FPC patch detection method, detection system, medium and program product

Abstract

The invention relates to the technical field of FPC patch detection, in particular to an FPC patch detection method and system, a medium and a program product, and the method comprises the steps that multi-angle detection images are acquired, and the multi-angle detection images are different-view-angle images of a to-be-detected FPC in a detection area; based on the multi-angle detection image, determining a three-dimensional FPC image corresponding to the to-be-detected FPC, and identifying three-dimensional patch features contained in the three-dimensional FPC image; and based on the three-dimensional patch characteristics, whether the to-be-detected FPC contains a deviation patch is judged, and if yes, early warning prompt information is generated based on deviation patch characteristics corresponding to the deviation patch. According to the invention, the accuracy in the FPC patch detection process can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of FPC patch detection, and in particular to an FPC patch detection method, detection system, medium and program product. Background Art

[0002] With the rapid development of electronic technology, flexible printed circuits (FPCs) have been widely used in electronic products due to their lightness, flexibility, and high-density wiring. As the miniaturization and integration of electronic products become increasingly obvious, the design and production technology of FPCs are also constantly improving to meet the needs of higher-density and more complex circuit layouts.

[0003] FPC patching involves accurately and reliably mounting electronic components on designated locations on an FPC. The quality of the patching process is directly related to the connection performance of subsequent circuits and the overall reliability of the product. Therefore, rigorous testing of the FPC patching process is a key step in ensuring FPC quality. However, due to factors such as the diverse materials, small component sizes, and complex shapes of FPCs, the accuracy of patch testing is relatively low. Low detection accuracy can lead to missed detections and false detections, resulting in substandard products entering the market. These substandard products can experience problems such as poor circuit connections and unstable signal transmission during use, seriously impacting the performance of electronic products and user experience. Summary of the Invention

[0004] In order to improve the accuracy of the FPC patch detection process and prevent unqualified products from flowing into the next process or market, the present application provides an FPC patch detection method, detection system, medium and program product.

[0005] In the first aspect, the present application provides an FPC patch detection method, which adopts the following technical solution: A method for detecting an FPC patch, comprising: Acquire a multi-angle detection image, wherein the multi-angle detection image is an image of the FPC to be detected at different viewing angles within the detection area; Based on the multi-angle detection image, determine the three-dimensional FPC image corresponding to the FPC to be detected, and identify the three-dimensional patch features contained in the three-dimensional FPC image; Based on the three-dimensional patch features, determining whether the FPC to be detected contains a deviation patch; If so, a warning prompt message is generated based on the deviation patch feature corresponding to the deviation patch.

[0006] By adopting the above technical solution, by analyzing the images of the FPC to be inspected in the inspection area from different perspectives, it is convenient to more comprehensively cover the surface and patch positions of the FPC to be inspected, thereby avoiding low detection accuracy caused by missing patch positions. The three-dimensional FPC image determined by the multi-angle detection image can provide richer spatial information than the two-dimensional image, thereby facilitating the improvement of the accuracy of the three-dimensional patch feature recognition of each patch position. In addition, by automatically identifying the three-dimensional patch features and judging whether the patch components at each patch position are deviated or damaged based on these three-dimensional patch features, it is convenient to realize the automation and intelligence of the detection process, which not only improves the detection efficiency, but also reduces the errors and uncertainties caused by human factors. When a deviated patch is detected, the early warning prompt information is generated in time, which facilitates the relevant operators to quickly locate the problem and take corresponding measures, thereby preventing unqualified products from flowing into the next process or market.

[0007] In one possible implementation, the method further includes: Obtain the warning record information generated within the preset integration time period, and identify the deviation patch position and deviation patch characteristics corresponding to each warning record information; Determining a deviation strain region corresponding to each deviation patch position based on each deviation patch position and a corresponding deviation patch feature; Determine a planar FPC image based on the multi-angle detection image, and superimpose the deviation strain area corresponding to each deviation patch position on the planar FPC image to obtain a strain image; Identifying a strain region of interest contained in the strain image, and determining a patch of interest corresponding to the strain region of interest, wherein a pixel value of a region corresponding to the strain region of interest is higher than a first preset pixel threshold; The focus patch link is superimposed on the strain image to obtain a focus strain image, and the focus strain image is fed back.

[0008] By adopting the above technical solution, by analyzing the characteristics of each deviation patch, it is convenient to accurately analyze the specific strain conditions of each deviation patch position after the deviation patch occurs on the FPC to be tested. At the same time, the deviation strain area corresponding to each deviation patch position is superimposed on the plane FPC image to obtain a strain image, which facilitates accurate analysis and determination of the most affected focus strain area. By providing feedback on the focus patch link corresponding to the most affected focus strain area, it is convenient for relevant operators to pay attention to and make timely adjustments to the focus patch link, so as to reduce the probability of similar or identical deviation patch situations occurring in subsequent patch operations.

[0009] In one possible implementation, determining a deviation strain region corresponding to the deviation patch position based on the deviation patch position and the corresponding deviation patch feature includes: Obtaining a deviation patch element and an original patch position corresponding to the deviation patch position, and determining an original strain region corresponding to the original patch position according to the original patch position and the deviation patch element; Determine a corresponding observation area based on the deviation patch position, and obtain the number of other patch elements and other patch element types contained in the observation area; Obtaining an actual strain region at the deviation patch position, adjusting the actual strain region based on the number of other patch elements and other patch element types contained in the observation area, to obtain a current strain region corresponding to the deviation patch position; The deviation strain area corresponding to the deviation patch position is determined according to the original strain area and the current strain area.

[0010] By adopting the above technical solution, by analyzing the number of other patch components and other patch component types in the observation area corresponding to the deviation patch position, it is convenient to more comprehensively analyze the impact of the deviation patch situation on the FPC to be tested. By accurately determining the deviation strain area corresponding to the deviation patch position, it is convenient to timely and accurately discover the focus patch link after the area superposition, and take corresponding improvement measures in time, thereby reducing the probability of similar or identical abnormal deviation patch situations occurring in the future.

[0011] In one possible implementation, the method further includes: When the deviation patch position includes an associated deviation position, determining a first adjustment area based on a time difference between an associated deviation moment of the associated deviation position and a deviation moment of the deviation patch position, the time difference between the associated deviation moment of the associated deviation position and the deviation moment of the deviation patch position being lower than a preset time difference threshold; Obtaining a patch workload corresponding to the deviation patch position in a preset patch time period, and determining a second adjustment area based on the patch workload; The deviation strain region corresponding to the deviation patch position is adjusted based on the first adjustment area and the second adjustment area.

[0012] By adopting the above technical solution, the influence of the deviation patch situation at the associated deviation position on the deviation patch position is taken into consideration when determining the deviation strain area, and the influence is quantified as an adjustment area, so as to improve the accuracy in determining the deviation strain area corresponding to the deviation patch position. At the same time, by analyzing the patch workload that the deviation patch position may face in the future, it is convenient to understand the busyness and importance of the deviation patch position in the patch process, and adjust the deviation strain area based on this, so as to increase the attention of relevant operators to the deviation strain area, and also facilitate timely adoption of relevant improvement measures.

[0013] In one possible implementation, the method further includes: Identifying a target strain region included in the strain image, and determining a target angle from the multi-angle detection image based on the target strain region, wherein a regional pixel value corresponding to the target strain region is higher than a second preset pixel threshold; Based on the target angle, a target patch process image and a preset standard patch process image corresponding to the target strain area are acquired; The preset patch process image is compared with the preset standard patch process image to determine patch differences, and the patch differences are fed back.

[0014] By adopting the above technical solution, the target angle is determined from the multi-angle detection image according to the target strain area, and the target patch process image is obtained based on the target angle, which helps to improve the pertinence and effectiveness of analyzing the cause of deviation patching. In addition, by comparing the obtained target patch process image with the preset standard patch process image, it helps to quickly discover the differences in the patch process, thereby facilitating targeted improvements to the patch operation and reducing the probability of deviation patching.

[0015] In one possible implementation, the method further includes: When the multi-angle detection image contains a preset material feature, obtaining detection spectrum data of the FPC to be detected; Determining a main peak interval from the detected spectral data, and determining a target lighting parameter corresponding to the main peak interval based on the main peak interval and a preset lighting mapping relationship, wherein the preset lighting mapping relationship is a correspondence between the main peak interval and the target lighting parameter; The actual lighting parameters of the lighting device are optimized based on the lighting parameters.

[0016] By adopting the above technical solution, the detection spectral data is analyzed and the corresponding main peak range is determined. Combined with the preset lighting mapping relationship, the target lighting parameters can be accurately determined. This targeted lighting optimization method ensures that the lighting light better matches the reflective characteristics of the FPC surface to be inspected, thereby improving the imaging quality and further improving the accuracy of deviation patch detection.

[0017] In a second aspect, the present application provides a detection system that adopts the following technical solution: A detection system, comprising: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute the above-mentioned FPC patch detection method.

[0018] In a third aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution: A computer-readable storage medium includes: a computer program that can be loaded by a processor and execute the above-mentioned FPC patch detection method.

[0019] In a fourth aspect, the present application provides a computer program product that adopts the following technical solution: A computer program product includes a computer program, wherein when the computer program is executed by a processor, the computer program implements the above-mentioned FPC patch detection method.

[0020] In summary, this application includes at least one of the following beneficial technical effects: By analyzing the images of the FPC to be inspected in the inspection area from different perspectives, it is convenient to more comprehensively cover the surface and patch positions of the FPC to be inspected, thereby avoiding low detection accuracy caused by missing patch positions. The three-dimensional FPC image determined by the multi-angle detection image can provide richer spatial information than the two-dimensional image, thereby facilitating the improvement of the accuracy of the three-dimensional patch feature recognition of each patch position. In addition, by automatically identifying the three-dimensional patch features and judging whether the patch components at each patch position are deviated or damaged based on these three-dimensional patch features, it is convenient to realize the automation and intelligence of the detection process, which not only improves the detection efficiency, but also reduces the errors and uncertainties caused by human factors. When a deviated patch is detected, the early warning prompt information is generated in time, which facilitates the relevant operators to quickly locate the problem and take corresponding measures, thereby preventing unqualified products from flowing into the next process or market.

[0021] By analyzing the characteristics of each deviation patch, it is convenient to accurately analyze the specific strain conditions of each deviation patch position after the deviation patch occurs on the FPC to be tested. At the same time, the deviation strain area corresponding to each deviation patch position is superimposed on the plane FPC image to obtain a strain image, which facilitates accurate analysis and determination of the most affected focus strain area. By providing feedback on the focus patch link corresponding to the most affected focus strain area, it is convenient for relevant operators to pay attention to and make timely adjustments to the focus patch link, so as to reduce the probability of similar or identical deviation patch situations occurring in subsequent patch operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 This is a flow chart of an FPC patch detection method in an embodiment of the present application; Figure 2This is a schematic diagram of a process for determining a strain image of interest in an embodiment of the present application; Figure 3 It is a structural diagram of a detection system in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following is combined with Figures 1 to 3 This application is described in further detail.

[0024] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they fall within the scope of the claims of this application.

[0025] To make the purpose, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application will be clearly and completely described below in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in 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.

[0026] It should be noted that in the optional embodiments of the present application, the object information and other related data involved, when the embodiments in the present application are applied to specific products or technologies, need to obtain the permission or consent of the object, and the collection, use and processing of the relevant data need to comply with the relevant laws, regulations and standards of the relevant countries and regions. In other words, if the embodiments of the present application involve data related to the object, it needs to be obtained through the authorization and consent of the object, the authorization and consent of the relevant departments, and in compliance with the relevant laws, regulations and standards of the country and region. If personal information is involved in the embodiments, the acquisition of all personal information requires the consent of the individual. If sensitive information is involved, the separate consent of the information subject needs to be obtained. The embodiments also need to be implemented with the authorization and consent of the object.

[0027] Specifically, embodiments of the present application provide an FPC patch detection method, which is performed by a detection system. The detection system can be a server or a terminal device. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet computer, laptop computer, desktop computer, etc., but is not limited to these. The terminal device and server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiments of the present application.

[0028] refer to Figure 1 , Figure 11 is a flow chart of an FPC patch detection method in an embodiment of the present application, the method comprising steps S110 to S130, wherein: Step S110: Acquire a multi-angle detection image, where the multi-angle detection image is an image of the FPC to be detected in the detection area at different viewing angles.

[0029] Specifically, the multi-angle detection images are collected by a multi-level image acquisition device installed at the FPC patch site after the FPC to be detected enters the detection area and uploaded to the detection system. The multi-level image acquisition device can be a high-resolution camera or laser scanner installed at the top and around the detection area. As long as the FPC to be detected enters the detection area, the image acquisition device installed at the top will first capture the overall picture of the FPC to be detected, and then control the image acquisition devices or laser scanners installed on the four sides to collect detailed images of the side of the FPC to be detected from four directions. After the detection system aggregates the top-collected data and the surrounding data, it can automatically compare the consistency between the different angle detection data. When it is found that the data difference between any angle detection data and other angle detection data at the same position exceeds the preset data difference threshold, an abnormal alarm will be immediately issued to remind the relevant operators to remove the abnormal angle detection data in time.

[0030] Step S120: Based on the multi-angle detection images, determine the three-dimensional FPC image corresponding to the FPC to be detected, and identify the three-dimensional patch features contained in the three-dimensional FPC image.

[0031] Specifically, before constructing a three-dimensional FPC image based on a multi-angle detection image, the multi-angle detection image may be subjected to pre-processing operations such as denoising, contrast enhancement, and image size adjustment. Then, a dense point cloud is generated from the multi-angle detection image according to a preset stereo matching algorithm, wherein the preset stereo matching algorithm may be an SGBM algorithm, and the specific algorithm is not specifically limited in the embodiment of this application. Then, the full picture of the FPC to be detected captured by the top image acquisition device is mapped to the surface of the dense point cloud, and the color and pattern information is supplemented. Finally, the dense point cloud is gridded using the Poisson reconstruction method to obtain a three-dimensional FPC image corresponding to the FPC to be detected. The method of determining a three-dimensional FPC image based on a multi-angle detection image is not specifically limited in the embodiment of this application, as long as the determined three-dimensional FPC image can highly restore the FPC to be detected at the geometric and appearance levels.

[0032] Three-dimensional patch features can be identified from a three-dimensional FPC image based on a preset feature recognition algorithm and a patch design drawing, wherein the preset feature recognition algorithm can be a normalized cross-correlation algorithm, or a support vector machine decision tree, a random forest, etc. The specific preset feature recognition algorithm is not specifically limited in the embodiment of this application. The patch design drawing contains the coordinates of each patch position in the FPC to be detected. The three-dimensional patch features include but are not limited to the geometric shape features, position features, and surface features of the patch elements.

[0033] Step S130: Based on the three-dimensional patch features, determine whether the FPC to be inspected contains a deviation patch. If so, generate warning prompt information based on the deviation patch features corresponding to the deviation patch.

[0034] Specifically, by comparing the three-dimensional patch features with the preset patch specifications, it is convenient to determine whether the FPC to be tested contains any deviation patches, wherein the preset patch specifications include standard patch images and standard patch shapes for each patch position. For a certain patch position, the three-dimensional patch features corresponding to the patch position are matched with the corresponding preset patch specifications. If the patch matching value is higher than the preset matching threshold, it is determined that there is no deviation patch; if the patch matching value is not higher than the preset matching threshold, it is determined that there is a deviation patch, wherein the specific preset matching threshold can be 98% or 95%. The specific numerical value is not specifically limited in the embodiment of this application, and can be determined by relevant staff based on historical experimental data and uploaded to the detection system.

[0035] For the embodiments of the present application, by analyzing the images of the FPC to be inspected in the inspection area from different perspectives, it is convenient to more comprehensively cover the surface and patch positions of the FPC to be inspected, thereby avoiding low detection accuracy caused by missing patch positions. The three-dimensional FPC image determined by the multi-angle detection image can provide richer spatial information than the two-dimensional image, thereby facilitating the improvement of the accuracy of the three-dimensional patch feature recognition of each patch position. In addition, by automatically identifying the three-dimensional patch features and judging whether the patch elements at each patch position are deviated or damaged based on these three-dimensional patch features, it is convenient to realize the automation and intelligence of the detection process, which not only improves the detection efficiency, but also reduces the errors and uncertainties caused by human factors. When a deviated patch is detected, the early warning prompt information is generated in time, which facilitates the relevant operators to quickly locate the problem and take corresponding measures, thereby preventing unqualified products from flowing into the next process or market.

[0036] Furthermore, in order to reduce the probability of similar or identical deviation patches occurring in subsequent patch operations, the method provided in the embodiment of the present application further includes steps S210 to S250, such as Figure 2 ,in: Step S210: Acquire the warning record information generated within a preset integration time period, and identify the deviation patch position and deviation patch features corresponding to each warning record information.

[0037] Specifically, the preset integration time period is a period of time before the current moment, and the duration corresponding to the preset integration time period can be 24 hours or 48 hours. The specific duration is not specifically limited in the embodiments of the present application. By analyzing and summarizing the early warning record information generated within the preset integration time period, it is convenient to summarize the characteristics or laws of the deviation patch situation that occurred within the preset integration time period, so as to facilitate subsequent targeted improvement of the patch operation. Each early warning record information contains at least one deviation patch position and deviation patch feature, wherein the deviation patch position is the patch position where the deviation patch situation exists, and the deviation patch feature can be determined by the deviation three-dimensional patch feature corresponding to the deviation patch position, which can specifically include but is not limited to patch position offset data and patch surface damaged data. The corresponding deviation patch and deviation patch feature can be extracted from each early warning record information through a preset feature recognition algorithm. The specific preset feature recognition algorithm is not specifically limited in the embodiments of the present application.

[0038] Step S220: Based on each deviation patch position and the corresponding deviation patch feature, determine the deviation strain region corresponding to each deviation patch position.

[0039] Specifically, during the patch stage of the FPC to be tested, a strain area will be generated at each patch position. This is due to factors such as the weight, volume, and thermal expansion coefficient differences of the patch components. The deviation strain area is the difference between the strain area generated at the original patch position after patching and the strain area generated at the deviation patch position after the deviation patch occurs. For example, the strain area corresponding to the original patch position is area a, and after the deviation patch occurs, the strain area corresponding to the deviation patch position is area b, where the deviation strain area is the area outside the intersection of area a and area b.

[0040] Furthermore, to improve the accuracy of determining the deviation strain area, the method provided in the embodiment of the present application may include the following steps when determining the deviation strain area corresponding to the deviation patch position based on the deviation patch position and the corresponding deviation patch features: Obtain the deviation patch element and the original patch position corresponding to the deviation patch position, and determine the original strain area corresponding to the original patch position based on the original patch position and the deviation patch element; determine the corresponding observation area based on the deviation patch position, and obtain the number of other patch elements and other patch element types contained in the observation area; obtain the actual strain area of the deviation patch position, adjust the actual strain area based on the number of other patch elements and other patch element types contained in the observation area, and obtain the current strain area corresponding to the deviation patch position; determine the deviation strain area corresponding to the deviation patch position based on the original strain area and the current strain area.

[0041] Specifically, since different patch elements have different weights, volumes and thermal expansion coefficients, different deviation patch elements generate different strain area areas after patching. When determining the original strain area corresponding to the original patch position, the first area area corresponding to the deviation patch element can be determined based on the mapping relationship between the deviation patch element and the first preset area area, and then the original strain area corresponding to the original patch position can be determined based on the original patch position and the first area area. The first preset area area mapping relationship is the correspondence between the deviation patch element and the first area area. The specific content is not specifically limited in the embodiment of this application, and can be determined by relevant staff based on historical experimental data and uploaded to the detection system.

[0042] Since the deviation patch element may affect the electrical connection between other patch elements after the deviation patch occurs, especially when the deviation patch position is close to other patch elements, it is necessary to determine the corresponding observation area based on the deviation patch position, and then analyze the types of the number of other patch elements contained in the observation area, and adjust the strain area corresponding to the deviation patch element. By appropriately adjusting the strain area corresponding to the deviation patch position, it is convenient to improve the matching degree between the importance of the strain area and the deviation patch position. The observation area area corresponding to different deviation patch positions is different. The observation area is the area with the deviation patch position as the center of the circle. When determining the observation area, the second area area corresponding to the different deviation patch positions can be determined according to the second preset area area mapping relationship, and then the observation area corresponding to the deviation patch position is determined based on the deviation patch position and the second area area. The second preset area area mapping relationship is the mapping relationship between the deviation patch position and the second area area. The specific content is not specifically limited in the embodiment of this application.

[0043] The number of other patch elements and other patch element types contained in the observation area can be identified from the multi-angle detection image containing the observation area through a preset feature recognition algorithm. The surface morphology of the patch elements corresponding to different other patch element types is different. Therefore, the surface morphology of the patch elements can be analyzed and determined by identifying the surface morphology of the patch elements. The preset type mapping relationship is the correspondence between the surface morphology of the patch elements and the patch element types. After determining the number of other patch elements and other patch element types contained in the observation area, the area adjustment value corresponding to the observation area can be determined based on the preset adjustment area mapping relationship. The actual strain area is then scaled based on the area adjustment value to finally obtain the current strain area, wherein the actual strain area is the strain area actually generated after the deviation patch position occurs. It can be determined by performing feature recognition on the multi-angle detection image. The preset adjustment area mapping relationship is the mapping relationship between the parameter combination of the number of other patch elements and the type of other patch elements and the area adjustment value. The specific content of the preset adjustment area mapping relationship is not specifically limited in the embodiment of the present application.

[0044] After determining the original and current strain regions, the area beyond their overlap is identified as the deviation strain region corresponding to the deviation patch location. By accurately determining the deviation strain region corresponding to the deviation patch location, it is possible to promptly and accurately identify patches of concern after the regions are superimposed, allowing for the timely implementation of appropriate improvement measures.

[0045] Step S230: determining a planar FPC image based on the multi-angle detection images, and superimposing the deviation strain area corresponding to each deviation patch position onto the planar FPC image to obtain a strain image.

[0046] Specifically, when determining the planar FPC image, the multi-angle detection image can be projected onto a two-dimensional plane. The specific determination method is not specifically limited in the embodiment of the present application. Each deviation strain area can be filled based on the preset pixel value to obtain a filled strain area. The specific preset pixel value is not specifically limited in the embodiment of the present application. The corresponding filled strain area can be superimposed based on the position of each deviation patch position in the planar FPC image. Since the preset integration time period corresponds to a long time, the same deviation patch position may correspond to multiple filled strain areas within the preset integration time period, but the corresponding filled strain areas are not necessarily the same. Therefore, the filled strain areas corresponding to the same deviation patch position may cross or overlap. In addition, the filled strain areas corresponding to adjacent deviation patch positions may also cross or overlap, and the pixel values corresponding to the crossed or overlapping areas will increase. After all the deviation strain areas are superimposed on the planar FPC image, a strain image can be obtained.

[0047] Step S240: identifying a strain region of interest contained in the strain image, and determining a patch of interest corresponding to the strain region of interest, wherein a pixel value of the region corresponding to the strain region of interest is higher than a first preset pixel threshold.

[0048] Specifically, the strain area of interest can be determined from the strain image by identifying the pixel values corresponding to each point in the strain image. The strain area of interest is an intersection or overlapping area where the regional pixel value is higher than the first preset pixel threshold. The specific first preset pixel threshold is not specifically limited in the embodiment of this application, and can be determined by relevant staff based on historical experimental data and uploaded to the detection system. Different areas on the FPC to be detected correspond to different patch links. Based on the mapping relationship between the strain area of interest and the preset patch link, the patch link of interest corresponding to the strain area of interest can be determined. The patch link of interest is mainly responsible for patching the strain area of interest. The preset patch link mapping relationship is the correspondence between the strain area of interest and the patch link of interest, and the specific content is not specifically limited in the embodiment of this application.

[0049] Step S250: superimposing the patch of interest onto the strain image to obtain the strain image of interest, and feeding back the strain image of interest.

[0050] Specifically, after determining the patch link of interest, the patch link of interest can be determined as display text, and the strain area of interest in the strain image can be superimposed in the form of text to obtain the strain image of interest. By providing feedback on the patch link of interest corresponding to the most affected strain area of interest, it is convenient for relevant operators to pay attention to and adjust the patch link of interest in a timely manner, so as to reduce the probability of similar or identical deviation patches in subsequent patch operations.

[0051] In order to improve the accuracy of determining the deviation patch position corresponding to the deviation strain area, the method provided in the embodiment of the present application further includes: When the deviation patch position includes an associated deviation position, a first adjustment area is determined based on the time difference between the associated deviation moment of the associated deviation position and the deviation moment of the deviation patch position, and the time difference between the associated deviation moment of the associated deviation position and the deviation moment of the deviation patch position is lower than a preset time difference threshold; the patch workload corresponding to the deviation patch position in the preset patch time period is obtained, and a second adjustment area is determined based on the patch workload; based on the first adjustment area and the second adjustment area, the deviation strain area corresponding to the deviation patch position is adjusted.

[0052] Specifically, since the material used for the FPC to be tested is a flexible material, such as polyimide, the deformation of the flexible material during the patch process may be transmitted to adjacent areas, especially when the patch operations are performed separately at adjacent patch positions within a short period of time. The deformation occurring at the previous moment may affect the deformation occurring at the next moment. The deviation patch positions corresponding to the previous moment and the next moment are associated, that is, the deviation patch position corresponding to the previous moment is the associated deviation position of the deviation patch position corresponding to the next moment. As long as the time difference between the associated deviation moment and the deviation moment is lower than the preset time difference threshold, the specific preset time difference threshold is not specifically limited in the embodiment of the present application, and can be determined by relevant staff based on historical experimental data and uploaded to the detection system. The smaller the time difference, the closer the moment when the deviation patch position is deformed is to the moment when the associated deviation position is deformed. At this time, the deviation patch position is more affected, and the corresponding first adjustment area is also larger. There is an adjustment correspondence between the time difference and the first adjustment area. Based on this adjustment correspondence, the first adjustment area corresponding to any time difference can be determined. The specific content of this adjustment correspondence is not specifically limited in the embodiment of this application, and can be determined by relevant staff based on historical experimental data.

[0053] The preset patch time period is a period of time after the current moment, and the duration corresponding to the preset patch time period can be 30 minutes, or 50 minutes. The specific duration is not specifically limited in the present application embodiment and can be set by relevant staff according to actual needs. The patch workload is used to characterize the patch operation amount that needs to be carried out at the deviation patch position in the future. The larger the patch workload, the higher the importance of the deviation patch position. At this time, it is necessary to adjust the deviation strain area corresponding to the deviation patch position, by expanding the deviation strain area so as to promote the attention of relevant staff to the deviation patch position. The second adjustment area corresponding to any patch workload can be determined according to the preset workload mapping relationship. The preset workload mapping relationship is the mapping relationship between the patch workload and the second adjustment area. The specific content of this mapping relationship is not specifically limited in the present application embodiment and can be uploaded to the detection system after being determined by relevant staff according to historical experimental data. The patch workload corresponding to the preset patch time period can be determined by the patch production plan. The patch production plan can be determined by relevant staff according to actual patch operation tasks and uploaded to the detection system.

[0054] Finally, the first adjustment area and the second adjustment area corresponding to the deviation patch position are integrated to determine the integrated adjustment area, and then the original deviation strain area is expanded according to the integrated adjustment area.

[0055] Furthermore, in order to reduce the probability of occurrence of deviation patch situation, the method further includes: Identify the target strain area contained in the strain image, and determine the target angle from the multi-angle detection image based on the target strain area, where the regional pixel value corresponding to the target strain area is higher than a second preset pixel threshold; based on the target angle, obtain the target patch process image and the preset standard patch process image corresponding to the target strain area; compare the preset patch process image with the preset standard patch process image to determine the patch difference, and provide feedback on the patch difference.

[0056] Specifically, pixel recognition can be used to identify target strain regions within the strain image where the regional pixel values exceed a second preset pixel threshold, where the second preset pixel threshold is higher than the first preset pixel threshold. The target angle can be determined from the multi-angle detection images using a preset clarity recognition algorithm and a preset morphological feature recognition algorithm, provided that the target angle is higher than a preset clarity and the target strain region in the target angle detection image is free of distortion or other morphological changes. The specific method for determining this determination is not specifically limited in the embodiments of this application.

[0057] The target patch process image corresponding to the target strain area is the patch process image corresponding to the target angle during the actual patch process. The preset standard patch process image can be uploaded to the detection system in advance by relevant personnel and retrieved from the detection system based on the target strain area and target angle when needed. Comparing the acquired target patch process image with the preset standard patch process image helps to quickly identify differences in the patch process, thereby facilitating targeted improvements to the patch operation and reducing the probability of deviation in patching.

[0058] Furthermore, in order to improve the imaging quality, the method provided in the embodiment of the present application further includes: When the multi-angle detection image contains preset material features, the detection spectrum data of the FPC to be detected is obtained; the main peak interval is determined from the detection spectrum data, and based on the main peak interval and the preset lighting mapping relationship, the target lighting parameters corresponding to the main peak interval are determined, and the preset lighting mapping relationship is the correspondence between the main peak interval and the target lighting parameters; the actual lighting parameters of the lighting equipment are optimized based on the lighting parameters.

[0059] Specifically, due to the diverse materials and inconsistent reflectivity of the FPC being inspected, errors may occur during image recognition. The specific preset material characteristics are not specifically defined in this embodiment of the application and can be determined by relevant personnel based on historical experimental data and uploaded to the inspection system. If the multi-angle inspection image includes the preset material characteristics, it indicates a high probability of error in image recognition of the FPC being inspected. In this case, spectral data analysis can be used to adjust or optimize the lighting parameters to ensure image recognition accuracy.

[0060] When the FPC to be tested is sent into the detection area, the detection system can control the spectrum analyzer set in the detection area to start, and collect spectral data of the surface material of the FPC to be tested. The spectrum analyzer emits light within a certain range. After the light is irradiated on the surface of the FPC to be tested, part of the light will be reflected back to the spectrum analyzer, thereby forming a spectrum graph. The spectrum graph is usually displayed as a relationship diagram between wavelength or frequency and corresponding light intensity. Each wavelength or frequency corresponds to a light intensity value, which indicates the reflection or absorption ability of the surface material of the FPC to be tested to light at this wavelength or frequency. In the spectrum graph, the area with the highest light intensity is identified, that is, the peak area. These peaks are used to characterize the strong reflection or absorption characteristics of the surface material of the FPC to be tested at a specific wavelength. The main peak interval usually refers to the wavelength range where these peaks are located. Since different surface materials have specific absorption or reflection peaks at different wavelengths, the main peak interval can be used to identify the material characteristics of the FPC surface. The main peak interval can be determined from the detection spectrum data by local extreme value method, continuous wavelet transform method, etc. The method of determining the main peak interval is not specifically limited in the embodiment of this application.

[0061] Different main peak intervals correspond to different target lighting parameters. The target lighting parameters corresponding to different main peak intervals can be determined by a preset lighting mapping relationship. The specific content of the preset lighting mapping relationship is not specifically limited in the embodiment of this application and can be determined by relevant staff based on historical experimental data and uploaded to the detection system. The target lighting parameters include but are not limited to wavelength, light intensity, pulse width, etc. The specific content can be set by relevant staff according to actual needs. By analyzing the detection spectrum data and determining the corresponding main peak interval, and then combining the preset lighting mapping relationship, it is convenient to accurately determine the target lighting parameters. This targeted lighting optimization method facilitates ensuring that the lighting light better matches the reflective characteristics of the FPC surface to be detected, thereby improving imaging quality and further facilitating the improvement of the accuracy of deviation patch detection.

[0062] The present application provides a detection system, such as Figure 3 As shown, Figure 3 The detection system 300 shown includes a processor 301 and a memory 303. The processor 301 and the memory 303 are connected, for example, via a bus 302. Optionally, the detection system 300 may further include a transceiver 304. It should be noted that in practical applications, the number of transceivers 304 is not limited to one, and the structure of the detection system 300 does not constitute a limitation on the embodiments of the present application.

[0063] Processor 301 can be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic device, transistor logic device, hardware component, or any combination thereof. It can implement or execute the various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 301 can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, etc.

[0064] Bus 302 may include a path for transmitting information between the above components. Bus 302 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. Bus 302 may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, Figure 3 The fact that only one line is used does not mean that there is only one bus or one type of bus.

[0065] The memory 303 may be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto.

[0066] The memory 303 is used to store application code for executing the solution of the present application, and the execution is controlled by the processor 301. The processor 301 is used to execute the application code stored in the memory 303 to implement the content shown in the above method embodiment.

[0067] The detection system includes, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Servers are also possible. Figure 3 The detection system shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0068] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents of the aforementioned method embodiment.

[0069] An embodiment of the present application provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the method in any of the above embodiments is implemented.

[0070] It should be understood that although the steps in the flowcharts of the accompanying drawings are shown in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a portion of the sub-steps or stages of other steps.

[0071] The above description is only part of the implementation methods of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A FPC patch detection method, characterized in that: include: Acquire multi-angle detection images, where the multi-angle detection images are images of the FPC to be detected at different viewing angles within the detection area; Based on the multi-angle detection image, determine the three-dimensional FPC image corresponding to the FPC to be detected, and identify the three-dimensional patch features contained in the three-dimensional FPC image; Based on the three-dimensional patch features, it is determined whether the FPC to be detected includes a deviation patch. If so, a warning prompt message is generated based on the deviation patch features corresponding to the deviation patch.

2. The FPC patch detection method according to claim 1, wherein: Also includes: Obtain the warning record information generated within the preset integration time period, and identify the deviation patch position and deviation patch characteristics corresponding to each warning record information; Determining a deviation strain region corresponding to each deviation patch position based on each deviation patch position and a corresponding deviation patch feature; Determine a planar FPC image based on the multi-angle detection image, and superimpose the deviation strain area corresponding to each deviation patch position on the planar FPC image to obtain a strain image; Identifying a strain region of interest contained in the strain image, and determining a patch of interest corresponding to the strain region of interest, wherein a pixel value of a region corresponding to the strain region of interest is higher than a first preset pixel threshold; The focus patch link is superimposed on the strain image to obtain a focus strain image, and the focus strain image is fed back.

3. The FPC patch detection method according to claim 2, wherein: Based on the deviation patch position and the corresponding deviation patch feature, the deviation strain area corresponding to the deviation patch position is determined, including: Obtaining a deviation patch element and an original patch position corresponding to the deviation patch position, and determining an original strain region corresponding to the original patch position according to the original patch position and the deviation patch element; Determine a corresponding observation area based on the deviation patch position, and obtain the number of other patch elements and other patch element types contained in the observation area; Obtaining an actual strain region at the deviation patch position, adjusting the actual strain region based on the number of other patch elements and other patch element types contained in the observation area, to obtain a current strain region corresponding to the deviation patch position; The deviation strain area corresponding to the deviation patch position is determined according to the original strain area and the current strain area.

4. The FPC patch detection method according to claim 3, characterized in that: Also includes: When the deviation patch position includes an associated deviation position, determining a first adjustment area based on a time difference between an associated deviation moment of the associated deviation position and a deviation moment of the deviation patch position, the time difference between the associated deviation moment of the associated deviation position and the deviation moment of the deviation patch position being lower than a preset time difference threshold; Obtaining a patch workload corresponding to the deviation patch position in a preset patch time period, and determining a second adjustment area based on the patch workload; The deviation strain region corresponding to the deviation patch position is adjusted based on the first adjustment area and the second adjustment area.

5. The FPC patch detection method according to claim 2, characterized in that: Also includes: Identifying a target strain region included in the strain image, and determining a target angle from the multi-angle detection image based on the target strain region, wherein a regional pixel value corresponding to the target strain region is higher than a second preset pixel threshold; Based on the target angle, a target patch process image and a preset standard patch process image corresponding to the target strain area are acquired; The preset patch process image is compared with the preset standard patch process image to determine patch differences, and the patch differences are fed back.

6. The FPC patch detection method according to claim 1, characterized in that: Also includes: When the multi-angle detection image contains a preset material feature, obtaining detection spectrum data of the FPC to be detected; Determining a main peak interval from the detected spectral data, and determining a target lighting parameter corresponding to the main peak interval based on the main peak interval and a preset lighting mapping relationship, wherein the preset lighting mapping relationship is a correspondence between the main peak interval and the target lighting parameter; The actual lighting parameters of the lighting device are optimized based on the lighting parameters.

7. A detection system, characterized in that: The detection system includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: execute an FPC patch detection method according to any one of claims 1-6.

8. A computer-readable storage medium, characterized in that include: A computer program is stored which can be loaded by a processor and executes an FPC patch detection method according to any one of claims 1 to 6.

9. A computer program product, characterized in that The invention comprises a computer program, which implements the steps of an FPC patch detection method according to any one of claims 1 to 6 when the computer program is executed by a processor.

Images