Tab defect detection method and system, storage medium and equipment

Abstract

The invention provides a tab defect detection method and system, a storage medium and equipment, and the method comprises the steps: obtaining a detection image of a to-be-detected tab, and obtaining a fitting straight line according to the detection image and a caliper region; then skeleton region subtraction is carried out based on the detection image, and the detection image after skeleton region subtraction is segmented into a plurality of line segments; and further comparing each line segment with the fitting straight line, and determining the defect detection condition of the to-be-detected tab according to a comparison result. According to the invention, when the caliper tool is used for measurement, the detection of the tab defects is realized, parameters in the caliper tool are utilized, a defect detection method does not need to be independently used for detection, and the detection efficiency of the tab defects is accelerated; meanwhile, the fitting straight line is compared with the line segment, the operation process is simple, and the tab defect detection efficiency is further improved.

Description

Technical Field

[0001] The present application relates to the field of battery technology, and in particular to a tab defect detection method, system, storage medium, and device. Background Art

[0002] The tab cutting process is crucial in the battery assembly process, directly impacting battery performance and quality. As a crucial conductive component during the battery's charge and discharge processes, the tab's dimensional accuracy and appearance play a decisive role in overall battery performance. Therefore, after the tab is cut, it must be precisely measured and rigorously inspected.

[0003] Measurements primarily focus on the length and width of the tabs, two critical dimensions that must strictly meet design requirements. Precise dimensions are essential for ensuring a perfect fit between the tabs and other battery components and efficient electrical conductivity. Calipers are typically used for these measurements. Any dimensional deviation outside the permitted range can lead to abnormal battery charging and discharging, or even pose a safety hazard. Currently, the industry typically uses blob analysis technology to detect tab defects. This analysis must be performed after the tabs have been measured, adding complexity and time to the overall inspection process. Summary of the Invention

[0004] In order to solve the above technical problems, the present application provides a tab defect detection method, system, storage medium and device that can improve the efficiency of tab defect detection.

[0005] Specifically, the present application provides a tab defect detection method, comprising: Acquire a test image of the tab to be inspected, and obtain a fitting straight line based on the test image and the caliper area; perform a skeleton area subtraction based on the test image, and divide the test image after the skeleton area subtraction into a plurality of line segments; and compare each line segment with the fitting straight line to determine the defect detection status of the tab to be inspected based on the comparison result.

[0006] In the above technical solution, the detection of tab defects is achieved when a caliper tool is used for measurement. The parameters in the caliper tool are utilized, and there is no need to use a separate defect detection method for detection, which speeds up the detection efficiency of tab defects. At the same time, fitting straight lines and line segments are used for comparison, and the operation process is simple, which further improves the detection efficiency of tab defects.

[0007] Furthermore, before acquiring the detection image, it includes: presetting detection parameters; wherein the detection parameters at least include the number of calipers, the size of the calipers, the search direction and the image grayscale value.

[0008] In the above technical solution, the setting parameters can be adjusted according to the specific characteristics of the tab and the actual situation of the image, so that the tab defect detection method can adapt to tabs with different lighting conditions, materials and surface conditions; at the same time, reasonable parameter settings can improve the accuracy of subsequent edge detection and reduce the possibility of false detection and missed detection; for example, by adjusting the number and size of calipers, the characteristics of the tab edge can be captured more finely.

[0009] Furthermore, obtaining the fitting straight line includes: setting a caliper area on the detection image based on the number and size of the calipers; based on the caliper area, finding the fitting points on the detection image according to the search direction; and obtaining the fitting straight line based on the fitting points by using the least squares method.

[0010] In the above technical solution, by drawing a caliper area on the detection image of the tab to be detected, the starting area where the edge needs to be found can be accurately located, providing a clear starting point for subsequent edge detection, reducing unnecessary image analysis range, and improving detection efficiency; the caliper area is set based on the number of calipers and the size of the caliper, so that the range of the caliper area is more accurate; in addition, the fitting point is a simplified representation of the edge features of the tab. By generating the fitting point, the complex edge information can be converted into a discrete point set, which is convenient for subsequent straight line fitting processing. At the same time, the fitting point can highlight the main features of the tab edge, reduce the influence of noise and other interference factors, and make the subsequent edge detection more accurate; further, the fitting point is processed using the least squares method to fit a straight line, which can quantify the position and direction information of the tab edge, which is convenient for subsequent analysis and judgment.

[0011] Among them, the least squares method is a commonly used fitting method with good stability and anti-interference ability. It can accurately fit the edge straight line of the tab in the presence of certain noise.

[0012] Furthermore, before performing the skeleton area subtraction, it includes: performing edge detection on the detection image based on the caliper area to obtain a lug edge image; performing grayscale processing on the lug edge image according to the image grayscale value to obtain a lug grayscale image; and performing skeleton extraction based on the lug grayscale image to obtain a skeleton area image.

[0013] In the above technical solution, edge detection of the tab is performed in the caliper area, which can highlight the edge features of the tab, so that subsequent analysis can focus more on the edge area of ​​the tab and reduce interference from other areas; at the same time, the result of edge detection is the basis for subsequent image grayscale analysis, skeleton extraction and other processing. Accurate edge detection can improve the accuracy of the entire foreign body detection process.

[0014] Furthermore, by performing image grayscale processing using the image grayscale value set in the set detection parameters, the tab and defect area can be distinguished based on the grayscale value difference, and the defect area can be separated from the background; and through grayscale analysis, the detection image can be enhanced to improve the image contrast, making the defect more obvious and facilitating subsequent detection and analysis.

[0015] Furthermore, skeleton extraction is performed on the grayscale processed inspection image, which can simplify the complex image structure into a one-dimensional skeleton line, reduce the amount of data and improve processing efficiency; and the skeleton line retains the main shape information of the tabs and defects, can accurately reflect their structural characteristics, and provide a basis for the subsequent extraction of junction points and end points.

[0016] Furthermore, obtaining a plurality of line segments includes: traversing the skeleton region image to obtain joining points and end points; performing skeleton region subtraction based on the joining points and end points to obtain a region subtraction image; and performing line segmentation based on the region subtraction image to obtain a plurality of line segments.

[0017] In the above technical solution, the joining point refers to the intersection of three or more skeleton lines, and the end point refers to the end point of the skeleton line; the extraction of the joining point and the end point can help distinguish the tab and the defect area, reduce the possibility of misjudgment, and improve the accuracy of defect detection; subtracting the original skeleton area from the area where the joining point and the end point are located can remove the interference area around the joining point and the end point, making the subsequent line segmentation more accurate, and the image after the area difference highlights the main features of the defect, which is convenient for subsequent line segmentation and defect judgment; through line segmentation, it is helpful to perform slope comparison more accurately in the future, thereby improving the accuracy of tab defect detection.

[0018] Furthermore, determining the defect detection status of the tab to be inspected includes: obtaining the line segment slope of each line segment, and comparing the line segment slope with the slope of the fitted straight line; if the difference between the slope of any line segment and the slope of the fitted straight line is greater than a set threshold, it is determined that the tab to be inspected has a defect; otherwise, it is determined that the tab to be inspected does not have a defect.

[0019] In the above technical solution, the image after regional difference is segmented into lines, and the slope of the segmented line segment is compared with the slope of the previously fitted straight line, so as to realize the automatic detection of tab defects and improve the detection efficiency and accuracy; by comparing the slopes of the line segments, it is possible to accurately determine which line segments are the lines where the tab defects are located and which line segments are the normal parts of the tab, thereby reducing the subjectivity and errors of manual judgment.

[0020] Furthermore, based on the same concept, the present application also provides a tab defect detection system, including: a fitting module, used to obtain a detection image of the tab to be detected, and obtain a fitting straight line based on the detection image and the caliper area; an analysis module, used to perform skeleton area subtraction based on the detection image, and divide the detection image after the skeleton area subtraction into a number of line segments; and a detection module, used to compare each line segment with the fitting straight line respectively, so as to determine the defect detection status of the tab to be detected based on the comparison results.

[0021] In the above technical solution, the tab defect detection is realized during the process of measuring the tab by the caliper tool, without the need for additional separate defect detection. To a certain extent, the efficiency of tab defect detection can be improved. At the same time, defect judgment is performed by fitting a straight line, which also improves the detection accuracy.

[0022] Furthermore, the system further includes: a setting module for presetting detection parameters.

[0023] In the above technical solution, reasonable parameter settings can improve the detection accuracy, and the parameters can be adjusted according to actual application conditions, so that the tab defect detection system can be applied to tab detection under more conditions.

[0024] Furthermore, based on the same concept, the present application also provides a computer-readable storage medium, which is used to store a computer program, and the computer program is used to execute the tab defect detection method.

[0025] Furthermore, based on the same concept, the present application also provides a computer device, including a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the tab defect detection method.

[0026] Compared with the prior art, the present invention has the following advantages: This application innovatively utilizes a caliper tool for tab defect detection, cleverly utilizing various caliper tool parameters during the measurement process, eliminating the need for separate defect detection methods. This integrated design significantly accelerates tab defect detection efficiency and avoids the time loss associated with traditional multi-step testing. Furthermore, by comparing fitted straight lines with line segments, the detection process becomes simpler and more direct. This simple and efficient detection method, without the need for complex algorithms and processes, further improves the overall efficiency of tab defect detection and saves significant time and cost for quality control during the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1This is a flow chart of the tab defect detection method described in this application.

[0028] Figure 2 This is a schematic diagram of the drawing caliper tool described in this application.

[0029] Figure 3 This is a schematic diagram of the fitting points described in this application.

[0030] Figure 4 This is a schematic diagram of the fitted straight line described in this application.

[0031] Figure 5 This is a schematic diagram of the tab edge image after edge detection as described in this application.

[0032] Figure 6 This is a schematic diagram of the grayscale image of the tab after grayscale processing as described in this application.

[0033] Figure 7 This is a schematic diagram of the skeleton region image after skeleton extraction described in this application.

[0034] Figure 8 This is a schematic diagram of the joining and ending points described in this application.

[0035] Figure 9 This is a schematic diagram of a regional difference image after the regional difference described in this application.

[0036] Figure 10 Schematic diagram of several segmented line segments described in this application.

[0037] Figure 11 This is a schematic diagram of line segments with large slope differences as described in this application.

[0038] Figure 12 This is an image diagram showing that the tab described in this application does not have defects.

[0039] Figure 13 This is a framework diagram of the tab defect detection system described in this application. DETAILED DESCRIPTION

[0040] The following is a further detailed description of a tab defect detection method, system, storage medium and device of the present application in conjunction with specific embodiments and drawings.

[0041] See Figure 1 , the present application provides a tab defect detection method, comprising the following steps S100-S300.

[0042] Step S100: obtaining a detection image of the tab to be detected, and obtaining a fitting straight line according to the detection image and the caliper area.

[0043] Step S200: performing skeleton region subtraction based on the detection image, and dividing the detection image after the skeleton region subtraction into a plurality of line segments.

[0044] Step S300: Compare each line segment with the fitted straight line to determine the defect detection status of the tab to be inspected based on the comparison result.

[0045] In some embodiments, a caliper tool is drawn on the detection image, and fitting points appearing on the edge are searched on the detection image based on the drawn caliper area. Then, a straight line is fitted based on several fitting points by the least squares method to obtain a fitted straight line. The detection image is further subjected to defect detection, which includes at least edge detection, image grayscale analysis, skeleton extraction, junction point and end point extraction, area difference and line segmentation, and several line segments of the edge of the tab are obtained. The slope of each line segment is further used to determine whether the current tab has a defect. If the slope of the line segment is significantly different from the slope of the fitted straight line, it is determined that the tab has a defect. Otherwise, it is determined that no defect exists.

[0046] Next, the steps S100-S300 are described in detail.

[0047] Before acquiring the detection image in step S100 , the process includes presetting detection parameters, wherein the detection parameters include at least the number of calipers, the size of the calipers, the search direction, and the image grayscale value.

[0048] In some embodiments, before measuring the length and width of a tab, technicians need to set the caliper tool parameters, as well as parameters for subsequent analysis. For example, the number of calipers should be set to 15, each caliper size should be set to 2 mm long and 0.5 mm wide, the search direction should be set to vertical (because the tab edge is more distinct in the vertical direction), and the image grayscale value should be set between 80 and 120.

[0049] It should be noted that, in actual testing, technicians can set the testing parameters to other values ​​according to actual application requirements, and are not limited to this.

[0050] In the above technical solution, the setting parameters can be adjusted according to the specific characteristics of the tab and the actual situation of the image, so that the tab defect detection method can adapt to tabs with different lighting conditions, materials and surface conditions; at the same time, reasonable parameter settings can improve the accuracy of subsequent edge detection and reduce the possibility of false detection and missed detection; for example, by adjusting the number and size of calipers, the characteristics of the tab edge can be captured more finely.

[0051] Furthermore, obtaining the fitting straight line in step S100 includes: setting a caliper area on the detection image based on the number and size of the calipers; based on the caliper area, finding the fitting points on the detection image according to the search direction; and obtaining the fitting straight line based on the fitting points by using the least squares method.

[0052] In some embodiments, the tab is placed on a detection platform, and a high-precision visual inspection device is used to capture an image of the tab (i.e., the detection image). Then, based on the size of the tab, the edge position to be detected, and the pre-set number and size of calipers, a caliper tool (e.g., a caliper tool) is drawn on the left and / or right side of the tab. Figure 2 Then the visual inspection equipment automatically generates fitting points on the edge of the tab to be found (as shown in Figure 3 As shown in the figure, these fitting points are obtained by analyzing the image in the caliper area. These fitting points can accurately reflect the general outline of the edge of the tab and provide reliable data for subsequent straight line fitting. The least squares method is further used to process the generated fitting points and fit a straight line (as shown in the figure). Figure 4 As shown), this straight line accurately represents the edge position of the left (or right) side of the tab.

[0053] In the above technical solution, by drawing a caliper area on the detection image of the tab to be detected, the starting area where the edge needs to be found can be accurately located, providing a clear starting point for subsequent edge detection, reducing unnecessary image analysis range, and improving detection efficiency; the caliper area is set based on the number of calipers and the size of the caliper, so that the range of the caliper area is more accurate; in addition, the fitting point is a simplified representation of the edge features of the tab. By generating the fitting point, the complex edge information can be converted into a discrete point set, which is convenient for subsequent straight line fitting processing. At the same time, the fitting point can highlight the main features of the tab edge, reduce the influence of noise and other interference factors, and make the subsequent edge detection more accurate; further, the fitting point is processed using the least squares method to fit a straight line, which can quantify the position and direction information of the tab edge, which is convenient for subsequent analysis and judgment.

[0054] Among them, the least squares method is a commonly used fitting method with good stability and anti-interference ability. It can accurately fit the edge straight line of the tab in the presence of certain noise.

[0055] Furthermore, before performing the skeleton area subtraction in step S200, the following steps are included: performing edge detection on the detection image based on the caliper area to obtain a tab edge image; performing grayscale processing on the tab edge image according to the image grayscale value to obtain a tab grayscale image (such as Figure 6 as shown); and, performing skeleton extraction based on the tab grayscale image to obtain a skeleton area image.

[0056] In some embodiments, edge detection is performed within the drawn caliper area, such as using the Canny algorithm, so that the tab edge is clearly discernible. By setting an appropriate threshold, the algorithm can effectively filter out noise and retain only the true tab edge (e.g., Figure 5 As shown in the figure). The image grayscale analysis is then performed using the set grayscale value to calculate the grayscale value of each pixel in the tab edge image. For example, it is found that the grayscale values ​​of the main part of the tab are mostly concentrated between 90-110, while the grayscale values ​​of areas where foreign matter may exist will deviate from this range. For example, in one tab sample, a grayscale value of 150 was found in one area, which is significantly higher than the normal range. The image after grayscale thresholding is further subjected to skeleton extraction. After skeleton extraction of the tab image, the originally thick edge lines are refined into single-pixel wide skeleton lines, as shown in the figure. Figure 7 As shown in the figure, the skeleton line obtained after skeleton extraction clearly shows the general outline of the tab.

[0057] In the above technical solution, edge detection of the tab is performed in the caliper area, which can highlight the edge features of the tab, so that subsequent analysis can focus more on the edge area of ​​the tab and reduce interference from other areas; at the same time, the result of edge detection is the basis for subsequent image grayscale analysis, skeleton extraction and other processing. Accurate edge detection can improve the accuracy of the entire foreign body detection process.

[0058] Furthermore, by performing image grayscale processing using the image grayscale value set in the set detection parameters, the tab and defect area can be distinguished based on the grayscale value difference, and the defect area can be separated from the background; and through grayscale analysis, the detection image can be enhanced to improve the image contrast, making the defect more obvious and facilitating subsequent detection and analysis.

[0059] Furthermore, skeleton extraction is performed on the grayscale processed inspection image, which can simplify the complex image structure into a one-dimensional skeleton line, reduce the amount of data and improve processing efficiency; and the skeleton line retains the main shape information of the tabs and defects, can accurately reflect their structural characteristics, and provide a basis for the subsequent extraction of junction points and end points.

[0060] Furthermore, in step S200, a plurality of line segments are obtained, including: traversing the skeleton region image to obtain joining points and end points; performing skeleton region subtraction based on the joining points and end points to obtain a region subtraction image; and performing line segmentation based on the region subtraction image to obtain a plurality of line segments.

[0061] In some embodiments, the entire skeleton region is traversed to find the joining point and the ending point (e.g. Figure 8As shown in , a method based on neighborhood pixel analysis can be used; for example, for a pixel point, if there are 3 or more pixels in its 8-neighborhood that belong to the skeleton line, then the pixel point is determined to be a junction point, and the two endpoints of the skeleton line are the end points.

[0062] Furthermore, in a tab sample, the skeleton area and the areas where the junction and end points are located are marked using image processing software, and then a regional subtraction operation is performed; after the regional subtraction, the obtained image more clearly shows the parts of the tab edge except the junction and end points (such as Figure 9 Then the image after the region difference is segmented into different line segments (such as Figure 10 shown).

[0063] In the above technical solution, the joining point refers to the intersection of three or more skeleton lines, and the end point refers to the end point of the skeleton line; the extraction of the joining point and the end point can help distinguish the tab and the defect area, reduce the possibility of misjudgment, and improve the accuracy of defect detection; subtracting the original skeleton area from the area where the joining point and the end point are located can remove the interference area around the joining point and the end point, making the subsequent line segmentation more accurate, and the image after the area difference highlights the main features of the defect, which is convenient for subsequent line segmentation and defect judgment; through line segmentation, it is helpful to perform slope comparison more accurately in the future, thereby improving the accuracy of tab defect detection.

[0064] Furthermore, determining the defect detection status of the tab to be inspected in step S300 includes: obtaining the line segment slope of each line segment, and comparing the line segment slope with the slope of the fitted straight line; if the difference between the slope of any line segment and the slope of the fitted straight line is greater than a set threshold, it is determined that the tab to be inspected has a defect; otherwise, it is determined that the tab to be inspected does not have a defect.

[0065] In some embodiments, for example, in a tab sample, after line segmentation, a total of 10 line segments are obtained; then, by calculating the slope of each line segment and comparing it with the slope of the previously fitted line, assuming that the slope of the fitted line is 1.2, among these 10 line segments, the slopes of 2 line segments are significantly different from 1.2, namely 2.5 and 0.3, respectively. The difference between the two exceeds the set threshold, and it is determined that the tab has a defect. Among them, the line segments with large slope differences are as follows: Figure 11 shown.

[0066] In other embodiments, if the difference between the slope of all line segments and the slope of the fitted straight line is within a set threshold, the tab is determined to be normal. The normal tab image is as follows: Figure 12 shown.

[0067] It should be noted that the threshold is set by technical personnel according to product requirements and is not restricted here.

[0068] In the above technical solution, the image after regional difference is segmented into lines, and the slope of the segmented line segment is compared with the slope of the previously fitted straight line, so as to realize the automatic detection of tab defects and improve the detection efficiency and accuracy; by comparing the slopes of the line segments, it is possible to accurately determine which line segments are the lines where the tab defects are located and which line segments are the normal parts of the tab, thereby reducing the subjectivity and errors of manual judgment.

[0069] To sum up, the present application realizes the detection of tab defects when using a caliper tool for measurement, utilizes the parameters in the caliper tool, and does not need to use a separate defect detection method for detection, thereby speeding up the detection efficiency of tab defects; at the same time, the fitting straight line and line segment are used for comparison, the operation process is simple, and the detection efficiency of tab defects is further improved.

[0070] Further, based on the same concept, see Figure 13 The present application also provides a tab defect detection system, comprising: a fitting module for acquiring a detection image of the tab to be detected, and obtaining a fitting straight line based on the detection image and the caliper area; an analysis module for performing a skeleton area subtraction based on the detection image, and dividing the detection image after the skeleton area subtraction into a plurality of line segments; and a detection module for comparing each line segment with the fitting straight line respectively, so as to determine the defect detection status of the tab to be detected based on the comparison result.

[0071] Since the tab defect detection system and the tab defect detection method are based on the same concept, the specific implementation of the system is the same as that of the tab defect detection method, and will not be described in detail here.

[0072] In the above technical solution, the tab defect detection is realized during the process of measuring the tab by the caliper tool, without the need for additional separate defect detection. To a certain extent, the efficiency of tab defect detection can be improved. At the same time, defect judgment is performed by fitting a straight line, which also improves the detection accuracy.

[0073] Furthermore, the system further includes: a setting module for presetting detection parameters.

[0074] In the above technical solution, reasonable parameter settings can improve the detection accuracy, and the parameters can be adjusted according to actual application conditions, so that the tab defect detection system can be applied to tab detection under more conditions.

[0075] Furthermore, based on the same concept, the present application also provides a computer-readable storage medium, which is used to store a computer program, and the computer program is used to execute the tab defect detection method.

[0076] In some embodiments, the storage medium stores a number of computer programs for enabling a computer device to execute all or part of the steps of the method described in each embodiment of the present application; the storage medium may include a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media that can store program codes.

[0077] Furthermore, based on the same concept, the present application also provides a computer device, including a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, the at least one program, the code set or instruction set is loaded and executed by the processor to implement the tab defect detection method.

[0078] In some embodiments, the memory and the processor are interconnected via a bus; the processor may be one or more CPUs. When the processor is a CPU, the CPU may be a single-core CPU or a multi-core CPU. The processor is used to control various functional modules of the computer device and process signals.

[0079] The memory includes but is not limited to RAM (Random Access Memory), ROM (Read-Only Memory), EPROM (Erasable Programmable Read-Only Memory), and CD-ROM (Compact Disc Read-Only Memory). The memory is used to store computer programs, operating systems, various applications and data, such as storing computer programs for implementing the tab defect detection method.

[0080] Although example embodiments have been described herein with reference to the accompanying drawings, it should be understood that the above example embodiments are merely illustrative and are not intended to limit the scope of the present application. Various changes and modifications may be made therein by those skilled in the art without departing from the scope and spirit of the present application. All such changes and modifications are intended to be included within the scope of the present application as required by the appended claims.

[0081] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units described is merely a logical function division. In actual implementation, other division methods may be used, such as combining or integrating multiple units or components into another device, or ignoring or not performing some features.

[0083] The various component embodiments of the present application can be implemented in hardware, or in a software module running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some modules according to the embodiments of the present application. The application can also be implemented as a part or all of a device program (e.g., a computer program and a computer program product) for performing the method described herein. Such a program implementing the present application can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0084] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0085] Although the present application is described in conjunction with the above specific embodiments, it is obvious that those skilled in the art can make many substitutions, modifications and variations based on the above content. Therefore, all such substitutions, improvements and variations are included in the spirit and scope of the appended claims.

Claims

1. A method for detecting tab defects, characterized in that: include: Acquire a detection image of the tab to be detected, and obtain a fitting straight line based on the detection image and the caliper area; Performing skeleton region subtraction based on the detection image, and dividing the detection image after the skeleton region subtraction into a plurality of line segments; Furthermore, each line segment is compared with the fitting straight line to determine the defect detection status of the tab to be inspected according to the comparison result.

2. The tab defect detection method according to claim 1, wherein: Before acquiring the detection image, include: Detection parameters are pre-set; wherein the detection parameters include at least the number of calipers, the size of the calipers, the search direction and the image grayscale value.

3. The tab defect detection method according to claim 2, characterized in that: The obtaining of the fitted straight line comprises: Setting a caliper area on the inspection image based on the number and size of the calipers; Based on the caliper area, finding a fitting point on the detection image according to the search direction; And, obtaining a fitting straight line based on the fitting points by a least square method.

4. The tab defect detection method according to claim 3, characterized in that: Before performing subtraction on the skeleton area, including: Based on the caliper area, edge detection is performed on the detection image to obtain a tab edge image; Performing grayscale processing on the tab edge image according to the image grayscale value to obtain a tab grayscale image; Furthermore, skeleton extraction is performed based on the tab grayscale image to obtain a skeleton region image.

5. The tab defect detection method according to claim 4, characterized in that: Get several line segments, including: Traversing the skeleton region image to obtain joining points and end points; Performing skeleton region subtraction based on the joining point and the end point to obtain a region subtraction image; Furthermore, line segmentation is performed based on a difference image of the region to obtain a plurality of line segments.

6. The tab defect detection method according to claim 5, characterized in that: Determining the defect detection status of the tab to be inspected includes: Obtaining the line segment slope of each line segment, and comparing each line segment slope with the slope of the fitted straight line; If the difference between the slope of any line segment and the slope of the fitting straight line is greater than a set threshold, it is determined that the tab to be detected has a defect; otherwise, it is determined that the tab to be detected does not have a defect.

7. A system using the tab defect detection method according to any one of claims 1 to 6, characterized in that: include: A fitting module, configured to obtain a detection image of the tab to be detected, and obtain a fitting straight line based on the detection image and the caliper area; An analysis module, configured to perform skeleton region subtraction based on the detection image, and segment the detection image after the skeleton region subtraction into a plurality of line segments; And, a detection module is used to compare each line segment with the fitting straight line respectively, so as to determine the defect detection status of the tab to be detected according to the comparison result.

8. The system according to claim 7, characterized in that Also includes: The setting module is used to pre-set detection parameters.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium is used to store a computer program, and the computer program is used to execute the tab defect detection method according to any one of claims 1 to 6.

10. A computer device, characterized in that: It includes a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set or instruction set, and the at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the tab defect detection method according to any one of claims 1 to 6.

Images