Circuit board drilling detection method, intelligent terminal and computer readable storage medium

Abstract

The invention discloses a circuit board drilling detection method, an intelligent terminal and a computer readable storage medium. The circuit board drilling detection method comprises the steps that a circuit board image is acquired; wherein the circuit board image comprises a to-be-measured aperture area; extracting a candidate aperture region by using the brightness feature of the aperture region to be measured; carrying out image correction and supplementation on the candidate aperture region according to the geometrical characteristics and morphological optimization processing of the candidate aperture region to obtain a dislocation step region; and carrying out position matching operation on the dislocation step area to obtain characteristic parameters of the dislocation step area. According to the scheme, the circuit board drilling detection method can effectively realize high-precision and stable high-thickness-diameter-ratio micro-hole dislocation step automatic measurement through multi-feature fusion and optimization strategies, the detection automation level is improved, the manual intervention requirement is reduced, and the detection efficiency is improved. The detection efficiency and quality in the field of PCB manufacturing and precision machining are greatly improved, and an efficient and reliable solution is provided for industrial intelligent detection.

Description

Technical Field

[0001] The present application relates to the field of data management technology, and in particular to a circuit board drilling detection method, an intelligent terminal, and a computer-readable storage medium. Background Art

[0002] In the PCB (Printed Circuit Board) manufacturing process, drilling is a critical step, especially when drilling holes in PCB panels with a high aspect ratio (board thickness to hole diameter ratio). However, the accuracy of the drill directly affects the formation of the step area within the hole, which in turn directly affects the performance and quality of the PCB. Therefore, it is usually inevitable to measure the misaligned step area within the hole during production line quality inspection.

[0003] However, traditional detection methods mainly rely on manual visual inspection or single-shot image processing technology, and have the following problems: single-shot extraction is incomplete. When only the circumscribed circle is extracted through the translucent white area in the hole, uneven lighting, noise interference or complex structure in the hole may lead to incomplete extraction of the step area; the misrecognition rate is high. A single extraction can easily misjudge other bright areas in the hole (such as reflections) as the aperture area, affecting the measurement accuracy; the adaptability is poor, and it is difficult to meet the detection needs of complex hole environments. Summary of the Invention

[0004] The main technical problem solved by this application is to provide a circuit board drilling detection method, an intelligent terminal and a computer-readable storage medium to solve the problems of incomplete single extraction, high misrecognition rate and poor adaptability in the circuit board drilling detection method in the prior art.

[0005] In order to solve the above problems, the first aspect of the present application provides a circuit board drilling detection method, wherein the circuit board drilling detection method includes: acquiring a circuit board image; extracting a candidate aperture area using the brightness characteristics of the aperture area to be measured; performing image correction and supplementation on the candidate aperture area based on the geometric characteristics and morphological optimization processing of the candidate aperture area to obtain a misaligned step area; and performing a position matching operation on the misaligned step area to obtain characteristic parameters of the misaligned step area.

[0006] Among them, after the step of performing image correction and supplement on the candidate aperture area according to the geometric features and morphological optimization processing of the candidate aperture area to obtain the dislocated step area, and before the step of performing position matching operation on the dislocated step area to obtain the characteristic parameters of the dislocated step area, it also includes: using the area, shape rules and edge convexity of the dislocated step area to remove noise; the step of performing position matching operation on the dislocated step area to obtain the dislocated step area and the characteristic parameters of the dislocated step area includes: performing position matching operation on the dislocated step area after noise removal to obtain the characteristic parameters of the dislocated step area.

[0007] Among them, the step of extracting candidate aperture areas using the brightness characteristics of the aperture area to be measured includes: preprocessing the circuit board image to extract a first high-brightness area whose brightness exceeds a first brightness threshold; performing shape feature operation on the first high-brightness area to extract candidate aperture areas whose characteristic area is within the first area threshold range.

[0008] The step of preprocessing the circuit board image includes: performing grayscale scaling, contrast enhancement, mean filtering, and dynamic threshold segmentation on the circuit board image in sequence.

[0009] Among them, the steps of performing shape feature operations on the first high-brightness area include: performing closing operations, connected area analysis, filling processing, and area screening on the first high-brightness area in sequence to obtain candidate filling areas; generating a minimum circumscribed circle corresponding to the candidate filling area; and measuring the area of ​​the minimum circumscribed circle to obtain a characteristic area.

[0010] Among them, the steps of performing image correction and supplement on the candidate aperture area according to the geometric features and morphological optimization processing of the candidate aperture area to obtain the dislocated step area include: performing a feature extraction operation on the candidate aperture area to extract the candidate step area whose characteristic area is within the second area threshold range; performing a brightness feature extraction operation on the candidate step area to obtain the highlight area in the hole; performing a second feature extraction operation on the highlight area in the hole to extract the optimized aperture area whose characteristic area is within the third area threshold range; performing a third feature extraction operation on the optimized aperture area to extract the dislocated step area whose characteristic area is within the fourth area threshold range and whose characteristic convexity is within the set convexity threshold range.

[0011] Among them, the step of performing a feature extraction operation on the candidate aperture area to extract a candidate step area whose characteristic area is within the second area threshold range includes: performing grayscale scaling and enhancement processing on the circuit board image in sequence to obtain an enhanced image; using the candidate aperture area to segment the enhanced image to obtain a restricted aperture area; performing threshold segmentation on the restricted aperture area to extract a second high-brightness area whose brightness exceeds the second brightness threshold; performing an opening operation on the second high-brightness area to obtain a noise reduction area; and performing area measurement on the noise reduction area to extract a candidate step area whose characteristic area is within the second area threshold range.

[0012] The step of performing brightness feature extraction on the candidate step region to obtain the highlight region in the hole includes: performing mean filtering, threshold segmentation, and shape screening on the candidate step region in sequence to obtain the highlight region in the hole.

[0013] Among them, the step of performing a secondary feature extraction operation on the highlighted area in the hole to extract the optimized aperture area whose feature area is within the third area threshold range includes: performing region merging and closing operations on the highlighted area in the hole in sequence, and generating a minimum circumscribed circle to obtain the optimized aperture area.

[0014] Among them, the step of performing three feature extraction operations on the optimized aperture area to extract the dislocated step area whose characteristic area is within the fourth area threshold range and whose characteristic convexity is within the set convexity threshold range includes: using the optimized aperture area to segment the enhanced image to obtain a restricted step area; extracting the dislocated step area according to the characteristic area, pixel length and width, and characteristic convexity of the restricted step area.

[0015] Among them, the steps of performing position matching operation on the dislocated step area to obtain the characteristic parameters of the dislocated step area include: calculating the center offset distance between the dislocated step area and the optimized aperture area; calculating the intersection area between the dislocated step area and the optimized aperture area; and calculating the area ratio of the intersection area in the optimized aperture area.

[0016] Among them, after the step of calculating the center offset distance between the misaligned step area and the optimized aperture area, and before the step of calculating the intersection area between the misaligned step area and the optimized aperture area, it also includes: detecting whether the center offset distance is greater than the set ratio of the optimized aperture area radius; if the center offset distance is greater than the set ratio of the optimized aperture area radius, removing the corresponding misaligned step area.

[0017] Among them, after the step of performing position matching operation on the dislocated step area to obtain the characteristic parameters of the dislocated step area, it also includes: detecting whether the characteristic parameters are within a set threshold range; if the characteristic parameters are not within the set threshold range, determining that the circuit board drilling corresponding to the circuit board image is unqualified.

[0018] In order to solve the above problems, the second aspect of the present application provides an intelligent terminal, wherein the intelligent terminal includes a memory and a processor coupled to each other, the memory stores program data; the processor is used to execute the program data to implement the circuit board drilling detection method as described in any one of the above items.

[0019] In order to solve the above problems, the third aspect of the present application provides a computer-readable storage medium on which program instructions are stored. When the program instructions are executed by a processor, any of the above circuit board drilling detection methods is implemented.

[0020] The beneficial effects of the present invention are as follows: different from the prior art, the circuit board drilling detection method provided by the present application obtains a circuit board image, extracts a candidate aperture area by utilizing the brightness characteristics of the aperture area to be measured, and performs image correction and supplement on the candidate aperture area according to the geometric characteristics and morphological optimization processing of the candidate aperture area to obtain a dislocated step area, and performs position matching operation on the dislocated step area to obtain the characteristic parameters of the dislocated step area, thereby effectively realizing high-precision and stable high-aspect-ratio micro-hole dislocated step measurement through multi-feature fusion and optimization strategy, and improving the level of detection automation, reducing the need for manual intervention, greatly improving the detection efficiency and quality in the field of PCB manufacturing and precision processing, and providing an efficient and reliable solution for industrial intelligent detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flow chart of the first embodiment of the circuit board drilling detection method of the present application;

[0022] Figure 2 This is a structural diagram of an embodiment of circuit board image acquisition;

[0023] Figure 3 yes Figure 1 A schematic diagram of a flow chart of an embodiment of S12;

[0024] Figure 4 yes Figure 3 A flow chart of an embodiment of S122;

[0025] Figure 5 yes Figure 1 A schematic diagram of a flow chart of an embodiment of S13;

[0026] Figure 6 yes Figure 5 A schematic diagram of a flow chart of an embodiment of S131;

[0027] Figure 7 yes Figure 5 A schematic diagram of a flow chart of an embodiment of S134;

[0028] Figure 8 This is a flow chart of a second embodiment of the circuit board drilling detection method of the present application;

[0029] Figure 9 This is a flow chart of a third embodiment of the circuit board drilling detection method of the present application;

[0030] Figure 10 This is a flow chart of a fourth embodiment of the circuit board drilling detection method of the present application;

[0031] Figure 11a-Figure 11z and Figure 11a1This is a structural diagram of an embodiment of S41-S418;

[0032] Figure 12 This is a schematic diagram of a framework of an embodiment of the smart terminal of the present application;

[0033] Figure 13 It is a schematic diagram of a framework of an embodiment of the computer-readable storage medium of the present application. DETAILED DESCRIPTION

[0034] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0035] The terms "first", "second" and "third" in this application are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, a feature defined as "first", "second" and "third" may explicitly or implicitly include at least one of such features. In the description of this application, "multiple" means at least two, for example, two, three, etc., unless otherwise clearly and specifically defined. All directional indications in the embodiments of this application (such as up, down, left, right, front, back...) are only used to explain the relative positional relationship, movement, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0036] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0037] The present application is described in detail below with reference to the accompanying drawings and implementation methods.

[0038] See also Figure 1 , Figure 1 It is a flow chart of the first embodiment of the circuit board drilling detection method of the present application.

[0039] Specifically, the following steps may be included:

[0040] S11: Acquire a circuit board image.

[0041] It can be understood that the circuit board drilling detection method in this embodiment can be specifically understood as running on any reasonable terminal device with image processing and program operation functions such as a computer, server, industrial camera or smart phone, or a software platform in a circuit board processing equipment, by obtaining the image of the circuit board after docking drilling and corresponding image processing and program operation detection to determine whether the docking drilling of the circuit board is qualified.

[0042] It's worth noting that butt drilling is a drilling process commonly used for drilling holes in PCBs with high aspect ratios. Using a long-edged drill bit in these situations can easily lead to problems like short blades and runout, potentially resulting in scrapped PCBs. Therefore, a double-drilling method is required. This involves drilling holes from opposite sides of the PCB, ultimately butting the holes together in the center. The accuracy of the butt drill directly affects the formation of the step area within the hole.

[0043] In addition, a high aspect ratio refers to the ratio of a PCB's thickness to its aperture diameter. High aspect ratio boards are typically thicker, such as 3mm-5mm, and have smaller apertures, such as 0.13mm or 0.11mm, making them more difficult to process.

[0044] Specifically, if Figure 2 As shown, Figure 2 This is a structural diagram of an embodiment of circuit board image acquisition. The software platform for implementing circuit board drilling detection can be specifically integrated into an industrial camera, or communicated with it to receive the image of the circuit board after docking drilling taken by the industrial camera, which includes the aperture area to be measured.

[0045] In one embodiment, the industrial camera may specifically include a camera lens and a light source to capture the object to be measured, i.e., the drilled circuit board, from opposite sides thereof at a first length α and a second length β, respectively, to obtain a circuit board image with sufficient resolution and contrast.

[0046] In other embodiments, the industrial camera may not include a light source, or may be replaced by an imaging module integrated into the circuit board processing equipment, which is not limited in this application.

[0047] Optionally, the first length α can be specifically 100-120 mm (millimeter); the second length β can be specifically 70-90 mm (millimeter), and the first length α and the second length β are preferably 110 mm and 80 mm respectively, which is not limited in this application.

[0048] S12: Extracting candidate aperture regions using the brightness features of the aperture region to be measured.

[0049] By analyzing the brightness (grayscale) and brightness distribution of each pixel in the image, we can identify areas that may represent the aperture, namely candidate aperture regions. Typically, the aperture region to be measured will exhibit different brightness characteristics in the image, such as darker or brighter areas. Therefore, we can use edge detection algorithms and image segmentation techniques (such as threshold segmentation and region growing) to eliminate noise interference in the aperture region to be measured from the image and preliminarily extract candidate areas that may contain the aperture, namely candidate aperture regions.

[0050] It is worth noting that the aperture area refers to the drilling area in the PCB board, which is usually circular or elliptical.

[0051] In addition, noise interference refers to any unwanted signal that exists in the image and is unrelated to the image content. Such noise will affect the acquisition and processing of image information, thereby reducing the quality of image recognition.

[0052] Brightness distribution: The statistical distribution of pixel brightness within a certain area of ​​an image, used to analyze the uniformity and characteristics of the area.

[0053] S13: performing image correction and supplementation on the candidate aperture region according to the geometric features and morphological optimization processing of the candidate aperture region to obtain a dislocated step region.

[0054] Furthermore, the extracted candidate aperture regions are subjected to geometric feature analysis, including parameters such as shape, size, and roundness. These features help to further screen out the regions that truly represent the aperture and exclude noise or non-target regions.

[0055] Morphological operations (such as dilation, erosion, opening, closing, etc.) are applied to optimize the candidate regions to fill small gaps, remove isolated small points, smooth boundaries, etc., so as to more accurately define the true contour of the aperture.

[0056] Therefore, we can identify areas where misalignment steps may exist based on the geometric characteristics of the aperture area and the PCB design specifications. Misalignment steps are usually caused by mismatches between different layers due to errors in the manufacturing process.

[0057] By combining the geometric features of the aperture area (such as the position of the circumscribed circle and the brightness distribution) and morphological optimization (closing operation, edge analysis, etc.), the candidate aperture area extracted for the first time can be effectively corrected and supplemented to identify the misplaced step area and ensure the integrity of the misplaced step area.

[0058] It is worth noting that the misaligned step area refers to the step-shaped defect area formed in the aperture area due to drill bit deflection and alignment error during the drilling process of the PCB butt drill.

[0059] Morphological operation: A mathematical operation method in image processing, mainly used for operations such as removing noise, filling holes, and extracting edges.

[0060] Closing operation: A morphological operation that first dilates the image and then erodes it to fill small holes and connect adjacent areas.

[0061] Opening operation: A morphological operation that first erodes the image and then dilates it to remove small noise and separate adjacent areas.

[0062] S14: performing a position matching operation on the dislocated step region to obtain characteristic parameters of the dislocated step region.

[0063] A position matching operation is performed on the identified misaligned step area to determine its precise position, relative deviation and other characteristic parameters.

[0064] Optionally, the characteristic parameters may specifically include one or more of any reasonable parameters such as the image coordinate position of the misaligned step area, the actual size of the misaligned step, the offset between the misaligned step area and the aperture area, the area ratio of the misaligned step area in the aperture area, etc., so as to determine whether the circuit board drilling corresponding to the circuit board image is qualified through the characteristic parameters. This application does not limit this.

[0065] The above solution, through the use of multi-feature fusion technology, combines the brightness, geometric, and morphological features of the aperture area to be measured to ensure the complete extraction of candidate step areas, reduce missed detections and false detections, thereby improving measurement accuracy and lowering the false recognition rate. Through secondary extraction optimization, the problem of missing step areas caused by single extraction is corrected, improving the accuracy and stability of the measurement data. By acquiring images captured in real time by industrial cameras and combining them with intelligent vision algorithms, step area detection is automatically completed, replacing manual visual inspection and improving detection efficiency. It can also automatically calculate the characteristic parameters of the misaligned step area, achieving standardized measurement, avoiding human error, and improving production consistency, thereby effectively improving the degree of detection automation and reducing human intervention. The use of a vision-based detection method eliminates the need for expensive physical measurement equipment, reduces implementation costs, and reduces equipment maintenance requirements, thereby improving production efficiency. Therefore, it breaks through the limitations of traditional detection methods and achieves high-precision, automated measurement of misaligned steps in high-aspect-ratio micro-holes, significantly improving detection efficiency and quality in PCB manufacturing and precision machining, and providing an efficient and reliable solution for industrial intelligent detection.

[0066] See also Figure 3 , Figure 3 yes Figure 1 Flowchart of S12 in an embodiment. In one embodiment, the circuit board drilling detection method of the present application includes, in addition to the above S11-S14, further includes some more specific steps. Specifically, the above S12 may further include the following steps:

[0067] S121: Preprocessing the circuit board image to extract a first high-brightness area whose brightness exceeds a first brightness threshold.

[0068] It is understandable that the aperture area to be measured usually exhibits different brightness characteristics in the circuit board image, such as darker or brighter areas, so a brightness threshold, called the "first brightness threshold", can be set to distinguish high-brightness areas from other parts.

[0069] Specifically, a brightness segmentation algorithm is applied, such as one or more of any reasonable processing methods such as global threshold segmentation, adaptive threshold segmentation, global threshold segmentation, adaptive threshold segmentation, morphological operations, etc., to pre-process the circuit board image to extract pixels in the image whose brightness values ​​exceed a first brightness threshold and determine them as a first high-brightness area.

[0070] S122: performing shape feature operation on the first high-brightness area to extract candidate aperture areas whose feature areas are within a first area threshold range.

[0071] Perform shape feature operations on the first high-brightness region, such as performing connected region analysis on the first high-brightness region obtained through brightness segmentation, to identify all independent high-brightness regions. Each connected region represents a possible aperture or other highlight feature; calculate the area of ​​each connected region (i.e., the number of pixels it contains); set an area threshold range based on the actual aperture size range, called the "first area threshold range"; compare the area of ​​each connected region with the set area threshold range, and retain regions with feature areas within the first area threshold range as candidate aperture regions.

[0072] It is worth noting that the first area threshold range is specifically a threshold range that is reasonably set in the image processing process of actual drilling detection based on the information data that has been recorded, measured, and reasonably analyzed to screen out those that meet the conditions and meet the corresponding needs. The same applies to other threshold ranges mentioned in this article. They are specifically determined by the actual application scenarios and will not be repeated here.

[0073] Furthermore, in one embodiment, the above S121 may specifically include: performing grayscale scaling, contrast enhancement, mean filtering, and dynamic threshold segmentation on the circuit board image in sequence.

[0074] Specifically, the grayscale of the circuit board image is scaled to enhance the contrast, and the scaled circuit board image is mean filtered to reduce noise interference, and then the areas with higher brightness are extracted through dynamic threshold segmentation, that is, the first high-brightness areas whose brightness exceeds the first brightness threshold. These areas may be aperture areas.

[0075] It is worth mentioning that grayscale scaling refers to enhancing the contrast of an image by adjusting the range or distribution of the grayscale values ​​of the image to facilitate the detection of the target area.

[0076] Contrast enhancement, also known as contrast adjustment or contrast optimization, is an image processing technique that aims to make image details clearer and visually more vivid by increasing the brightness difference between bright and dark areas in the image.

[0077] Mean filtering is a typical linear filtering algorithm, which refers to giving a template to the target pixel in the image. The template includes the adjacent pixels around it (8 pixels around the target pixel as the center constitute a filtering template, that is, including the target pixel itself), and then using the average value of all pixels in the template to replace the original pixel value.

[0078] Dynamic threshold segmentation is an image segmentation method that uses dynamically changing thresholds to distinguish the target area from the background in an image.

[0079] See also Figure 4 , Figure 4 yes Figure 3In one embodiment, the circuit board drilling detection method of the present application includes, in addition to the above S121-S122, further includes some more specific steps. Specifically, in the above S122, the following steps may also be included:

[0080] S1221: performing closing operation, connected region analysis, filling processing, and area screening on the first high-brightness region in sequence to obtain a candidate filling region.

[0081] Specifically, a closing operation is performed on the first high-brightness area to reduce burrs and ensure the integrity of the aperture area in the image, and a connected region analysis is performed on the image area after the closing operation to obtain multiple connected regions, which are then filled to ensure the integrity of the region, and qualified regions are screened out as candidate filling regions based on their area.

[0082] S1222: Generate a minimum circumscribed circle corresponding to the candidate filling area.

[0083] Furthermore, a minimum circumscribed circle is generated for the selected candidate filling areas.

[0084] It is worth noting that the circumscribed circle refers to the smallest circular area that can completely surround a certain area, and is usually used to describe the geometric characteristics of the target area.

[0085] S1223: Calculate the area of ​​the minimum circumscribed circle to obtain a characteristic area.

[0086] Furthermore, the characteristic area of ​​the minimum circumscribed circle is measured and obtained, so that areas with characteristic areas within a first area threshold range can be screened out as candidate aperture areas.

[0087] See also Figure 5 , Figure 5 yes Figure 1 Specifically, in one embodiment, in the above S13, the following steps may be further included:

[0088] S131: performing a feature extraction operation on the candidate aperture region to extract a candidate step region whose feature area is within a second area threshold range.

[0089] Specifically, a feature extraction operation is performed on the candidate aperture regions, such as calculating the area (number of pixels) of all candidate aperture regions, and based on a set reasonable area range as the second area threshold, the candidate aperture regions with feature areas within the second area threshold are screened out as candidate step regions.

[0090] S132: Performing a brightness feature extraction operation on the candidate step region to obtain a highlight region within the hole.

[0091] Within each candidate step region, analyze the brightness (grayscale) of the pixels. Typically, there are bright areas inside the hole, which may be caused by reflections or other optical properties. Apply a brightness thresholding method (such as dynamic thresholding) to mark pixels with brightness above a certain threshold as bright areas. Local adaptive thresholding can be used to set a threshold for each candidate step region to adapt to different lighting conditions.

[0092] S133: performing a secondary feature extraction operation on the highlight area in the aperture to extract an optimized aperture area whose feature area is within a third area threshold range.

[0093] According to more refined design requirements, a new area threshold range is set, called the "third area threshold range", which is used to further screen the highlight area in the hole. For example, the highlight area in the hole whose characteristic area is within the third area threshold range is screened out as the optimized aperture area.

[0094] S134: performing three feature extraction operations on the optimized aperture area to extract a dislocated step area whose characteristic area is within a fourth area threshold range and whose characteristic convexity is within a set convexity threshold range.

[0095] According to more refined design requirements, a new area threshold range is set, called the "third area threshold range", to further screen the optimized aperture area. For example, the minimum area is 250 pixels and the maximum area is 550 pixels, so as to screen out the optimized aperture area whose characteristic area is within the fourth area threshold range, and further perform shape feature analysis on the screened optimized aperture area to calculate its convexity, that is, the ratio of the actual perimeter of the area to the perimeter of its minimum circumscribed convex polygon. The ideal aperture edge should have a higher convexity value. A reasonable convexity threshold range is set according to actual conditions (for example, the convexity is greater than 0.85). Combined with the fourth area threshold range and the set convexity threshold range, those optimized aperture areas whose area and convexity meet the requirements are screened out as the final dislocation step area.

[0096] This multi-level feature extraction and optimization process effectively improves the accuracy of identifying PCB apertures and their misaligned step areas. Multiple area threshold screening and shape feature analysis ensure that the final extracted area highly meets design requirements. Brightness and convexity features are further utilized to eliminate noise and other non-target areas, reducing the possibility of misjudgment. The entire process can be automated, reducing manual intervention and improving inspection efficiency and accuracy.

[0097] See also Figure 6 , Figure 6 yes Figure 5Specifically, in one embodiment, in the above S131, the following steps may be further included:

[0098] S1311: performing grayscale scaling and enhancement processing on the circuit board image in sequence to obtain an enhanced image.

[0099] Specifically, grayscale scaling and enhancement processing are performed on the circuit board image to highlight the step area in the hole to obtain an enhanced image.

[0100] S1312: Segment the enhanced image using the candidate aperture regions to obtain restricted aperture regions.

[0101] The enhanced image is cut using the candidate aperture region to obtain the restricted aperture region, so as to reduce the image domain and the image processing range to the restricted aperture region, thereby reducing the interference to irrelevant areas.

[0102] S1313: Perform threshold segmentation on the limited aperture area to extract a second high brightness area whose brightness exceeds a second brightness threshold.

[0103] Furthermore, threshold segmentation is performed on the cut-out limited aperture area to extract a second high brightness area whose brightness exceeds a second brightness threshold.

[0104] S1314: Perform an opening operation on the second high brightness area to obtain a noise reduction area.

[0105] An opening operation is performed on the second highest brightness area to remove small noise to obtain a noise reduction area.

[0106] S1315: performing area measurement on the noise reduction area to extract candidate step areas whose characteristic areas are within a second area threshold range.

[0107] The area of ​​the noise reduction region is measured to screen out qualified image regions according to the area of ​​the noise reduction region, that is, image regions whose characteristic areas are within the second area threshold range as candidate step regions.

[0108] Furthermore, in one embodiment, the above S132 may specifically include: performing mean filtering, threshold segmentation, and shape screening on the candidate step regions in sequence to obtain a highlight region in the hole.

[0109] Specifically, mean filtering is performed on the circuit board image to reduce noise interference; image areas with grayscale values ​​close to 255 are extracted through threshold segmentation, and the highlight area inside the aperture, i.e., the highlight area inside the hole, is screened out based on the area.

[0110] Furthermore, in one embodiment, the above S133 may specifically include: performing region merging and closing operations on the highlighted regions in the aperture in sequence, generating a minimum circumscribed circle to obtain an optimized aperture region.

[0111] Specifically, a set operation is performed on the highlight area in the hole and the candidate step area to obtain a merged area, a closing operation is performed on the merged area, and a very small gap between the second high brightness area and the candidate step area is connected to obtain a complete optimized aperture area.

[0112] See also Figure 7 , Figure 7 yes Figure 5 Specifically, in one embodiment, in the above S134, the following steps may be further included:

[0113] S1341: Segment the enhanced image using the optimized aperture region to obtain a restricted step region.

[0114] Specifically, the enhanced image is cut using the optimized aperture region, and the cut image region is again subjected to threshold segmentation to extract the restricted step region.

[0115] S1342: Extract the misaligned step region based on the characteristic area, pixel length and width, and characteristic convexity of the restricted step region.

[0116] Furthermore, the restricted step region is screened according to the characteristic area, pixel length and width, and characteristic convexity to generate the final image region as the dislocation step region.

[0117] In one embodiment, a restricted step area that meets any one or more conditions of the feature area being within a fourth area threshold range, the pixel length and width being within a set length and width threshold range, and the feature convexity being within a set convexity threshold range is used as a misaligned step area; and / or, the center offset distance between the restricted step area and the optimized aperture area is calculated. If the center offset distance exceeds 10% of the radius of the optimized aperture area, it is determined to be a misidentification, so as to remove the unidentified area, and the restricted step area whose center offset distance does not exceed 10% of the radius of the optimized aperture area is used as a misaligned step area. This application does not impose any restrictions on this.

[0118] It is worth noting that convexity refers to an indicator that describes the shape of a region. The closer the convexity value, that is, the characteristic convexity, is to 1, the more regular the shape of the region is.

[0119] See also Figure 8 , Figure 8 This is a flow chart of the second embodiment of the circuit board drilling detection method of the present application. The circuit board drilling detection method of this embodiment is Figure 1 A flowchart of a detailed embodiment of the circuit board drilling detection method in the embodiment includes the following steps:

[0120] S21: Acquire a circuit board image.

[0121] S22: Extracting candidate aperture regions using the brightness features of the aperture region to be measured.

[0122] S23: performing image correction and supplementation on the candidate aperture region according to the geometric features and morphological optimization processing of the candidate aperture region to obtain a dislocated step region.

[0123] Among them, S21, S22 and S23 are Figure 1 S11, S12 and S13 are the same, please refer to S11, S12 and S13 and their related text descriptions for details, which will not be repeated here.

[0124] S24: Noise removal is performed using the area, shape regularity, and edge convexity of the dislocated step region.

[0125] Specifically, by setting a reasonable area range as a threshold, the area of ​​all candidate step areas is calculated, and those areas whose areas exceed the preset threshold range are eliminated; the shape factor of each candidate step area is calculated. Common shape factors include circularity, ellipticity, etc., and areas that do not conform to the set regular shape are filtered out; the edge contour of each candidate area is extracted using an edge detection algorithm; the convexity of the edge of each area is calculated, that is, the ratio of the actual perimeter of the area to the perimeter of its minimum circumscribed convex polygon, so as to eliminate those areas with convexity lower than a certain threshold, thereby obtaining the dislocated step area after noise removal.

[0126] S25: performing a position matching operation on the dislocated step region after noise removal to obtain characteristic parameters of the dislocated step region.

[0127] A position matching operation is performed on the identified misaligned step area after noise removal to determine one or more of any reasonable characteristic parameters, such as its precise position, relative deviation, offset between the misaligned step area and the aperture area, and the area ratio of the misaligned step area in the aperture area. This application does not impose any restrictions on this.

[0128] See also Figure 9 , Figure 9 This is a flow chart of the third embodiment of the circuit board drilling detection method of the present application. The circuit board drilling detection method of this embodiment is Figure 1 A flowchart of a detailed embodiment of the circuit board drilling detection method in the embodiment includes the following steps:

[0129] S31: Acquire a circuit board image.

[0130] S32: Extracting candidate aperture regions using the brightness features of the aperture region to be measured.

[0131] S33: performing image correction and supplementation on the candidate aperture region according to the geometric features and morphological optimization processing of the candidate aperture region to obtain a dislocated step region.

[0132] S34: performing a position matching operation on the dislocated step region to obtain characteristic parameters of the dislocated step region.

[0133] Among them, S31, S32, S33 and S34 are Figure 1 S11, S12, S13 and S14 are the same. For details, please refer to S11, S12, S13 and S14 and their related text descriptions, which will not be repeated here.

[0134] S35: Detect whether the characteristic parameter is within a set threshold range.

[0135] It is understandable that in the drilling process of circuit boards, due to drill bit wear, insufficient equipment accuracy or improper operation, the drilling of the docking drill may be misaligned, forming a misaligned step area in the hole. In order to detect defective products due to unqualified drilling, the drilling process can be inspected based on the characteristic parameters of the misaligned step area and the corresponding set threshold range.

[0136] If the characteristic parameter is within the set threshold range, S36 is executed; if the characteristic parameter is not within the set threshold range, S37 is executed.

[0137] S36: Determine whether the drilling of the circuit board corresponding to the circuit board image is qualified.

[0138] When it is determined that the characteristic parameters of the misaligned step area are within the set threshold range, the currently completed drilling of the circuit board corresponding to the circuit board image is determined to be qualified and can enter the next process or be accepted.

[0139] S37: Determine that the circuit board drilling corresponding to the circuit board image is unqualified.

[0140] If the characteristic parameter of the misaligned step area is determined to be not within the set threshold range, it is determined that the drilling currently completed on the circuit board corresponding to the circuit board image is unqualified, and an alarm indication needs to be issued to remind the user that the drilling currently completed is unqualified, or it needs to be directly scrapped.

[0141] See also Figure 10 、 Figure 11a-Figure 11z and Figure 11a1 ,in, Figure 10 This is a flow chart of the fourth embodiment of the circuit board drilling detection method of the present application. Figure 11a-Figure 11z and Figure 11a1 This is a schematic diagram of the structure of an embodiment of S41-S418. This embodiment specifically includes the following steps:

[0142] S41: Acquire a circuit board image.

[0143] Specifically, if Figure 11aAs shown, an industrial camera captures a circuit board image a1 containing the aperture area to be measured and the step area within the hole. After the image is captured, it can also be processed in real time by an industrial computer.

[0144] S42: performing grayscale scaling, contrast enhancement, mean filtering, and dynamic threshold segmentation on the circuit board image in sequence to extract a first high-brightness area whose brightness exceeds a first brightness threshold.

[0145] like Figure 11b 、 Figure 11c 、 Figure 11d As shown, the grayscale of the circuit board image a1 is scaled to obtain the scaled image b1 to enhance the contrast, and the scaled image b1 is mean filtered to obtain the filtered image c1 to reduce noise interference. Then, dynamic threshold segmentation is used to extract areas with higher brightness, that is, the first high-brightness area d1 whose brightness exceeds the first brightness threshold. These areas may be aperture areas.

[0146] S43: performing closing operation, connected region analysis, filling processing, and area screening on the first high-brightness region in sequence to obtain a candidate filling region.

[0147] like Figure 11e 、 Figure 11f 、 Figure 11g 、 Figure 11h As shown, a closing operation is performed on the first high-brightness area d1 to reduce burrs to obtain a first closed image e1, and the integrity of the aperture area in the first closed image e1 is ensured. A connected region analysis is performed on the first closed image e1 to obtain multiple connected regions f1, and then the connected regions f1 are filled to ensure the integrity of the region to obtain a filled region g1, and the filled regions g1 that meet the conditions are screened out as candidate filled regions h1 based on the area.

[0148] S44: Generate a minimum circumscribed circle corresponding to the candidate filling area.

[0149] like Figure 11i As shown, a minimum circumscribed circle i1 is generated for the selected candidate filling area h1.

[0150] S45: Calculating the area of ​​the minimum circumscribed circle to obtain a characteristic area, so as to extract candidate aperture regions whose characteristic areas are within a first area threshold range.

[0151] like Figure 11j As shown, the characteristic area of ​​the minimum circumscribed circle i1 is measured and obtained, so that the area with the characteristic area within the first area threshold range can be screened out as the candidate aperture area j1.

[0152] S46: performing grayscale scaling and enhancement processing on the circuit board image in sequence to obtain an enhanced image.

[0153] like Figure 11k 、 Figure 11l As shown, the circuit board image a1 is grayscale scaled to obtain a grayscale scaled image k1, and enhanced to highlight the step area in the hole to obtain an enhanced image l1.

[0154] S47: Segment the enhanced image using the candidate aperture regions to obtain restricted aperture regions.

[0155] like Figure 11m As shown, the enhanced image l1 is cut using the candidate aperture region j1 ​​to obtain the restricted aperture region m1, so as to reduce the image domain and the image processing range to the restricted aperture region m1, thereby reducing interference with irrelevant areas.

[0156] S48: Performing threshold segmentation on the limited aperture area to extract a second high brightness area whose brightness exceeds a second brightness threshold.

[0157] like Figure 11n As shown, the cut aperture-limited area m1 is segmented by threshold value, and a second high-brightness area n1 whose brightness exceeds a second brightness threshold is extracted.

[0158] S49: performing an opening operation on the second high brightness area to obtain a noise reduction area.

[0159] like Figure 11o As shown, an opening operation is performed on the second high brightness area n1 to remove small noise to obtain a noise reduction area o1.

[0160] S410: performing area measurement on the noise reduction area to extract candidate step areas whose characteristic areas are within a second area threshold range.

[0161] like Figure 11p As shown, the area of ​​the noise reduction area o1 is measured to screen out qualified image areas according to the area of ​​the noise reduction area o1, that is, image areas whose characteristic areas are within the second area threshold range as candidate step areas p1.

[0162] S411: performing mean filtering, threshold segmentation, and shape screening on the candidate step regions in sequence to obtain a highlight region within the hole.

[0163] like Figure 11r 、 Figure 11s As shown, the circuit board image a1 is mean filtered to reduce noise interference to obtain the filtered image q1; the segmented image area r1 with a grayscale value close to 255 is extracted through threshold segmentation, and the highlight area inside the aperture is screened out according to the area, that is, the highlight area s1 inside the hole.

[0164] S412: performing region merging and closing operations on the highlighted areas in the aperture in sequence to generate a minimum circumscribed circle to obtain an optimized aperture area.

[0165] like Figure 11t 、 Figure 11u 、 Figure 11v 、 Figure 11w As shown, a set operation is performed on the highlight area s1 in the hole and the candidate step area p1 to obtain a merged area t1, and a closing operation is performed on the merged area t1, and the second high-brightness area n1 and the candidate step area p1 are connected with a very small gap to obtain a complete area u1; the minimum circumscribed circle v1 is generated for the complete area u1 to obtain the optimized aperture area w1 of the secondary extraction optimization.

[0166] S413: Segment the enhanced image using the optimized aperture region to obtain a restricted step region.

[0167] like Figure 11x As shown, the enhanced image l1 is cut using the optimized aperture region w1, and the cut image region v1 is again subjected to threshold segmentation to extract the restricted step region x1.

[0168] S414: Extract the misaligned step region based on the characteristic area, pixel length and width, and characteristic convexity of the restricted step region.

[0169] like Figure 11y As shown, the restricted step region x1 is screened according to the area, pixel length and width, and convexity to generate the final region as the dislocated step region y1.

[0170] S415: Calculate and obtain the center offset distance between the dislocated step region and the optimized aperture region.

[0171] Calculate the center offset distance between the misaligned step area y1 and the optimized aperture area w1.

[0172] S416: Detect whether the circle center offset distance is greater than a set ratio of the optimized aperture area radius.

[0173] Check whether the currently calculated center offset distance is greater than the set ratio of the optimized aperture area radius.

[0174] Optionally, the set ratio may be 8%-12%, and preferably 10%, which is not limited in this application.

[0175] If the circle center offset distance is greater than the set ratio of the optimized aperture area radius, then S417 is executed; if the circle center offset distance is not greater than the set ratio of the optimized aperture area radius, then S418 is executed.

[0176] S417: removing the corresponding misaligned step area.

[0177] It is understandable that if the center offset distance exceeds 10% of the radius of the optimized aperture area, it is determined to be a misidentification, so that the unrecognized area, ie, the corresponding misaligned step area y1, is removed.

[0178] S418: Calculate and obtain the intersection area between the misaligned step area and the optimized aperture area.

[0179] When the circle center offset distance does not exceed 10% of the radius of the optimized aperture area, the corresponding misaligned step area y1 is the effectively identified misaligned step area y1.

[0180] like Figure 11z As shown, the intersection area z1 of the misaligned step area y1 and each optimized aperture area w1 is calculated cyclically.

[0181] S419: Calculate the area ratio of the intersection region in the optimized aperture region.

[0182] The step area ratio is calculated by the formula: the area of ​​each intersection region z1 / the area of ​​the corresponding optimized aperture region w1 × 100%.

[0183] like Figure 11a1 As shown, the calculated area of ​​each intersection region z1 and the area ratio of each step are marked in the figure.

[0184] See also Figure 12 , Figure 12 Schematic diagram of a framework of an embodiment of a smart terminal of the present application. In this embodiment, the smart terminal 50 includes a memory 51 and a processor 52 coupled to each other, and the processor 52 is configured to execute program instructions stored in the memory 51 to implement the steps of any of the above-mentioned circuit board drilling detection method embodiments.

[0185] In a specific implementation scenario, the smart terminal 50 may include but is not limited to: industrial cameras, mobile phones, tablet computers, computers, servers, circuit board processing equipment, and any other reasonable terminal devices with image processing and program calculation functions. This application does not limit this.

[0186] Specifically, the processor 52 is used to control itself and the memory 51 to implement the steps of any of the above-mentioned video display method embodiments. The processor 52 can also be called a CPU (Central Processing Unit). The processor 52 may be an integrated circuit chip with signal processing capabilities. The processor 52 can also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor 52 can also be any conventional processor, etc. In addition, the processor 52 can be implemented by an integrated circuit chip.

[0187] See also Figure 13 , Figure 13 Schematic diagram of a computer-readable storage medium embodiment of the present invention. In this embodiment, the computer-readable storage medium 60 stores program instructions 61 that can be executed by a processor, and the program instructions 61 are used to implement the steps of any of the above-mentioned circuit board drilling detection method embodiments.

[0188] In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device implementation methods described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation. For example, units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0189] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0190] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0191] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

Claims

1. A circuit board drilling detection method, characterized in that: The circuit board drilling detection method comprises: Acquire a circuit board image; wherein the circuit board image includes an aperture area to be measured; Extracting a candidate aperture region using the brightness characteristics of the aperture region to be measured; Performing image correction and supplementation on the candidate aperture region according to the geometric features and morphological optimization processing of the candidate aperture region to obtain a dislocated step region; A position matching operation is performed on the dislocated step region to obtain characteristic parameters of the dislocated step region.

2. The circuit board drilling detection method according to claim 1, characterized in that: After the step of performing image correction and supplementation on the candidate aperture region according to the geometric features and morphological optimization processing of the candidate aperture region to obtain the dislocated step region, and before the step of performing position matching operation on the dislocated step region to obtain the characteristic parameters of the dislocated step region, the method further includes: Noise removal is performed using the area, shape regularity, and edge convexity of the dislocated step region; The step of performing position matching operation on the dislocated step region to obtain the dislocated step region and characteristic parameters of the dislocated step region comprises: A position matching operation is performed on the dislocated step region after noise removal to obtain characteristic parameters of the dislocated step region.

3. The circuit board drilling detection method according to claim 1, characterized in that: The step of extracting a candidate aperture region by using the brightness feature of the aperture region to be measured comprises: Preprocessing the circuit board image to extract a first high-brightness area whose brightness exceeds a first brightness threshold; A shape feature operation is performed on the first high-brightness area to extract a candidate aperture area whose characteristic area is within a first area threshold range.

4. The circuit board drilling detection method according to claim 3, characterized in that: The step of preprocessing the circuit board image comprises: Grayscale scaling, contrast enhancement, mean filtering, and dynamic threshold segmentation are sequentially performed on the circuit board image.

5. The circuit board drilling detection method according to claim 3, characterized in that: The step of performing shape feature calculation on the first high-brightness area includes: performing closing operation, connected region analysis, filling processing, and area screening on the first high-brightness region in sequence to obtain a candidate filling region; Generating a minimum circumscribed circle corresponding to the candidate filling area; The characteristic area is obtained by measuring the area of ​​the minimum circumscribed circle.

6. The circuit board drilling detection method according to claim 1, characterized in that: The step of performing image correction and supplementation on the candidate aperture region according to the geometric features and morphological optimization processing of the candidate aperture region to obtain the dislocated step region comprises: Performing a feature extraction operation on the candidate aperture region to extract a candidate step region whose characteristic area is within a second area threshold range; Performing a brightness feature extraction operation on the candidate step region to obtain a highlight region in the hole; performing a secondary feature extraction operation on the highlighted area in the hole to extract an optimized aperture area whose characteristic area is within a third area threshold range; The optimized aperture region is subjected to three feature extraction operations to extract the dislocation step region whose characteristic area is within a fourth area threshold range and whose characteristic convexity is within a set convexity threshold range.

7. The circuit board drilling detection method according to claim 6, characterized in that: The step of performing a feature extraction operation on the candidate aperture region to extract a candidate step region whose feature area is within a second area threshold range includes: performing grayscale scaling and enhancement processing on the circuit board image in sequence to obtain an enhanced image; Segmenting the enhanced image using the candidate aperture regions to obtain restricted aperture regions; performing threshold segmentation on the aperture-limited region to extract a second high-brightness region whose brightness exceeds a second brightness threshold; performing an opening operation on the second high-brightness area to obtain a noise reduction area; The area of ​​the noise reduction area is measured to extract the candidate step area whose characteristic area is within the second area threshold range.

8. The circuit board drilling detection method according to claim 6, characterized in that: The step of performing a brightness feature extraction operation on the candidate step area to obtain a highlight area in the hole includes: The candidate step area is sequentially subjected to mean filtering, threshold segmentation, and shape screening processing to obtain the highlight area in the hole.

9. The circuit board drilling detection method according to claim 6, characterized in that: The step of performing a secondary feature extraction operation on the highlighted area in the hole to extract an optimized aperture area whose feature area is within a third area threshold range includes: The optimized aperture area is obtained by sequentially performing region merging and closing operations on the highlighted area in the hole and generating a minimum circumscribed circle.

10. The circuit board drilling detection method according to claim 7, characterized in that: The step of performing three feature extraction operations on the optimized aperture area to extract the dislocation step area having a feature area within a fourth area threshold range and a feature convexity within a set convexity threshold range includes: Segmenting the enhanced image using the optimized aperture region to obtain a restricted step region; The dislocated step region is extracted according to the characteristic area, pixel length and width, and characteristic convexity of the restricted step region.

11. The circuit board drilling detection method according to claim 10, characterized in that: The step of performing a position matching operation on the dislocated step region to obtain characteristic parameters of the dislocated step region comprises: Calculating the center offset distance between the dislocated step area and the optimized aperture area; Calculating and obtaining an intersection area between the dislocation step area and the optimized aperture area; The area ratio of the intersection region in the optimized aperture region is calculated.

12. The circuit board drilling detection method according to claim 11, characterized in that: After the step of calculating the center offset distance between the staggered step region and the optimized aperture region, and before the step of calculating the intersection region between the staggered step region and the optimized aperture region, the method further includes: Detecting whether the circle center offset distance is greater than a set ratio of the optimized aperture area radius; If the circle center offset distance is greater than the set ratio of the radius of the optimized aperture area, the corresponding misaligned step area is removed.

13. The circuit board drilling detection method according to claim 1, characterized in that: After the step of performing position matching operation on the dislocated step region to obtain characteristic parameters of the dislocated step region, the method further includes: Detecting whether the characteristic parameter is within a set threshold range; If the characteristic parameter is not within the set threshold range, it is determined that the circuit board drilling corresponding to the circuit board image is unqualified.

14. An intelligent terminal, characterized in that: The intelligent terminal includes a memory and a processor coupled to each other; The memory stores program data; The processor is configured to execute the program data to implement the circuit board drilling detection method according to any one of claims 1 to 13.

15. A computer-readable storage medium, characterized in that The computer-readable storage medium stores program data, and the program data can be executed to implement the circuit board drilling detection method according to any one of claims 1 to 13.

Images