain the pin length value. The formula for calculating the length of the pin is as follows: I=(C i -2*x) / 2; Where I represents the pin length, C i The circumference of the pin is represented by , and w represents the width of the pin. Pin defect detection is performed on components based on pin engineering parameters to obtain component pin defect detection results. The pin engineering parameters include the total number of pin outlines, the degree of deformation, the width value, and the length value; the total number of pin outlines is the number of pin outline sets. include: If the total number of pin outlines is 1, it indicates a missing pin or pin crossing defect; if the pin deformation exceeds the threshold, it indicates a pin bending defect.
2. The method for detecting component pin defects according to claim 1, characterized in that, The process of performing pin positioning processing on component images to obtain pin positioning frames containing the component pin images is as follows: The component image is input into the pin selection model to obtain pin location information, wherein the pin selection model is a deep learning network model after model training; The component image is cropped based on the pin positioning information to obtain a pin positioning box containing the component pin image.
3. The method for detecting component pin defects according to claim 1, characterized in that, The process of performing pixel processing and contour extraction on the pin positioning box to obtain a set of pin contours containing pin contour information is as follows: The pin positioning frame is converted to grayscale to obtain a grayscale image of the pin positioning frame; The grayscale image of the pin positioning frame is subjected to binarization segmentation to obtain the binarized image of the pin positioning frame; Contour extraction processing is performed on the binarized image of the pin positioning box to obtain a set of pin contours containing pin contour information.
4. A component pin defect detection system for implementing the method of claim 1, characterized in that, The system includes: A pin positioning frame acquisition unit is used to perform pin positioning processing on a component image to obtain a pin positioning frame containing the component pin image. A contour set acquisition unit is used to perform pixel processing and contour extraction processing on the pin positioning box to obtain a pin contour set containing pin contour information. The deformation degree acquisition unit obtains the wrapping area and convex hull area of the pin based on the pin contour set, and performs a ratio calculation on the wrapping area and convex hull area of the pin to obtain the deformation degree of the pin. The pin width acquisition unit obtains the perimeter of the region corresponding to the preset sampling length based on the pin profile set, and performs a subtraction operation on the region perimeter and the sampling length to obtain the pin width value. A pin length acquisition unit obtains the pin outline perimeter based on a pin outline set, and performs a subtraction operation between the pin outline perimeter and the pin width value to obtain the pin length value. A pin defect detection unit performs pin defect detection on components based on the pin's engineering parameters to obtain the pin defect detection results. The pin's engineering parameters include the degree of pin deformation, width value, and length value.
5. 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 the component pin defect detection method according to any one of claims 1-3.
6. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the component pin defect detection method according to any one of claims 1-3.
Citation Information
Patent Citations
QFP chip pin defect discrimination method based on pixel region growth
CN112348840A
Component antipole defect detection method, system and equipment and storage medium
CN116468680A
