Bridging defect visual detection method for solder paste detection instrument, storage medium and equipment

Abstract

The invention discloses a bridging defect visual detection method for a solder paste detection instrument, a storage medium and equipment, and belongs to the technical field of surface mounting defect detection. In order to solve the problems that an existing bridging defect visual detection algorithm in a solder paste detection instrument is high in complexity and the detection accuracy needs to be improved, a solder paste area binary image is obtained based on a binary image and a solder paste area binary image, and then a solder paste printing area in the solder paste detection area binary image is removed; obtaining a binary image of the solder paste overflowing the solder paste printing area; taking a pixel of a solder paste printing area in the solder paste detection area image as a target, taking other pixels as a background, and adopting a chessboard distance to measure the length of the solder paste overflowing from the solder paste printing area; obtaining the distance between each pixel in the overflowing solder paste and the solder paste printing area through the binary image and the distance transformation image of the solder paste overflowing from the solder paste printing area, searching the maximum value and the minimum value, taking the difference between the maximum value and the minimum value as the distance of the solder paste overflowing from the solder paste printing area, and judging that the bridging defect exists if the difference exceeds a length threshold value.

Description

Technical Field

[0001] This invention belongs to the field of surface mount defect detection technology, and relates to a visual inspection method, storage medium and equipment for solder paste bridging defects. Background Technology

[0002] With the popularization of information and digital technologies, people's demand for electronic devices is increasing day by day. Printed circuit boards are an indispensable component of various electronic devices, so how to efficiently produce printed circuit boards while ensuring product quality has become an urgent problem to be solved in the industry.

[0003] Surface Mount Technology (SMT) primarily refers to a technology that mounts surface-mount devices (SMDs) onto printed circuit boards (PCBs). Due to the advantages of SMDs, such as small size, light weight, and stable performance, they can better meet the high-density mounting requirements of modern electronic equipment assembly. This has led to SMT gradually replacing through-hole mounting technology and becoming the mainstream component mounting technology. A surface mount production line mainly consists of solder paste printers, solder paste inspection (SPI) instruments, pick-and-place machines, automated optical inspection (AOI) equipment, reflow ovens, and post-reflow AOI equipment.

[0004] This invention is primarily applied to SPI instruments in surface mount technology (SMT) production lines. SPI instruments, short for solder paste inspection instruments, are mainly used to detect printing defects in solder paste on the surface of solder pads on printed circuit boards. The surface mount process is complex, and product defects are difficult to avoid during production. Research in relevant literature indicates that most soldering defects in surface mount products are caused by defects occurring during the solder paste printing process, with bridging being the most damaging type of defect. Therefore, achieving rapid and accurate detection of solder paste bridging defects is of great significance to the development of SPI instruments.

[0005] Current SPI instruments primarily determine bridging defects by measuring the length and width of the minimum bounding rectangle of the solder paste overflow area. This requires manually set parameters in steps such as solder paste region segmentation and morphological denoising, leaving significant room for improvement in the accuracy of the detection results. Furthermore, existing detection methods using artificial intelligence algorithms suffer from high algorithm complexity and substantial model training overhead, and their accuracy also still has room for improvement. Summary of the Invention

[0006] This invention aims to address the problems of complex and high-precision visual detection algorithms for bridging defects in existing solder paste inspection instruments, as well as the need to improve detection accuracy.

[0007] A visual inspection method for bridging defects in solder paste inspection instruments includes:

[0008] S1. The solder paste detection region image in color space is segmented using a color-based segmentation algorithm to initially obtain a binary image of the solder paste region.

[0009] S2. Based on the height threshold set according to the thickness of the stencil of the solder paste printing machine, the height image of the solder paste detection area is binarized, and the intersection of the binary image and the binary image of the solder paste area obtained in step S1 is taken to obtain the binary image of the solder paste area.

[0010] S3. Perform morphological operations on the binary image of the solder paste region obtained in step S2, and then remove the solder paste printing area from the binary image of the solder paste detection area to obtain the binary image of the solder paste overflowing printing area.

[0011] S4. Using the pixels of the solder paste printing area in the solder paste detection area image as the target and the remaining pixels as the background, the length of the solder paste overflowing from the solder paste printing area is measured by the chessboard distance.

[0012] S6. Using the binary image of the solder paste in the overflow solder paste printing area in S3 and the distance transformation image in S4, the distance between each pixel in the overflow solder paste and the solder paste printing area is obtained. That is, the pixel value of the pixel at the position corresponding to the non-zero pixel in the distance transformation image and the binary image of the overflow solder paste printing area. The maximum and minimum values ​​are found in the recorded pixel values. The difference between the maximum and minimum values ​​is defined as the distance of the solder paste overflowing from the solder paste printing area. If the distance exceeds the length threshold, it is determined that there is a bridging defect.

[0013] Furthermore, the specific process of step S1 includes:

[0014] The solder paste detection area image in the RGB color space is split into three grayscale images according to the color channels. Then, the grayscale images of each color channel are binarized according to the upper and lower limits of grayscale values ​​set for each channel. That is, the pixel values ​​of the grayscale values ​​between the upper and lower limits are assigned non-zero values, and the other pixels are set to zero. Then, the three binary images are ANDed with each other to obtain the preliminary binary segmentation result of the solder paste area.

[0015] Preferably, during the process of assigning non-zero values ​​to pixel values ​​whose grayscale values ​​are between the upper and lower limits, the upper and lower limits of the red channel grayscale image are 220 and 90, respectively; the upper and lower limits of the green channel grayscale image are 240 and 150, respectively; and the upper and lower limits of the blue channel grayscale image are 210 and 100, respectively.

[0016] Preferably, the height threshold set according to the stencil thickness of the solder paste printer is 40% of the stencil thickness.

[0017] Furthermore, during the morphological operation on the binary image of the solder paste region obtained in step S2, the size of the morphological structural element is set according to the size of the solder paste printing area in the production data, and the morphological operation is performed on the binary image of the solder paste region obtained in step S2. The size of the morphological structural element is as follows:

[0018]

[0019] in, This represents the size of the morphological structural element, where the size of the structural element is... The unit is pixels; , These represent the width and height of the solder paste detection area, respectively, in pixels; This indicates the operation of rounding up; , These represent operations to retrieve the maximum and minimum values, respectively.

[0020] Furthermore, in step S4, when the pixels of the solder paste printing area in the solder paste detection area image are taken as the target and the remaining pixels are the background, the pixel value of the target pixel is zero and the pixel value of the background pixel is non-zero.

[0021] Furthermore, the formula for measuring the length of the solder paste overflow printing area using the chessboard distance in step S4 is as follows:

[0022]

[0023]

[0024] in, This represents the non-zero pixels in the binary image of the solder paste detection area; , These represent the horizontal and vertical coordinates of non-zero pixels in the binary image in the top-left coordinate system of the image, respectively, in pixels. This represents the set containing all non-zero pixels in a binary image; Represents a pixel with a gray level of zero in a binary image; , These represent the horizontal and vertical coordinates of the pixels with zero grayscale in the binary image, respectively, in the upper left coordinate system of the image. This represents the set of all pixels in a binary image that have a gray level of zero. , These represent the camera's scale on the horizontal and vertical axes, respectively, in millimeters per pixel (mm / pixel). This indicates that for a set medium pixel The distance transformation performed; This indicates that for a set medium pixel Distance transformation performed.

[0025] Furthermore, the length threshold mentioned in step S6 is as follows:

[0026]

[0027]

[0028] in, This indicates the center point of the solder paste printing area currently being detected. The solder paste printing area currently being detected is the area where the bridging length threshold needs to be calculated. , Indicates the center point The coordinates; This represents the center point of the smallest bounding rectangle of the solder paste printing area that is not currently being inspected. , Indicates the center point The coordinates; This represents the set of center points of all solder paste printing areas within the same pad group; , These represent the width and height of the solder paste printing area image, respectively. Indicates the center of the current solder paste printing area. and solder paste printing area center The Euclidean distance; This indicates the length threshold for bridging detection in the current solder paste printing area.

[0029] A computer storage medium storing at least one instruction, which is loaded and executed by a processor to implement the aforementioned visual inspection method for bridging defects in a solder paste inspection instrument.

[0030] A visual inspection device for bridging defects in a solder paste inspection instrument, the device comprising a processor and a memory, the memory storing at least one instruction, the at least one instruction being loaded and executed by the processor to implement the aforementioned visual inspection method for bridging defects in a solder paste inspection instrument.

[0031] Compared with existing technologies, the beneficial effects of this invention are as follows:

[0032] This invention provides a visual detection method for bridging defects in solder paste inspection instruments. This method innovatively filters noise from solder paste segmentation images using height information and cleverly uses a chessboard distance to define the length of the solder paste overflow area. The distance transformation formula is optimized for scenarios where camera scales differ in the horizontal and vertical axes during actual production. Finally, the bridging defect threshold is automatically calculated using empirical formulas and pad group information, and a judgment is made as to whether bridging exists in the current solder paste printing area. This invention not only features a simple algorithm, reducing hardware requirements and avoiding the overhead of training models; more importantly, it achieves very high detection accuracy. Attached Figure Description

[0033] Figure 1 This is a flowchart of the visual inspection method for bridging defects in a solder paste inspection instrument according to the present invention.

[0034] Figure 2 This is a schematic diagram illustrating the invention for distinguishing between the solder paste detection area and the solder paste printing area;

[0035] Figure 3 This is a schematic diagram of the visual inspection results of bridging defects in the solder paste inspection instrument of the present invention. Detailed Implementation

[0036] The main objective of this invention is to detect potential bridging defects in solder paste from color and height images of the solder paste inspection area acquired via SPI using a visual inspection algorithm. To address the problems in the background art, this invention proposes a visual inspection method for solder paste bridging defects based on color and height information. This method accurately calculates the distance of the solder paste overflow portion through distance transformation and automatically calculates the parameters required for each step using empirical formulas and pad group information, thus automating the inspection process. Specific implementation methods are described below.

[0037] Specific implementation method one: Combining Figure 1 This implementation method is described below.

[0038] This embodiment is a visual inspection method for bridging defects in solder paste inspection instruments, comprising the following steps:

[0039] S1. The solder paste detection region image in the RGB color space is segmented using a color-based segmentation algorithm to initially obtain a binary image of the solder paste region (the pixel values ​​of pixels containing solder paste are assigned non-zero values, and the pixel values ​​of other pixels are zero).

[0040] The specific process of the color-based segmentation algorithm includes:

[0041] The solder paste detection area image in the RGB color space is split into three grayscale images according to color channels. Then, each grayscale image is binarized using pre-set upper and lower limits for each channel's grayscale value; pixels with grayscale values ​​between the upper and lower limits are assigned non-zero values, while other pixels are set to zero. Finally, a bitwise AND operation is performed on the three binary images to obtain a preliminary segmentation result binary image of the solder paste area. Based on engineering experience, the initial values ​​for the upper and lower limits of the red channel are set to 220 and 90, respectively; for the green channel, 240 and 150; and for the blue channel, 210 and 100.

[0042] Because the solder paste composition used in actual production varies, and the light sources and camera models used for image acquisition are also different, the upper and lower limits of each channel need to be manually adjusted. Considering that machine learning methods such as clustering and neural networks are difficult to adjust in real time and efficiently in production, and that predictions have a certain degree of instability, manual setting is preferred. Furthermore, the segmentation parameters are usually consistent for all solder paste printing areas of the same printed circuit board product, meaning that only one setting is required, making the operation convenient. It should be noted that the above segmentation parameters are the only parameters in this invention that require manual setting.

[0043] S2. Set a height threshold according to the stencil thickness of the solder paste printer. Binarize the height image of the solder paste detection area using this height threshold. The height image refers to a planar image that stores the height of the solder paste at the corresponding position in pixel values. Take the intersection of this binary image and the binary image of the solder paste area obtained in step S1 to obtain a binary image of the solder paste area after filtering out interference from the screen printing and substrate background.

[0044] This invention performs preliminary segmentation of the solder paste area based on the color information of the image. Due to the complexity of the printed circuit board background pattern and color information, such as areas with transitional colors at the edges of white silkscreen printing and substrates of different colors, interference can occur in the segmentation results. However, it is also noted that the height of these interfering objects relative to the reference surface is much lower than that of the solder paste. Therefore, by setting a height threshold, the aforementioned noise is cleverly filtered out. Stencil thickness is an important parameter in solder paste printing. Typically, for a normal solder paste printing process, the stencil height is the upper limit of the solder paste height on the printed circuit board pads. Therefore, using the stencil thickness as a reference is appropriate. In practice, 40% of the stencil thickness is used as the height threshold.

[0045] S3. Based on the solder paste printing area dimensions in the production data, set the dimensions of the morphological structural elements, and perform morphological opening and closing operations on the binary image of the solder paste area obtained in step S2 to eliminate fine lines and fill holes in the image. Then, remove the solder paste printing area from the binary image of the solder paste detection area to obtain the overflow solder paste printing area (e.g., Figure 3 (The box on the right shows a binary image of the solder paste.)

[0046] In fact, the solder paste printing area refers to the ideal area where the solder paste is located, determined by analyzing the production data GBS file, such as... Figure 2 As shown in the box; unlike the area where the solder pad is located, some larger solder pads may contain multiple solder paste printing areas. The solder paste inspection area refers to the area obtained by expanding around a single solder paste printing area, such as... Figure 2 The rectangular ring around the outer edge of the square frame is used to detect potential defects in the solder paste. In actual production, the surface of the solder paste is relatively rough, sometimes granular, leading to many small holes in the segmentation results. Simultaneously, the height image also contains noise appearing as mountain peaks, resulting in small dots and lines in the segmentation results. To eliminate these noises, morphological opening and closing operations are used to process the segmentation results. The size of the morphological structural element is determined based on the size of the solder paste printing area, and the calculation formula is shown below:

[0047]

[0048] in, This represents the size of the morphological structural element, where the size of the structural element is... The unit is pixels; , These represent the width and height of the solder paste detection area, respectively, in pixels. This indicates the operation of rounding up; , These represent the operations for finding the maximum and minimum values, respectively. It's important to note that since morphology calculations are performed at the pixel level, all values ​​in this step are in pixels.

[0049] S4. Based on the information regarding the shape and size of the solder paste printing area provided by the production data, a distance transformation is performed using the pixels of the solder paste printing area in the image as the target and the remaining pixels as the background. It is stipulated that the pixel value of the target pixel in the binary image is zero, and the pixel value of the background pixel is non-zero. In actual production, the inconsistent scale of the camera in the horizontal and vertical coordinate directions must also be considered when performing the distance transformation. Furthermore, experiments show that the chessboard distance can effectively describe the distance of solder paste overflow from the solder paste printing area. Therefore, this invention adopts the following distance transformation formula:

[0050]

[0051]

[0052] in, This represents non-zero pixels in a binary image, i.e., background pixels; , These represent the horizontal and vertical coordinates of non-zero pixels in the binary image in the top-left coordinate system of the image, respectively, in pixels. This represents the set containing all non-zero pixels in a binary image; This represents the pixel with zero gray level in a binary image, i.e., the target pixel; , These represent the horizontal and vertical coordinates of the pixels with zero grayscale in the binary image, respectively, in the upper left coordinate system of the image. This represents the set of all pixels in a binary image that have a gray level of zero. , These represent the camera's scale on the horizontal and vertical axes, respectively, in millimeters per pixel (mm / pixel). This indicates that for a set medium pixel The distance transformation performed; This indicates that for a set medium pixel Distance transformation performed.

[0053] S5. The threshold for judging bridging defects is obtained by finding the minimum width and height of the minimum bounding rectangle of the solder paste printing area and the minimum distance between the current solder paste printing area and other solder paste printing areas in the pad group. The calculation formula is as follows:

[0054]

[0055]

[0056] in, This indicates the center point of the solder paste printing area currently being detected. The solder paste printing area currently being detected is the area where the bridging length threshold needs to be calculated. , Indicates the center point The coordinates in the lower right coordinate system of the PCB (which is actually the coordinate system in the solder paste inspection machine) are in millimeters (mm). This represents the center point of the smallest bounding rectangle of the solder paste printing area that is not currently being inspected (i.e., the solder paste printing area that is not currently being inspected). , Indicates the center point The coordinates in the lower right coordinate system of the PCB are in millimeters (mm). This represents the set of center points of all solder paste printing areas within the same pad group; , These represent the width and height of the solder paste printing area image, respectively, in millimeters (mm); An empirical formula representing the width and height of the solder paste printing area image; Indicates the center of the current solder paste printing area. and solder paste printing area center The Euclidean distance; This indicates the length threshold for bridging detection in the current solder paste printing area, in millimeters (mm).

[0057] S6. Finally, using the binary image of the overflow solder paste printing area in S3 and the distance transformation image in S4, the distance between each pixel in the overflow solder paste and the solder paste printing area is obtained. Specifically, the pixel value (i.e., the distance of that pixel from the solder paste printing area) corresponding to the non-zero pixel in the distance transformation image and the binary image of the overflow solder paste printing area is recorded. The maximum and minimum values ​​are then found among the recorded pixel values. The difference between these maximum and minimum values ​​is defined as the distance of the overflow solder paste printing area. If this distance exceeds the threshold calculated in S5, a bridging defect is determined, and a bridging anomaly is output.

[0058] The present invention has the following effects:

[0059] (1) In the solder paste separation process, the present invention innovatively uses height information to filter out image noise that overlaps with the color information of the silk screen, pads and other solder paste, which can achieve better solder paste separation effect, effectively filter out the potential interference caused by green substrate and white silk screen to the separation, and significantly improve the stability of detection.

[0060] (2) The present invention uses the difference between the maximum and minimum values ​​of the chessboard distance between the solder paste overflowing area and the solder paste printing area in the image as the threshold for predicting solder paste bridging defects. In the calculation of distance transformation, the inconsistency of the scale in the horizontal and vertical coordinate directions of the camera is taken into account, which ensures the accuracy and speed of bridging defect detection.

[0061] (3) The threshold for bridging defects is automatically set using empirical formulas and the minimum distance between solder paste printing areas of pad groups, which reduces manual parameter setting while ensuring the effectiveness of the detection results. Furthermore, the algorithm of this invention is simple, reduces hardware requirements, improves detection efficiency, and avoids the overhead of training models. Specific Implementation Method Two:

[0063] This embodiment is a computer storage medium that stores at least one instruction, which is loaded and executed by a processor to implement the aforementioned visual inspection method for bridging defects in a solder paste inspection instrument.

[0064] It should be understood that the instructions include computer program products, software, or computerized methods corresponding to any method described in this invention; the instructions can be used to program computer systems or other electronic devices. Computer storage media may include readable media on which instructions are stored, and may include, but are not limited to, magnetic storage media, optical storage media; magneto-optical storage media include read-only memory (ROM), random access memory (RAM), erasable programmable memory (e.g., EPROM and EEPROM), and flash memory layers, or other types of media suitable for storing electronic instructions. Specific implementation method three:

[0066] This embodiment is a visual inspection device for bridging defects in solder paste inspection instruments. The device includes a processor and a memory. It should be understood that this includes any device including a processor and a memory described in this invention. The device may also include other units or modules that perform display, interaction, processing, control, and other functions through signals or instructions.

[0067] The memory stores at least one instruction, which is loaded and executed by the processor to implement the aforementioned visual inspection method for bridging defects in a solder paste inspection instrument.

[0068] Those skilled in the art will understand that at least one stored instruction constitutes a computer program product corresponding to a method or system. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0069] This application is described with reference to flowchart illustrations and / or block diagrams of methods, systems, and computer program products according to embodiments of this application, and can also be used with corresponding devices. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0070] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0071] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0072] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0073] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0074] The above examples of the present invention are merely illustrative of the computational model and process of the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is impossible to exhaustively list all possible implementations here. Any obvious variations or modifications derived from the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A visual inspection method for bridging defects in solder paste inspection instruments, characterized in that, include: S1. The solder paste detection region image in color space is segmented using a color-based segmentation algorithm to initially obtain a binary image of the solder paste region. S2. Based on the height threshold set according to the thickness of the stencil of the solder paste printing machine, the height image of the solder paste detection area is binarized, and the intersection of the binary image and the binary image of the solder paste area obtained in step S1 is taken to obtain the binary image of the solder paste area. S3. Perform morphological operations on the binary image of the solder paste region obtained in step S2, and then remove the solder paste printing area from the binary image of the solder paste detection area to obtain the binary image of the solder paste overflowing printing area. S4. Using the pixels of the solder paste printing area in the solder paste detection area image as the target and the remaining pixels as the background, the length of the solder paste overflowing from the solder paste printing area is measured by the chessboard distance. S6. Using the binary image of the solder paste in the overflow solder paste printing area in S3 and the distance transformation image in S4, the distance between each pixel in the overflow solder paste and the solder paste printing area is obtained. That is, the pixel value of the pixel at the position corresponding to the non-zero pixel in the distance transformation image and the binary image of the overflow solder paste printing area. The maximum and minimum values ​​are found in the recorded pixel values. The difference between the maximum and minimum values ​​is defined as the distance of the solder paste overflowing from the solder paste printing area. If the distance exceeds the length threshold, it is determined that there is a bridging defect.

2. The visual inspection method for bridging defects in a solder paste inspection instrument according to claim 1, characterized in that, The specific process of step S1 includes: The solder paste detection area image in the RGB color space is split into three grayscale images according to the color channels. Then, the grayscale images of each color channel are binarized according to the upper and lower limits of grayscale values ​​set for each channel. That is, the pixel values ​​of the grayscale values ​​between the upper and lower limits are assigned non-zero values, and the other pixels are set to zero. Then, the three binary images are ANDed with each other to obtain the preliminary binary segmentation result of the solder paste area.

3. The visual inspection method for bridging defects in a solder paste inspection instrument according to claim 2, characterized in that, During the process of assigning non-zero values ​​to pixels whose grayscale values ​​are between the upper and lower limits, the upper and lower limits of the red channel grayscale image are 220 and 90, respectively; the upper and lower limits of the green channel grayscale image are 240 and 150, respectively; and the upper and lower limits of the blue channel grayscale image are 210 and 100, respectively.

4. The visual inspection method for bridging defects in a solder paste inspection instrument according to claim 1, characterized in that, The height threshold set according to the stencil thickness of the solder paste printer is 40% of the stencil thickness.

5. A visual inspection method for bridging defects in a solder paste inspection instrument according to claim 1, characterized in that, During the morphological operation on the binary image of the solder paste region obtained in step S2, the size of the morphological structural element is set according to the size of the solder paste printing area in the production data, and the morphological operation is performed on the binary image of the solder paste region obtained in step S2. The size of the morphological structural element is as follows: in, This represents the size of the morphological structural element, where the size of the structural element is... The unit is pixels; , These represent the width and height of the solder paste detection area, respectively, in pixels; This indicates the operation of rounding up; , These represent operations to retrieve the maximum and minimum values, respectively.

6. The visual inspection method for bridging defects in a solder paste inspection instrument according to claim 1, characterized in that, In step S4, when the pixels of the solder paste printing area in the solder paste detection area image are taken as the target and the other pixels are the background, the pixel value of the target pixel is zero and the pixel value of the background pixel is non-zero.

7. A visual inspection method for bridging defects in a solder paste inspection instrument according to claim 6, characterized in that, The formula for measuring the length of the solder paste overflow printing area using the chessboard distance in step S4 is as follows: in, This represents the non-zero pixels in the binary image of the solder paste detection area; , These represent the horizontal and vertical coordinates of non-zero pixels in the binary image in the top-left coordinate system of the image, respectively, in pixels. This represents the set containing all non-zero pixels in a binary image; Represents a pixel with a gray level of zero in a binary image; , These represent the horizontal and vertical coordinates of the pixels with zero grayscale in the binary image, respectively, in the upper left coordinate system of the image. This represents the set of all pixels in a binary image that have a gray level of zero. , These represent the camera's scale on the horizontal and vertical axes, respectively, in millimeters per pixel (mm / pixel). This indicates that for a set medium pixel The distance transformation performed; This indicates that for a set medium pixel Distance transformation performed.

8. A visual inspection method for bridging defects in a solder paste inspection instrument according to any one of claims 1 to 7, characterized in that, The length threshold mentioned in step S6 is as follows: in, This indicates the center point of the solder paste printing area currently being detected. The solder paste printing area currently being detected is the area where the bridging length threshold needs to be calculated. , Indicates the center point The coordinates; This represents the center point of the smallest bounding rectangle of the solder paste printing area that is not currently being inspected. , Indicates the center point The coordinates; This represents the set of center points of all solder paste printing areas within the same pad group; , These represent the width and height of the solder paste printing area image, respectively. Indicates the center of the current solder paste printing area. and solder paste printing area center The Euclidean distance; This indicates the length threshold for bridging detection in the current solder paste printing area.

9. A computer storage medium, characterized in that, The storage medium stores at least one instruction, which is loaded and executed by a processor to implement a visual inspection method for bridging defects in a solder paste inspection instrument as described in any one of claims 1 to 8.

10. A visual inspection device for bridging defects in solder paste inspection instruments, characterized in that, The device includes a processor and a memory, the memory storing at least one instruction, which is loaded and executed by the processor to implement a visual inspection method for bridging defects in a solder paste inspection instrument as described in any one of claims 1 to 8.

Images