A method and system for crimping defect detection based on image processing

Abstract

The present invention relates to the technical field of crimping defect detection, and discloses a crimping defect detection method and system based on image processing, the method comprising: obtaining a copper column crimping image, graying the copper column crimping image, and obtaining a copper column crimping gray image; edge detection processing the copper column crimping gray image, and obtaining a copper column crimping edge image; processing the copper column crimping edge image, and obtaining a lens seat edge point set, and determining the center position of the lens seat according to the lens seat edge point set; binarizing the copper column crimping edge image, and obtaining a copper column crimping binary image, and determining the copper column position based on the copper column crimping binary image; based on the set copper column crimping parameters, defect detection is performed according to the relationship between the copper column position and the center position. The method of the present invention can effectively improve the accuracy and efficiency of lens copper column crimping defect detection, reduce production costs, and improve product quality.

Description

Technical Field

[0001] The present invention relates to the technical field of crimping defect detection, and in particular to a crimping defect detection method and system based on image processing. Background Art

[0002] The automatic crimping machine for lens copper pillars is a precision device specially used to connect cameras to various electronic devices. This machine plays a vital role in the production process of electronic products such as smartphones and computers, especially in the assembly stage of camera modules. Its core function is to accurately crimp the copper pillars to the lens through precise crimping technology, thereby ensuring the stability and reliability of the electrical connection. This process uses advanced "crimping" technology, which uses high-voltage force to accurately embed the copper pillars into the contact points of the lens to achieve seamless docking. The reason why the automatic crimping machine for lens copper pillars is so popular is mainly due to its efficient automated operation capabilities, which can significantly speed up the production process, reduce labor costs, and improve overall production efficiency.

[0003] Copper pillar crimping is a crucial interconnection technology that not only affects the smoothness of electrical connections between electronic components, but also directly affects the stability of mechanical fixation. These copper pillars are mostly made of copper or other metal materials with excellent conductive properties. One end is firmly crimped to the contact point of the circuit board, and the other end is tightly connected to another contact point or wire to build a stable electrical path. In order to ensure excellent electrical conductivity and reliable physical bonding strength, high-quality crimping technology is particularly important. Therefore, after the crimping is completed, the crimping results must be strictly tested and evaluated to ensure that every detail is perfect and impeccable.

[0004] However, at present, copper pillar crimping defect detection is generally carried out through human visual observation, or defects can only be discovered after using a crimping lens. This method is time-consuming and labor-intensive, involves subjective judgment, and using a crimping lens can easily cause a bad experience for users. Therefore, there is an urgent need for a crimping defect detection method and system based on image processing to realize intelligent crimping defect detection. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for crimping defect detection based on image processing, so as to solve the problem that the current copper pillar crimping defect detection is generally carried out by human naked eye observation, or the defects can only be found after using the crimping lens. This method is time-consuming and labor-intensive, involves subjective judgment, and the use of the crimping lens can easily cause a bad experience for users.

[0006] The present invention provides a method for detecting crimping defects based on image processing, the method comprising:

[0007] Acquire a copper pillar crimping image, and perform grayscale processing on the copper pillar crimping image to obtain a copper pillar crimping grayscale image;

[0008] Performing edge detection processing on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image;

[0009] Processing the copper column crimping edge image to obtain a lens mount edge point set, and determining the center position of the lens mount according to the lens mount edge point set;

[0010] Binarizing the copper pillar crimping edge image to obtain a copper pillar crimping binary image, and determining the copper pillar position based on the copper pillar crimping binary image;

[0011] Based on the set copper pillar crimping parameters, defect detection is performed according to the relationship between the copper pillar position and the center position.

[0012] Preferably, edge detection processing is performed on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image, including:

[0013] Obtaining the grayscale value of each pixel in the copper column crimping grayscale image;

[0014] The fuzzy edge points of each row in the copper pillar crimping grayscale image are determined, and the copper pillar crimping grayscale image is intercepted according to the fuzzy edge points to obtain a copper pillar crimping edge image.

[0015] Preferably, determining the fuzzy edge points of each row in the copper pillar crimping grayscale image comprises:

[0016] Dividing the copper pillar crimping grayscale image into m×n pixel points;

[0017] Calculate the grayscale difference between adjacent pixels in each row, and compare the grayscale difference with a preset grayscale difference;

[0018] If the grayscale difference is greater than the preset grayscale difference, determining that the pixel point corresponding to the grayscale difference is a fuzzy edge point;

[0019] If the grayscale difference is less than or equal to the preset grayscale difference, determining that the pixel point corresponding to the grayscale difference is not a fuzzy edge point;

[0020] Wherein, the grayscale difference is calculated according to the following formula:

[0021] ;

[0022] G ij1 G represents the grayscale difference between the pixel in the i-th row and j-th column and the pixel in the i-th row and j-1-th column. ijRepresents the grayscale value of the pixel in the i-th row and j-th column, G ij-1 Gd represents the gray value of the pixel in the i-th row and j-1th column. ij2 G represents the grayscale difference between the pixel in the i-th row and j-th column and the pixel in the i-th row and j+1-th column. ij+1 Represents the grayscale value of the pixel in the i-th row and j+1-th column.

[0023] Preferably, the copper column crimping edge image is processed to obtain a lens seat edge point set, including:

[0024] Determine all fuzzy edge points of the copper pillar crimping edge image;

[0025] The positions of the blurred edge points are compared to determine whether the blurred edge points are boundary points. If the blurred edge points are boundary points, the blurred edge points are added to the lens mount edge point set.

[0026] Preferably, determining the center position of the lens mount according to the lens mount edge point set comprises:

[0027] Determine the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01 of the copper column crimping edge image according to the lens mount edge point set;

[0028] Determine the center position of the lens mount according to the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01;

[0029] The calculation method of the zero-order moment M00 is:

[0030] ;

[0031] The calculation method of the horizontal first-order moment M10 is:

[0032] ;

[0033] The calculation method of the vertical first-order moment M01 is:

[0034] ;

[0035] Among them, i represents the i-th row, j represents the j-th column, and G ij Represents the grayscale value of the pixel in the i-th row and j-th column.

[0036] Preferably, the center position of the lens mount is calculated as follows:

[0037] ;

[0038] Among them, X represents the row where the center position is located, and Y represents the column where the center position is located.

[0039] Preferably, the copper column crimping edge image is binarized, comprising:

[0040] Set the binarization threshold;

[0041] The gray value G of each pixel in the copper column crimping edge image is ij Compare with the binarization threshold g, and determine the binarization value according to the comparison result;

[0042] When the gray value G ij ≥ the binarization threshold g, the binarization value is 255;

[0043] When the gray value G ij When <binarization threshold g, the binarization value is 0.

[0044] Preferably, determining the position of the copper pillar based on the copper pillar crimping binary image includes:

[0045] Determine the pixel points of the copper pillar according to the copper pillar crimping binary image;

[0046] The position of the copper column is determined according to the pixel points of the copper column.

[0047] Preferably, based on the set copper column crimping parameters, defect detection is performed according to the relationship between the copper column position and the center position, including:

[0048] The copper pillar crimping parameters include the copper pillar standard position;

[0049] Determining a standard position relationship between the center position and the standard position of the copper column;

[0050] Determining a real-time positional relationship between the center position and the copper column position;

[0051] The real-time position relationship is compared with the standard position relationship. If the real-time position relationship is consistent with the standard position relationship, it is determined that there is no defect in the crimping.

[0052] The present invention also discloses a crimping defect detection system based on image processing, which is used to apply the crimping defect detection method based on image processing, and the system comprises:

[0053] An image acquisition module is used to photograph the copper pillar after crimping to obtain a copper pillar crimping image;

[0054] A grayscale processing module, used for performing grayscale processing on the copper pillar crimping image to obtain a copper pillar crimping grayscale image;

[0055] An edge detection module is used to perform edge detection processing on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image;

[0056] A lens mount copper pillar determination module is used to process the copper pillar crimping edge image to obtain a lens mount edge point set, and determine the center position of the lens mount according to the lens mount edge point set; and to perform binarization processing on the copper pillar crimping edge image to obtain a copper pillar crimping binary image, and determine the copper pillar position based on the copper pillar crimping binary image;

[0057] The defect detection module is used to perform defect detection based on the set copper column crimping parameters and the relationship between the copper column position and the center position.

[0058] Compared with the prior art, the invention has the beneficial effect that the method of the invention can effectively improve the accuracy and efficiency of lens copper column crimping defect detection, reduce production costs, and improve product quality. Through automated image processing and intelligent analysis, the workload and subjective errors of manual inspection are greatly reduced, providing an efficient and accurate quality control method for the electronics manufacturing industry.

[0059] The present invention can accurately detect the defects of copper pillar crimping through the image processing method, ensure product quality, realize an automated detection process, and improve detection efficiency. The present invention can quickly detect and judge crimping defects by processing crimping images, find problems in time, and facilitate taking corresponding measures, thereby reducing rework and waste caused by defects, improving production efficiency, and avoiding the influence of human factors on the detection results, so that the detection results are more objective and accurate. The present invention can be applied to the detection of different types of copper pillar crimping images, and has good adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0061] Figure 1 It is a flow chart of a crimping defect detection method based on image processing of the present invention.

[0062] Figure 2 It is a functional block diagram of a crimping defect detection system based on image processing of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0064] like Figure 1 As shown, the present invention provides a crimping defect detection method based on image processing, the method comprising:

[0065] S1, obtaining a copper pillar crimping image, and performing grayscale processing on the copper pillar crimping image to obtain a copper pillar crimping grayscale image.

[0066] S2, performing edge detection processing on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image.

[0067] S3, processing the copper column crimping edge image to obtain a lens mount edge point set, and determining the center position of the lens mount according to the lens mount edge point set.

[0068] S4, binarizing the copper pillar crimping edge image to obtain a copper pillar crimping binary image, and determining the copper pillar position based on the copper pillar crimping binary image.

[0069] S5, based on the set copper pillar crimping parameters, defect detection is performed according to the relationship between the copper pillar position and the center position.

[0070] In this embodiment, the present application provides a crimping defect detection technology based on image processing, which can accurately identify and detect defects in the copper pillar crimping process through a series of fine image processing steps. The method is mainly as follows: first, image data of copper pillar crimping is obtained. The original copper pillar crimping image is obtained through a high-precision image acquisition device. Next, in order to reduce unnecessary color information in the image, we grayscale the image, through which the copper pillar crimping image can be converted into a grayscale image containing only brightness information, thereby simplifying subsequent processing steps. The obtained grayscale image is edge detected. Edge detection is an important image processing technology, and its purpose is to identify the contour lines of objects in the image. Through this step, an edge image of copper pillar crimping can be obtained, which clearly shows the contour of the copper pillar crimping part. Further, the copper pillar crimping edge image is finely processed to extract a set of points on the edge of the lens mount. These point sets are the key to determining the center position of the lens mount. By calculating and analyzing these edge points, the center position of the lens mount can be determined, which is of great significance for subsequent defect detection. The edge image of the copper pillar crimping is binarized. Binarization is a technology that divides the pixels in an image into two different grayscale levels, usually black and white. Through this processing, a binary image of the copper pillar crimping can be obtained, which can clearly show the position information of the copper pillar, providing strong support for further defect detection. Finally, based on the pre-set copper pillar crimping parameters, defect detection is performed using the relationship between the copper pillar position and the center position. In this process, the quality of the copper pillar crimping is evaluated through calculation and analysis to determine whether there are defects. This step is the core of the entire method, and its results are of great significance for controlling and improving the crimping quality. In general, the present invention provides an efficient and accurate crimping defect detection method through a series of innovative image processing technologies, which is of great value for improving production efficiency and product quality.

[0071] In some embodiments of the present application, edge detection processing is performed on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image, including: obtaining the grayscale value of each pixel in the copper pillar crimping grayscale image; determining the fuzzy edge points of each row in the copper pillar crimping grayscale image, and intercepting the copper pillar crimping grayscale image according to the fuzzy edge points to obtain the copper pillar crimping edge image.

[0072] In the present embodiment, the grayscale image of the copper column crimping is processed in depth using edge detection technology, with the purpose of accurately obtaining the edge image of the copper column crimping. The processing process involves the following main steps: First, it is necessary to obtain the grayscale value of each pixel in the copper column crimping grayscale image. This step is the basis and the key, because subsequent image processing is based on this basis. Each pixel is scanned and its grayscale value is recorded, which provides data support for subsequent image analysis. Next, the fuzzy edge points of each row in the copper column crimping grayscale image are determined, and those points in the image with significant grayscale changes are identified, which are often the edges of objects. Since the image may be disturbed by various factors in the real environment, the edge points may be blurred. Finally, according to the determined fuzzy edge points, the copper column crimping grayscale image is intercepted to obtain the copper column crimping edge image. This step is actually a cropping of the image, retaining only the edge parts containing key information, so that image analysis is more efficient and accurate. The obtained copper pillar crimping edge image can be used for subsequent advanced processing such as image recognition and shape analysis, which helps to improve the control level and efficiency of copper pillar crimping quality. In general, through this series of image processing steps, not only the clarity of the image is improved, but also the most critical information is retained, which is of great significance for the quality assessment of copper pillar crimping and the improvement of the production process.

[0073] In some embodiments of the present application, determining the fuzzy edge points of each row in the copper pillar crimping grayscale image includes: dividing the copper pillar crimping grayscale image into m×n pixel points; calculating the grayscale difference between adjacent pixel points in each row, and comparing the grayscale difference with a preset grayscale difference; if the grayscale difference is greater than the preset grayscale difference, determining that the pixel point corresponding to the grayscale difference is a fuzzy edge point; if the grayscale difference is less than or equal to the preset grayscale difference, determining that the pixel point corresponding to the grayscale difference is not a fuzzy edge point.

[0074] In this embodiment, in order to identify the fuzzy edge points of each row in the grayscale image of the copper pillar crimping part, a series of detailed processing steps need to be performed. First, the entire grayscale image of the copper pillar crimping is subdivided into a grid structure consisting of m rows and n columns of pixels. This step is to decompose the image into smaller, easier to analyze areas so that the pixels of each row can be checked separately. Next, in order to identify the fuzzy edge points in each row, it is necessary to calculate the grayscale difference between each pair of adjacent pixels. The grayscale difference refers to the brightness difference between two adjacent pixels in the grayscale level, which can identify the edges or boundaries that may exist in the image. After obtaining the grayscale difference of each pair of adjacent pixels, these differences are compared with a preset grayscale difference threshold set in advance. This preset threshold is set based on the characteristics of the image and the edge type you want to identify. The purpose of the comparison is to determine whether the actual grayscale difference exceeds the preset threshold range. If the grayscale difference of a pair of adjacent pixels exceeds the preset threshold, it means that this area may be a fuzzy edge part of the image. In this case, this pair of pixels can be determined as a fuzzy edge point. This is because a large grayscale difference usually indicates a significant change in brightness in the image, which is often associated with edges. On the contrary, if the grayscale difference between a pair of adjacent pixels does not exceed the preset threshold, the pixel corresponding to this grayscale difference will not be identified as a fuzzy edge point. This indicates that the image may be smooth in this area, without obvious edges or boundaries. Through such analysis, the fuzzy edge points in the image can be identified line by line, providing important information for further image processing and analysis. These identified fuzzy edge points can be used in a variety of applications, such as image segmentation, feature extraction or quality control.

[0075] Wherein, the grayscale difference is calculated according to the following formula:

[0076] ;

[0077] G ij1 G represents the grayscale difference between the pixel in the i-th row and j-th column and the pixel in the i-th row and j-1-th column. ij Represents the grayscale value of the pixel in the i-th row and j-th column, G ij-1 Gd represents the gray value of the pixel in the i-th row and j-1th column. ij2 G represents the grayscale difference between the pixel in the i-th row and j-th column and the pixel in the i-th row and j+1-th column. ij+1 Represents the grayscale value of the pixel in the i-th row and j+1-th column.

[0078] It can be understood that, assuming that the copper pillar crimping grayscale image is divided into 1000 rows and 800 columns, if the number of columns is 300, when calculating the grayscale difference, the grayscale difference Gd between the pixel point at the 100th row and 300th column and the pixel point at the 100th row and 299th column is1003001 , Gd 1003001 Compare with the preset grayscale difference, if Gd 1003001 is 125, and the preset grayscale difference is 100, then Gd 1003001 If the grayscale difference is greater than the preset grayscale difference, the pixel at the 100th row and 300th column is a fuzzy pixel; if the number of columns is 500, when calculating the grayscale difference, the grayscale difference Gd between the pixel at the 100th row and 500th column and the pixel at the 100th row and 501st column is 1005002 , Gd 1005002 Compare with the preset grayscale difference, if Gd 1005002 is 130, and the preset grayscale difference is 100, then Gd 1005002 If the grayscale difference is greater than the preset grayscale difference, the pixel at the 100th row and 500th column is a fuzzy pixel.

[0079] In some embodiments of the present application, the copper pillar crimping edge image is processed to obtain a lens mount edge point set, including: determining all fuzzy edge points of the copper pillar crimping edge image; comparing the positions of the fuzzy edge points to determine whether the fuzzy edge points are boundary points, and if the fuzzy edge points are boundary points, adding them to the lens mount edge point set.

[0080] In the present embodiment, the copper pillar crimping edge image is processed to obtain a point set of the lens mount edge. First, all fuzzy edge points in the copper pillar crimping edge image are identified. Next, the positions of the identified fuzzy edge points are compared and analyzed. The purpose of this process is to determine whether these fuzzy edge points are boundary points. Boundary points refer to those points located at the edge of an object, which play an important role in subsequent image processing and analysis. If, after comparative analysis, it is determined that a certain fuzzy edge point is a boundary point, then we will add it to the lens mount edge point set. In general, this process is to process the copper pillar crimping edge image to obtain a detailed description of the lens mount edge point set. The purpose of this process is to ensure the accuracy of subsequent processing and provide reliable data support for image processing and analysis.

[0081] In some embodiments of the present application, the center position of the lens mount is determined based on the set of edge points of the lens mount, including: determining the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01 of the copper pillar crimping edge image based on the set of edge points of the lens mount; and determining the center position of the lens mount based on the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01.

[0082] In this embodiment, in order to accurately locate the core position of the lens mount in the image, this method adopts a calculation method based on the edge point set. Specifically, this process first involves careful analysis and processing of the key points on the edge of the lens mount. These key points include a series of edge points, which are important references for determining the position of the lens mount. When processing these edge points, three important mathematical moments are first calculated, namely the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01. These moments are basic concepts in image processing, and they can reflect the characteristic distribution of the image in all directions. The zero-order moment M00 represents the total area of ​​the edge points of the lens mount, which can be regarded as the brightness center of the image; the horizontal first-order moment M10 is the integral of the image in the horizontal direction, which can indicate the approximate position of the image center in the horizontal direction; the vertical first-order moment M01 is the integral of the image in the vertical direction, which can also reflect the position of the image center in the vertical direction. After obtaining these three moments, they can be converted into the center position coordinates of the lens mount through a series of mathematical calculations. Specifically, this process uses the above-mentioned zero-order moment M00, horizontal first-order moment M10 and vertical first-order moment M01 to determine the center point position of the lens mount through an image processing algorithm. This process can not only improve the accuracy of the lens mount position determination, but also make the lens mount positioning process more automated and efficient. In summary, by analyzing the zero-order moment M00, horizontal first-order moment M10 and vertical first-order moment M01, the center position of the lens mount can be accurately calculated, providing a solid foundation for subsequent image processing and analysis. This method has broad application prospects in the field of image processing, especially in situations where high-precision positioning is required, its superiority is more obvious.

[0083] The calculation method of the zero-order moment M00 is:

[0084] ;

[0085] The calculation method of the horizontal first-order moment M10 is:

[0086] ;

[0087] The calculation method of the vertical first-order moment M01 is:

[0088] ;

[0089] Among them, i represents the i-th row, j represents the j-th column, and G ij Represents the grayscale value of the pixel in the i-th row and j-th column.

[0090] In some embodiments of the present application, the center position of the lens mount is calculated as follows:

[0091] ;

[0092] Among them, X represents the row where the center position is located, and Y represents the column where the center position is located.

[0093] In some embodiments of the present application, the copper column crimping edge image is binarized, including: setting a binarization threshold; converting the gray value G of each pixel in the copper column crimping edge image into ij The gray value G is compared with the binary threshold g, and the binary value is determined according to the comparison result; when the gray value G ij ≥ binarization threshold g, the binarization value is 255; when the gray value G ij When <binarization threshold g, the binarization value is 0.

[0094] In this embodiment, the copper pillar crimping edge image needs to be binarized, and this step mainly includes the following aspects: first, a binarization threshold is set, and this threshold will be used as a comparison standard; next, the grayscale value Gij of each pixel in the copper pillar crimping edge image needs to be analyzed one by one, and the grayscale value of each pixel is compared with the set binarization threshold g; through this comparison process, the binarization value of each pixel can be determined according to the comparison result; specifically, when the grayscale value Gij of a pixel is greater than or equal to the binarization threshold g, its binarization value is set to 255; conversely, when the grayscale value Gij of the pixel is less than the binarization threshold g, its binarization value is set to 0.

[0095] It is understandable that, assuming the following pixel gray value G 11 180, G 12 160, G 13 190, G 21 170, G 22 150, G 23 is 140, and the binarization threshold is set to 160. According to the above comparison rules, the binarized value is: G 11 Corresponding to 255, G 12 Corresponding to 255, G 13 Corresponding to 255, G 21 Corresponding to 255, G 22 Corresponding to 0, G 23 The corresponding value is 0.

[0096] In some embodiments of the present application, determining the position of the copper pillar based on the copper pillar crimping binary image includes: determining the pixel points of the copper pillar according to the copper pillar crimping binary image; and determining the position of the copper pillar according to the pixel points of the copper pillar.

[0097] In this embodiment, based on the binarization process of the copper pillar crimping image, the specific position of the copper pillar in the image can be accurately determined. This process mainly includes two steps: first, it is necessary to analyze the copper pillar crimping binary image to identify the pixel points corresponding to the copper pillar; second, through these pixel points, the exact position of the copper pillar in the image can be calculated. In this way, it is possible to accurately identify the position of the copper pillar, providing a reliable basis for subsequent image processing and analysis. Specifically, the first step involves the observation and analysis of the copper pillar crimping binary image. In this process, the computer algorithm scans the entire image to find those pixels that match the copper pillar features. These pixels may be different from the surrounding pixels due to the shape, size or texture of the copper pillar, so that they can be identified in the image. By collecting and sorting these pixels, a set of pixels related to the copper pillar can be constructed. Next, the second step is to further determine the position of the copper pillar based on this set of pixels. This involves calculating and analyzing the coordinates of the pixel points to obtain the specific coordinates of the copper pillar in the image. These coordinates include not only the center position of the copper column, but also the edge of the copper column or the position of other important feature points. By analyzing the data of these coordinates, the precise position of the copper column in the image can be obtained, providing an important reference for subsequent image processing and analysis.

[0098] In summary, the process of determining the position of the copper pillar based on the binary image of the copper pillar crimping is a process of accurately identifying the position of the copper pillar in the image through pixel analysis and coordinate calculation. This process not only relies on efficient computer algorithms, but also requires a deep understanding and mastery of the characteristics of the copper pillar and the characteristics of the image. Through such processing, it can ensure that the position of the copper pillar is accurately identified and marked in the image, thereby providing a reliable basis for subsequent image processing and analysis.

[0099] In some embodiments of the present application, based on the set copper pillar crimping parameters, defect detection is performed according to the relationship between the copper pillar position and the center position, including: the copper pillar crimping parameters include the copper pillar standard position; determining the standard position relationship between the center position and the copper pillar standard position; determining the real-time position relationship between the center position and the copper pillar position; comparing the real-time position relationship with the standard position relationship, if the real-time position relationship is consistent with the standard position relationship, determining that there is no defect in the crimping.

[0100] In this embodiment, in the process of performing the copper pillar crimping operation, in order to ensure that the crimping quality meets the predetermined standards, a set of precise defect detection mechanisms are introduced. The mechanism is based on a series of pre-set copper pillar crimping parameters, which specify in detail various indicators of the copper pillar during the crimping process, such as size, shape and position. Among these parameters, the standard position of the copper pillar is one of the core elements, which provides a reference point for detection. When implementing defect detection, it is first necessary to determine the position of the copper pillar, which is done by high-precision sensors and measuring equipment. Subsequently, according to the set copper pillar crimping parameters, the ideal relationship between the center position and the standard position is calculated, and this process is called determining the standard position relationship. Next, the position change of the copper pillar is monitored in real time, and the real-time position relationship between the center position and the actual crimping position is calculated. This step is crucial because it directly reflects the actual state of the copper pillar during the crimping process. Finally, the real-time position relationship is carefully compared and analyzed with the standard position relationship. If there is no significant difference between the two, that is, the real-time position relationship meets the requirements of the standard position relationship, then it will be determined that the crimping operation is qualified and there are no defects. The efficient use of this detection method has greatly improved the yield and reliability of the copper pillar crimping process, ensuring that the quality standards of the manufacturing industry are implemented. This intelligent detection method can not only detect problems in a timely manner and correct them, but also greatly improve production efficiency and reduce resource waste. It is one of the indispensable technical means in modern manufacturing.

[0101] The present invention also discloses a crimping defect detection system based on image processing, which is used to apply the crimping defect detection method based on image processing, such as Figure 2 As shown, the system comprises:

[0102] The image acquisition module is used to photograph the copper pillar after crimping to obtain the copper pillar crimping image.

[0103] The grayscale processing module is used to perform grayscale processing on the copper pillar crimping image to obtain a copper pillar crimping grayscale image.

[0104] The edge detection module is used to perform edge detection processing on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image.

[0105] The lens mount copper pillar determination module is used to process the copper pillar crimping edge image to obtain a lens mount edge point set, and determine the center position of the lens mount based on the lens mount edge point set; and to binarize the copper pillar crimping edge image to obtain a copper pillar crimping binary image, and determine the copper pillar position based on the copper pillar crimping binary image.

[0106] The defect detection module is used to perform defect detection based on the set copper column crimping parameters and the relationship between the copper column position and the center position.

[0107] The present application discloses a crimping defect detection system based on image processing. Specifically, the system includes the following key modules: an image acquisition module, which is used to photograph the copper column after crimping, thereby obtaining the original image of the copper column crimping. This step is the basis for subsequent image processing, ensuring that clear and accurate image data can be obtained.

[0108] Grayscale processing module, this module performs grayscale processing on the acquired copper pillar crimping image. Grayscale processing is a common technology in image processing. By removing the color information in the image and converting the image into a grayscale image, it helps to simplify the subsequent processing process and reduce the amount of calculation.

[0109] Edge detection module, which performs edge detection on the grayscale copper pillar crimping image. Edge detection is an important step in image processing, which can extract edge information in the image, thereby more clearly showing the shape and structure of the copper pillar crimping. Through edge detection, the edge image of the copper pillar crimping can be further obtained.

[0110] The lens mount copper pillar determination module is responsible for further processing the image after edge detection. First, by processing the edge image, the point set of the lens mount edge is obtained, and the center position of the lens mount is determined based on this. At the same time, the edge image is binarized to obtain a binary image of the copper pillar crimping. In the binary image, the position of the copper pillar can be more clearly identified, thereby determining the specific position of the copper pillar.

[0111] Defect Detection Module,Finally, this module performs defect detection based on the set copper pillar crimping parameters and the relationship between the copper pillar position and the center position of the lens mount.,By comparing the difference between the actual position and the ideal position, it can be determined whether there is a defect in the copper pillar crimping and give the corresponding detection results.

[0112] In summary, the image processing-based crimping defect detection system of the present invention realizes the automated detection of copper pillar crimping defects through the collaborative work of multiple modules. The system is efficient, accurate and reliable, and can significantly improve the efficiency and quality of crimping quality detection.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that they can still modify or replace the technical solution of the present invention with equivalents, and these modifications or equivalent replacements cannot cause the modified technical solution to deviate from the spirit and scope of the technical solution of the present invention.

[0114] The system provided in the above embodiment is only illustrated by the division of the above functional modules. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the modules or steps in the embodiments of the present invention can be decomposed or combined. For example, the modules in the above embodiment can be combined into one module, or further divided into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only for distinguishing the modules or steps, and are not regarded as improper limitations of the present invention.

[0115] Those skilled in the art should be able to appreciate that the modules and method steps of each example described in conjunction with the embodiments disclosed herein can be implemented with electronic hardware, computer software or a combination of the two, and the programs corresponding to the software modules and method steps can be placed in random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the technical field. In order to clearly illustrate the interchangeability of electronic hardware and software, the composition and steps of each example have been generally described in the above description according to the function. Whether these functions are performed in electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

Claims

1. A crimping defect detection method based on image processing, characterized in that: The method comprises: Acquire a copper pillar crimping image, and perform grayscale processing on the copper pillar crimping image to obtain a copper pillar crimping grayscale image; Performing edge detection processing on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image; Processing the copper column crimping edge image to obtain a lens mount edge point set, and determining the center position of the lens mount according to the lens mount edge point set; Binarizing the copper pillar crimping edge image to obtain a copper pillar crimping binary image, and determining the copper pillar position based on the copper pillar crimping binary image; Based on the set copper pillar crimping parameters, defect detection is performed according to the relationship between the copper pillar position and the center position; Determining the center position of the lens mount according to the lens mount edge point set includes: Determine the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01 of the copper column crimping edge image according to the lens mount edge point set; Determine the center position of the lens mount according to the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01; The calculation method of the zero-order moment M00 is: ； The calculation method of the horizontal first-order moment M10 is: ； The calculation method of the vertical first-order moment M01 is: ； Among them, i represents the i-th row, j represents the j-th column, G ij Represents the grayscale value of the pixel in the i-th row and j-th column; The center position of the lens mount is calculated as: ； Among them, X represents the row where the center position is located, and Y represents the column where the center position is located; Based on the set copper pillar crimping parameters, defect detection is performed according to the relationship between the copper pillar position and the center position, including: The copper pillar crimping parameters include the copper pillar standard position; Determining a standard position relationship between the center position and the standard position of the copper column; Determining a real-time positional relationship between the center position and the copper column position; The real-time position relationship is compared with the standard position relationship. If the real-time position relationship is consistent with the standard position relationship, it is determined that there is no defect in the crimping.

2. The crimping defect detection method based on image processing according to claim 1 is characterized in that: Performing edge detection processing on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image includes: Obtaining the grayscale value of each pixel in the copper column crimping grayscale image; The fuzzy edge points of each row in the copper pillar crimping grayscale image are determined, and the copper pillar crimping grayscale image is intercepted according to the fuzzy edge points to obtain a copper pillar crimping edge image.

3. The crimping defect detection method based on image processing according to claim 2 is characterized in that: Determining the fuzzy edge points of each row in the copper pillar crimping grayscale image includes: Dividing the copper pillar crimping grayscale image into m×n pixel points; Calculate the grayscale difference between adjacent pixels in each row, and compare the grayscale difference with a preset grayscale difference; If the grayscale difference is greater than the preset grayscale difference, determining that the pixel point corresponding to the grayscale difference is a fuzzy edge point; If the grayscale difference is less than or equal to the preset grayscale difference, determining that the pixel point corresponding to the grayscale difference is not a fuzzy edge point; Wherein, the grayscale difference is calculated according to the following formula: ； G ij1 G represents the grayscale difference between the pixel in the i-th row and j-th column and the pixel in the i-th row and j-1-th column. ij Represents the grayscale value of the pixel in the i-th row and j-th column, G ij-1 Gd represents the gray value of the pixel in the i-th row and j-1th column. ij2 G represents the grayscale difference between the pixel in the i-th row and j-th column and the pixel in the i-th row and j+1-th column. ij+1 Represents the grayscale value of the pixel in the i-th row and j+1-th column.

4. The crimping defect detection method based on image processing according to claim 3 is characterized in that: The copper column crimping edge image is processed to obtain a lens seat edge point set, including: Determine all fuzzy edge points of the copper pillar crimping edge image; The positions of the blurred edge points are compared to determine whether the blurred edge points are boundary points. If the blurred edge points are boundary points, the blurred edge points are added to the lens mount edge point set.

5. The crimping defect detection method based on image processing according to claim 4 is characterized in that: The copper pillar crimping edge image is binarized, including: Set the binarization threshold; The gray value G of each pixel in the copper column crimping edge image is ij Compare with the binarization threshold g, and determine the binarization value according to the comparison result; When the gray value G ij ≥ the binarization threshold g, the binarization value is 255; When the gray value G ij When <binarization threshold g, the binarization value is 0.

6. The crimping defect detection method based on image processing according to claim 5 is characterized in that: Determining the position of the copper pillar based on the copper pillar crimping binary image includes: Determine the pixel points of the copper pillar according to the copper pillar crimping binary image; The position of the copper column is determined according to the pixel points of the copper column.

7. A crimping defect detection system based on image processing, used for applying the crimping defect detection method based on image processing as described in any one of claims 1 to 6, characterized in that: The system comprises: An image acquisition module is used to photograph the copper pillar after crimping to obtain a copper pillar crimping image; A grayscale processing module, used for performing grayscale processing on the copper pillar crimping image to obtain a copper pillar crimping grayscale image; An edge detection module is used to perform edge detection processing on the copper pillar crimping grayscale image to obtain a copper pillar crimping edge image; A lens mount copper pillar determination module is used to process the copper pillar crimping edge image to obtain a lens mount edge point set, and determine the center position of the lens mount according to the lens mount edge point set; and to perform binarization processing on the copper pillar crimping edge image to obtain a copper pillar crimping binary image, and determine the copper pillar position based on the copper pillar crimping binary image; A defect detection module, used for performing defect detection based on the set copper column crimping parameters and the relationship between the copper column position and the center position; The lens mount copper column determination module determines the center position of the lens mount according to the lens mount edge point set, including: Determine the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01 of the copper column crimping edge image according to the lens mount edge point set; Determine the center position of the lens mount according to the zero-order moment M00, the horizontal first-order moment M10, and the vertical first-order moment M01; The calculation method of the zero-order moment M00 is: ； The calculation method of the horizontal first-order moment M10 is: ； The calculation method of the vertical first-order moment M01 is: ； Among them, i represents the i-th row, j represents the j-th column, G ij Represents the grayscale value of the pixel in the i-th row and j-th column; The center position of the lens mount is calculated as: ； Among them, X represents the row where the center position is located, and Y represents the column where the center position is located; The defect detection module performs defect detection based on the set copper column crimping parameters and the relationship between the copper column position and the center position, including: The copper pillar crimping parameters include the copper pillar standard position; Determining a standard position relationship between the center position and the standard position of the copper column; Determining a real-time positional relationship between the center position and the copper column position; The real-time position relationship is compared with the standard position relationship. If the real-time position relationship is consistent with the standard position relationship, it is determined that there is no defect in the crimping.

Images