Flexible circuit board pad detection method and system

Abstract

The present invention provides a method and system for detecting solder pads of a flexible circuit board, wherein in the method for detecting solder pads of a flexible circuit board, by collecting a detection image of the flexible circuit board, the detection image is divided into at least one region of interest, the boundaries of the solder pads in each region of interest are extracted to obtain the external graphics of each solder pad in each region of interest, the first area and the first center coordinate of the external graphics of each solder pad are obtained, the symmetry of the solder pads in a solder pad group is calculated, the second center coordinate of the solder pad group is calculated according to the first center coordinate, the first area, the first center coordinate, the symmetry and the second center coordinate are compared with the first preset area, the first preset center coordinate, the preset symmetry and the second preset center coordinate one by one to determine the quality of the solder pads in the region of interest, the defects of the solder pads can be detected according to the position, size and symmetry of the solder pads, quantitative detection of the solder pads is achieved, and the efficiency and accuracy of solder pad detection are improved.

Description

Technical Field

[0001] The present invention relates to the field of quality inspection of flexible circuit boards, and in particular to a method and system for inspecting solder pads of flexible circuit boards. Background Art

[0002] Flexible Printed Circuit (FPC) has been widely used in electronic products, such as smart phones, LCD TVs, tablet computers, new energy vehicles, etc. With the development of science and technology, FPC is also developing in the direction of thinner and higher density, resulting in an increase in its production defects and further increase in the difficulty of detection. At present, there are three main ways to detect defects in FPC: manual visual inspection, scanning probe and high-precision automatic optical inspection method. At present, most domestic manufacturers still use manual visual inspection method, which requires workers to use a magnifying glass to conduct a comprehensive and careful inspection of the entire substrate, which is easy to cause missed inspections, low efficiency, and greatly increase labor costs; scanning probe detection technology uses the electron beam emitted by the electron gun to converge into a thin electron beam through the optical system and focus on the sample surface, and repeatedly scans the sample surface to generate various information. This method can obtain clearer images, but the efficiency is low, and the equipment cost is high, making it difficult to promote; compared with the first two detection methods, automatic optical detection technology has obvious advantages, which can not only greatly improve the detection speed, but also has low cost. Although there are many automatic optical inspection equipment now, they can basically only detect some appearance defects of FPC pads, such as short circuits, short connections and burrs, and cannot perform quantitative inspection of pads. Summary of the invention

[0003] The object of the present invention is to provide a method and system for detecting solder pads of a flexible circuit board, which can perform quantitative detection on the solder pads of the flexible circuit board and improve the efficiency and accuracy of solder pad detection.

[0004] In order to achieve the above object, the present invention provides a method for detecting a pad of a flexible circuit board, comprising:

[0005] Collect inspection images of flexible circuit boards;

[0006] Divide the detection image into at least one region of interest, wherein the region of interest includes a pad group, and the pad group includes at least two pads arranged linearly at intervals;

[0007] Extracting the boundaries of each of the pads in each of the regions of interest, and acquiring the external graphics of each of the pads in each of the regions of interest according to the extracted boundaries;

[0008] Calculating the first area and the first center coordinate of the circumscribed figure of each of the pads in each of the regions of interest, calculating the area ratio between the circumscribed figures of the pads in the pad group to obtain the symmetry of the pads, and calculating the second center coordinate of the pad group according to the first center coordinate of the pad in the pad group;

[0009] The first area, the first center coordinate, the symmetry and the second center coordinate are compared with preset parameters to determine the pad quality of the area of ​​interest, wherein the preset parameters include a first preset area and a first preset center coordinate of the circumscribed graphic of the pad, a preset symmetry of the pad within the pad group, and a second preset center coordinate of the pad group.

[0010] Optionally, the pad group includes a window area, the pads are linearly spaced in the window area, the shape of the window area is rectangular, and the preset parameters also include a third preset center coordinate of the circumscribed figure of the window area and a preset deviation value between the third preset center coordinate and the second preset center coordinate;

[0011] The method further comprises:

[0012] Extracting the boundary of the windowing area and obtaining the external graphics of the windowing area according to the boundary;

[0013] Calculating the third center coordinates of the window opening area;

[0014] Calculating the deviation value between the third center coordinate and the second center coordinate;

[0015] The deviation value is compared with the preset deviation value.

[0016] Optionally, the preset parameters further include a second preset area, and the second preset area is a set area of ​​the window opening area;

[0017] The method further comprises:

[0018] Acquire a second area of ​​the window area according to an external graphic of the window area in the pad group;

[0019] The second area of ​​the window opening region is compared with the second preset area.

[0020] Optionally, dividing the detection image into at least one region of interest includes:

[0021] Performing threshold segmentation on the detection image according to a preset threshold;

[0022] Morphological processing is performed on the detection image after the threshold segmentation to divide the detection image into at least one region of interest.

[0023] Optionally, the collecting the detection image of the flexible circuit board includes:

[0024] capturing at least two images based on the movement of the photographing unit;

[0025] The images are spliced ​​to obtain the detection image.

[0026] Optionally, the shooting unit moves along a first direction and a second direction to capture images of the flexible circuit board, the first direction is perpendicular to the second direction, and the stitching of the images to obtain the detection image includes:

[0027] Establishing a rectangular coordinate system with a specific point of the first image captured by the photographing unit as the origin and the moving direction of the photographing unit as the coordinate axis;

[0028] Taking the corresponding positions in each of the images as feature points, and obtaining the coordinates of the feature points of the first image;

[0029] Obtaining coordinates of feature points of other images in the rectangular coordinate system according to the size of each image and the coordinates of feature points of the first image;

[0030] Each of the images is spliced ​​in the rectangular coordinate system according to the coordinates of the feature points of each of the images.

[0031] Optionally, the collecting the detection image of the flexible circuit board also includes:

[0032] Performing smoothing filtering on the image to remove noise;

[0033] The contrast of the image is enhanced.

[0034] Optionally, identification points are provided on the flexible printed circuit board, and a coordinate system is established according to the identification points to obtain the first center coordinates and the second center coordinates.

[0035] Optionally, the flexible circuit board pad detection method further includes:

[0036] A Gerber file of the flexible circuit board is imported, wherein the Gerber file includes the preset parameters.

[0037] In order to achieve the above object, the present invention also provides a flexible circuit board pad detection system, comprising:

[0038] An acquisition module, wherein the acquisition module is used to acquire a detection image of the flexible circuit board;

[0039] An image processing module, wherein the image processing module is used to divide the detection image into at least one region of interest, wherein the region of interest includes a pad group, and the pad group includes at least two pads arranged at a linear interval;

[0040] A boundary extraction module, the boundary extraction module is used to extract the boundary of each pad in each region of interest, and obtain the external graphics of each pad in each region of interest according to the extracted boundary;

[0041] A processing module, the processing module is used to calculate the first area and the first center coordinate of the circumscribed figure of each of the pads in each of the regions of interest, calculate the area ratio between the circumscribed figures of the pads in the pad group to obtain the symmetry of the pads, and calculate the second center coordinate of the pad group according to the first center coordinate of the pad in the pad group;

[0042] A judgment module, the judgment module is used to compare the first area, the first center coordinate, the symmetry and the second center coordinate with preset parameters to determine the pad quality of the area of ​​interest, wherein the preset parameters include a first preset area and a first preset center coordinate of the external graphic of the pad, a preset symmetry of the pad in the pad group, and a second preset center coordinate of the pad group.

[0043] In the flexible circuit board pad detection method of the present invention, by collecting a detection image of the flexible circuit board, the detection image is divided into at least one region of interest, the boundary of the pad in each region of interest is extracted, and the circumscribed figure of each pad in each region of interest is obtained according to the extracted boundary, and the first area and the first center coordinate of the circumscribed figure of each pad in each region of interest are obtained, and the area ratio between the circumscribed figures of the pads in the pad group is calculated to obtain the symmetry of the pad, and the second center coordinate of the pad group is calculated according to the first center coordinate. The first area, the first center coordinate, the symmetry and the second center coordinate are compared with the first preset area, the first preset center coordinate, the preset symmetry and the second preset center coordinate to determine the pad quality of the region of interest, and the defects of the pad can be detected according to the position, size and symmetry of the pad, so as to realize quantitative detection of the pad and improve the efficiency and accuracy of pad detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of a method for detecting pads of a flexible circuit board according to an embodiment of the present invention.

[0045] Figure 2 It is a flow chart of detecting the window area according to an embodiment of the present invention.

[0046] Figure 3 yes Figure 1Flowchart of step S200 in FIG.

[0047] Figure 4 is an image captured by the shooting unit of the embodiment of the present invention.

[0048] Figure 5 It is a detection image after morphological processing in the embodiment of the present invention.

[0049] Figure 6a and Figure 6b It is a schematic diagram of stitching images according to an embodiment of the present invention.

[0050] Figure 7 It is a module diagram of a flexible circuit board pad detection system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0051] In order to explain the technical content, structural features and achieved effects of the present invention in detail, the following is a detailed description in conjunction with the implementation modes and the accompanying drawings.

[0052] In the present invention, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0053] In addition, the technical solutions between the various embodiments of the present invention can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0054] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0055] The flexible circuit board pad detection method of the present invention is applicable to flexible circuit boards in which pads in the same pad group have the same size, the same interval and are linearly arranged.

[0056] like Figure 1 As shown, an embodiment of the present invention provides a method for detecting a pad of a flexible circuit board, comprising the following steps:

[0057] S100: collecting a detection image of the flexible circuit board.

[0058] Wherein, at least two images (such as Figure 4The captured images are spliced ​​to obtain a detection image of the entire flexible circuit board. Since the relative movement speed of the shooting unit and the flexible circuit board is not completely uniform, when the movement speed and the line frequency of the shooting unit do not match, the image captured by the shooting unit will be distorted, so the captured image needs to be corrected according to parameters such as the movement speed, resolution, focal length, and object distance. Since the distortion correction of the image taken by the shooting unit belongs to the prior art, it will not be repeated here.

[0059] It is understandable that the shooting unit can be a camera. In order to improve the accuracy of the camera's image acquisition, the camera can be calibrated before starting to acquire images, and the camera's internal parameters, external parameters and distortion parameters can be solved to prevent the acquired images from being deformed. Image preprocessing can be performed before or after image stitching is completed.

[0060] It is understandable that the shooting unit can move along the first direction and the second direction to capture images of the flexible circuit board, and the first direction is perpendicular to the second direction. In order to improve the accuracy of image stitching, the captured images can be converted to the same coordinate system for stitching. Specifically, Figure 6a / 6b, the corresponding position in each image of the first image captured by the shooting unit is taken as the feature point, and the coordinates of the feature point of the first image are obtained; the coordinates of the feature points of other images in the rectangular coordinate system are obtained according to the size of each image and the coordinates of the feature points of the first image, and each image is spliced ​​in the rectangular coordinate system according to the coordinates of the feature points of each image.

[0061] In some specific examples, the coordinates of the feature points of the first image are (x, y), and the length of each image is h, and the width is w. The coordinates of the feature points of the images collected by moving along the first direction are (x, y), (x, y+h), (x, y+2h)…(x, y+nh), that is, the shooting unit moves h along the first direction to collect an image once; after the shooting unit moves s along the second direction, the coordinates of the feature points of the images continued to be collected along the first direction are (x+s, y), (x+s, y+h), (x+s , y+2h), (x+s, y+3h)…(x+s, y+nh); after the shooting unit moves s along the second direction, the coordinates of the feature points of the images continued to be collected along the first direction are (x+2s, y), (x+2s, y+h), (x+2s, y+2h), (x+2s, y+3h)…(x+2s, y+nh), and so on, to obtain the coordinates of the feature points of each image, so as to splice the images in the rectangular coordinate system according to the coordinates of the feature points of each image to obtain a complete detection image.

[0062] More specifically, if Figure 6aAs shown in FIG. 6b, the lower left corner point of the first image is taken as the specific point of the first image, and the specific point of each image is its lower left corner point, which is also a feature point. Assume that the length of each image is h and the width is w, the coordinate of the feature point of the first image is (0,0), and the coordinates of the feature points of the image collected by moving along the first direction are (0,0), (0,h), (0,2h), (0,3h)…(0,nh) respectively; after the shooting unit moves s along the second direction, the coordinates of the feature points of the image collected along the first direction are (s,0), ​​(s,h), (s,2h), (s,3h)…(s,nh) respectively; after the shooting unit moves s along the second direction again, the coordinates of the feature points of the image collected along the first direction are (2s,0), ​​(2s,h), (2s,2h), (2s,3h)…(2s,nh) respectively, and so on, the coordinates of the feature points of each image are obtained, so that the images are spliced ​​in the rectangular coordinate system according to the coordinates of the feature points of each image to obtain a complete detection image. In the above specific example, each image captured by the shooting unit along the first direction does not have any repeated shooting parts, and each image shot along the second direction may have or may not have any repeated shooting parts. When there are repeated shooting parts, the repeated parts can be fused or the overlapping parts of one of the images can be removed for splicing, etc.

[0063] Of course, in some other specific examples, each image captured by the shooting unit along the first direction may also have a repeated part. When there is a repeated part, the coordinate acquisition method and image stitching method of the specific points of each image captured along the first direction are the same as those of the above-mentioned images captured along the second direction.

[0064] Of course, for a shooting unit whose field of view can completely accommodate a complete flexible circuit board, the detection image may also be an image obtained by shooting the flexible circuit board once.

[0065] Further, in order to eliminate irrelevant information in the collected image, enhance the detectability of relevant information and simplify the data information in the image, the collected image can be preprocessed, specifically including: performing smoothing filtering on the collected image to remove noise in the image; enhancing the contrast of the image. Since the pad and the substrate in the flexible circuit board have color difference, the above preprocessing can make the pad display in the collected image more obvious, and improve the reliability of pad recognition. In some specific examples, the contrast of the image can be enhanced by image multiplication. For example, in the Halcon environment, the mult_image operator is used to implement g'=g1*g2*Mult+Add, where (g1, g2) represent the pixel values ​​of the input image respectively, g' is the output image (that is, the detection image after contrast enhancement), Mult is the multiplier factor, and Add is the offset value, which increases the contrast of the image, that is, the whiter the white, the blacker the black, and the fewer pixels of the intermediate gray value in the output image. Of course, in the embodiment of the present invention, the contrast of the detection image can also be enhanced by other methods known to those skilled in the art, for example, by using histogram equalization, grayscale stretching, etc., and the embodiment of the present invention is not limited to this.

[0066] S200, dividing the detection image into at least one region of interest, where the region of interest includes a pad group, and the pad group includes at least two pads arranged linearly at intervals.

[0067] like Figure 4 As shown in the figure, the region of interest is the boxed area shown in the figure. Of course, the region of interest can also be Figure 4 The area of ​​the selected area can be a larger range, or it can be an area in which multiple pad groups are selected. Among them, the pads in the pad group can be pads used to weld the same part in the flexible circuit board, or pads for welding two opposite pins of the same part, or pads with a smaller spacing in the flexible circuit board, or pads with the same spacing in the same column or row, etc. The present invention does not limit the pads in the pad group. By dividing the detection image into an area of ​​interest containing a pad group, image recognition and feature extraction are no longer performed on other areas in the detection image, which can reduce the amount of calculation to improve the efficiency of pad detection.

[0068] S300 , extracting the boundaries of each pad in each region of interest, and obtaining the external graphics of each pad in each region of interest according to the extracted boundaries.

[0069] Among them, the boundary of each pad can be extracted through edge detection methods such as Canny edge detection, differential edge detection, Roberts edge detection, and Sobel edge detection.

[0070] S400, calculating the first area and the first center coordinate of the circumscribed figure of each pad in each region of interest, calculating the area ratio between the circumscribed figures of the pads in the pad group to obtain the symmetry of the pad, and calculating the second center coordinate of the pad group according to the first center coordinate of the pad in the pad group.

[0071] The first area of ​​the circumscribed graphics of each pad refers to the area of ​​the area defined by the circumscribed graphics of each pad, not the sum of the areas of the circumscribed graphics of all pads, but the area of ​​the area enclosed by the circumscribed graphics of a single pad; the first center coordinate is the center point of the area enclosed by the circumscribed graphics of a single pad (such as Figure 4 The second center coordinate refers to the center point of all pads in the pad group (such as Figure 4 The degree of symmetry refers to the ratio of the first areas of the pads in the pad group. For example, when the pad group includes two pads, the second center coordinates are the center coordinates between the circumscribed figures of the two pads. When the pad group includes three pads, the first center coordinates are the coordinates of the center point between the circumscribed figures of the three pads (the center point of the middle pad). The degree of symmetry refers to the ratio of the first areas of the pads in the pad group. For example, when the pad group includes two pads, the degree of symmetry refers to the ratio of the first areas of the two pads in the pad group. When the pad group includes three pads, the degree of symmetry refers to the ratio of the first areas between each two adjacent pads or the ratio of the first areas between two of the three pads, and so on.

[0072] In order to obtain the first center coordinate and the second center coordinate, a marking point can be set on the flexible circuit board, and a coordinate system can be established according to the marking point in the captured detection image, so as to obtain the first center coordinate and the second center coordinate. Figure 5 As shown, the identification point can be set at the upper left corner of the flexible circuit board, identify the identification point in the detection image and establish a coordinate system with the identification point as the origin (not shown in the figure), so as to obtain the first center coordinate of each pad and the second center coordinate of each pad group. The second center coordinate can be obtained according to the first center coordinate of each pad in the pad group, for example, Figure 5 The first center coordinates of the two pads are (X1, Y1) and (X2, Y2) respectively. Since the second center coordinates are the coordinates of the center points of the two pads, it can be concluded that the second center coordinates (X3, Y3) are ((X2-X1) / 2+X1, (Y2-Y1) / 2+Y1). Figure 5 As shown in , X1 and X2 are equal, therefore, the second center coordinate is (X1, (Y2-Y1) / 2+Y1), that is, X3=X1=X2, Y3=(Y2-Y1) / 2+Y1.

[0073] S500, comparing the first area, the first center coordinate, the symmetry and the second center coordinate with preset parameters to determine the pad quality of the area of ​​interest, wherein the preset parameters include a first preset area and a first preset center coordinate of the circumscribed graphic of the pad, a preset symmetry of the pads in the pad group, and a second preset center coordinate of the pad group.

[0074] It can be understood that by comparing the calculated first area, first center coordinate, second center coordinate and symmetry with the first preset area, first preset center coordinate, second preset center coordinate and preset symmetry one by one, the pad quality of the area of ​​interest can be obtained based on the comparison result.

[0075] The preset parameter can be a preset range, and the pad quality is considered qualified when each calculated parameter falls within the corresponding preset parameter range. When any parameter obtained is not within the corresponding preset parameter range, the pad is considered unqualified and recorded; of course, the preset parameter can also be a fixed value, and the preset parameter, the allowable error range and the calculated parameter are compared. For example, in general, the pads in the same pad group have the same size, and the ratio of the area between the external graphics of the pads in the pad group is 1 under standard conditions, that is, the preset symmetry of the pad can be 1. Of course, the preset symmetry can also be a range value, such as [0.98, 1.02], etc. When the pad group includes two pads, the ratio of the area between the external graphics of the two pads is calculated to obtain the symmetry of the pad. When the symmetry falls within [0.98, 1.02], the symmetry of the pad group is considered qualified, otherwise the symmetry of the pad group is considered unqualified.

[0076] Generally speaking, a window area is provided on the flexible circuit board, and the pads are arranged in the window area, that is, the pad group includes the window area and the pads arranged in the window area, and the pads in the pad group can be pads arranged in the same window area.

[0077] Specifically, the same pad group of the flexible circuit board also includes a window area (such as Figure 4 As shown, generally speaking, one pad group is provided with one window area), the pads are linearly spaced in the window area, and the shape of the window area is a rectangle; the preset parameters also include the third preset center coordinates of the external figure of the window area and the preset deviation value between the third preset center coordinates and the second preset center coordinates, so, if Figure 2 As shown, the flexible circuit board pad detection method may also include:

[0078] S600: extracting the boundary of the windowing area and obtaining the external graphics of the windowing area according to the boundary.

[0079] S700, calculating the third center coordinates located in the window opening area.

[0080] S800: Calculate the deviation between the third center coordinate and the second center coordinate.

[0081] S900: Compare the deviation value with a preset deviation value.

[0082] Similarly, the third center coordinate refers to the center point of the area enclosed by the circumscribed figure of the window area (such as Figure 5 The coordinates of the third center shown); according to the properties of the flexible circuit board, the center points of all the pads in the pad group coincide with the center points of the window area, so the second center coordinates and the third center coordinates in the same pad group are the same, that is, the preset deviation value can be 0. Of course, it can also be a range close to 0 such as [-0.03, 0.03], [-0.05, 0.05]. Compare the deviation value with the preset deviation value. When the deviation value is the same as the preset deviation value or the deviation value falls within the preset deviation value range, the window area of ​​the pad group and the pad deviation are qualified, otherwise they are unqualified. Among them, the area of ​​interest can be the area defined by the external graphics formed by the boundary of the window area (such as Figure 4 ).

[0083] Furthermore, the preset parameters also include a second preset area, and the second preset area is a set area of ​​the window area; the flexible circuit board pad detection method also includes:

[0084] Acquire a second area of ​​the window area according to an external graphic of the window area in the pad group;

[0085] The second area of ​​the window opening region is compared with the second preset area respectively.

[0086] The second area refers to the area of ​​the region defined by the circumscribed graphics of the window area in the pad group; whether the area of ​​the window area of ​​the pad group is qualified is determined by comparing the calculated second area with the second preset area.

[0087] In order to conveniently obtain the preset parameters, the Gerber file of the flexible circuit board can be directly imported. The Gerber file includes the preset parameters, so that the preset parameters can be directly obtained from the Gerber file to make a qualified judgment on the pad group.

[0088] In the flexible circuit board pad detection method in the embodiment of the present invention, by collecting a detection image of the flexible circuit board, the detection image is divided into at least one region of interest, the boundary of the pad in each region of interest is extracted, and the circumscribed figure of each pad in each region of interest is obtained according to the extracted boundary, and the first area and the first center coordinate of the circumscribed figure of each pad in each region of interest are obtained, and the area ratio between the circumscribed figures of the pads in the pad group is calculated to obtain the symmetry of the pad, and the second center coordinate of the pad group is calculated according to the first center coordinate. The first area, the first center coordinate, the symmetry and the second center coordinate are compared with the first preset area, the first preset center coordinate, the preset symmetry and the second preset center coordinate to determine the pad quality of the region of interest, and the defects of the pad can be detected according to the position, size and symmetry of the pad, so as to realize quantitative detection of the pad and improve the efficiency and accuracy of pad detection.

[0089] Among them, the flexible circuit board pad detection method of the embodiment of the present invention can be applied to the pad quality detection of the Mini LED flexible circuit board.

[0090] like Figure 3 As shown, step S200 may specifically include:

[0091] S210 , performing threshold segmentation on the detection image according to a preset threshold.

[0092] like Figure 4 As shown, since the color of the pad in the flexible circuit board is white and the color of the window is black, the preset threshold value can be used to perform threshold segmentation on the detection image, so as to extract features of the pad and window in the detection image. The preset threshold value can be one or more. The detection image is divided into several parts according to the preset threshold value, and the pixels belonging to the same part are considered to be the same object. The grayscale values ​​of the pads in the detection image are the same or similar, and the grayscale values ​​of the window are the same or similar. Therefore, the pads and window can be extracted (of course, when the area of ​​interest only includes the pads, only the pads can be extracted). For example, the grayscale histogram and the feature histogram can be used to extract features of the pads and window in the detection image through global threshold segmentation.

[0093] S220: Perform morphological processing on the detection image after the threshold segmentation to divide the detection image into at least one region of interest.

[0094] like Figure 5 As shown, through threshold segmentation, the features of the pads and windows of the detection image can be extracted, so that the pads and windows are clearly displayed in the detection image, and then morphological processing is performed to outline the regions of interest of the detection image according to the boundaries of the pads and windows, and each region of interest includes a pad group.

[0095] like Figure 7 As shown, an embodiment of the present invention further provides a flexible circuit board pad detection system, comprising:

[0096] The acquisition module 100 is used to acquire the detection image of the flexible circuit board.

[0097] The acquisition module 100 may include a camera and an image control unit, and the image control unit may be used to control the camera to acquire images of the flexible circuit board; for example, the image control unit may include a driving mechanism, and the driving mechanism is used to drive the relative movement between the camera and the flexible circuit board, so as to realize the image acquisition of the flexible circuit board; specifically, the image control unit may include a control end, a driving mechanism, a mechanical platform and a vacuum unit, wherein the driving mechanism may include a driving motor, and the driving motor is controlled by the control end, the camera may be arranged above the mechanical platform, the mechanical platform is used to place the flexible circuit board, the vacuum unit is used to fix the flexible circuit board to prevent the displacement during the movement process, the driving motor may be used to drive the mechanical platform to move to the photographing area, when the mechanical platform moves the flexible circuit board to the photographing area, the driving motor may drive the camera to move to shoot the flexible circuit board, and the driving motor driving the mechanical platform to move and the driving motor driving the camera to move may not be the same; wherein the camera may be a linear array camera, and the image control unit may also include a grating ruler, and the camera may be triggered by the pulse signal sent by the grating ruler to acquire images. It is understandable that the control end may be provided with a human-computer interaction interface, parameter setting may be performed, or the detection image may be displayed, etc.

[0098] The image processing module 200 is used to divide the detection image into at least one region of interest, the region of interest includes a pad group, and the pad group includes at least two pads arranged at a linear interval.

[0099] The boundary extraction module 300 is used to extract the boundary of each pad in each region of interest, and obtain the external graphics of each pad in each region of interest according to the extracted boundary.

[0100] Processing module 400, processing module 400 is used to calculate the first area and first center coordinates of the circumscribed graphics of each pad in each area of ​​interest, calculate the area ratio between the circumscribed graphics of the pads in the pad group to obtain the symmetry of the pad, and calculate the second center coordinates of the pad group based on the first center coordinates of the pads in the pad group.

[0101] Judgment module 500, judgment module 500 is used to compare the first area, the first center coordinate, the symmetry and the second center coordinate with preset parameters to determine the pad quality of the area of ​​interest, wherein the preset parameters include a first preset area and a first preset center coordinate of the circumscribed graphic of the pad, a preset symmetry of the pads in the pad group, and a second preset center coordinate of the pad group.

[0102] The above disclosure is only a preferred embodiment of the present invention, which is intended to facilitate the understanding and implementation of the present invention by those skilled in the art. It certainly cannot be used to limit the scope of rights of the present invention. Therefore, equivalent changes made according to the scope of the patent application of the present invention still fall within the scope covered by the present invention.

Claims

1. A method for detecting pads of a flexible circuit board, characterized in that: include: Collect inspection images of flexible circuit boards; Divide the detection image into at least one region of interest, wherein the region of interest includes a pad group, and the pad group includes at least two pads arranged linearly at intervals; Extracting the boundaries of each of the pads in each of the regions of interest, and acquiring the external graphics of each of the pads in each of the regions of interest according to the extracted boundaries; Calculating the first area and the first center coordinate of the circumscribed figure of each of the pads in each of the regions of interest, calculating the area ratio between the circumscribed figures of the pads in the pad group to obtain the symmetry of the pads, and calculating the second center coordinate of the pad group according to the first center coordinate of the pad in the pad group; Comparing the first area, the first center coordinate, the symmetry, and the second center coordinate with preset parameters to determine the pad quality of the region of interest, wherein the preset parameters include a first preset area and a first preset center coordinate of a circumscribed pattern of the pad, a preset symmetry of the pad in the pad group, and a second preset center coordinate of the pad group; The pad group includes a window area, the pads are linearly spaced in the window area, the window area is rectangular in shape, and the preset parameters further include a third preset center coordinate of a circumscribed figure of the window area and a preset deviation value between the third preset center coordinate and the second preset center coordinate; The method further comprises: Extracting the boundary of the windowing area and obtaining the external graphics of the windowing area according to the boundary; Calculating the third center coordinates of the window opening area; Calculating a deviation value between the third center coordinate and the second center coordinate; The deviation value is compared with the preset deviation value.

2. The method for detecting pads of a flexible circuit board according to claim 1, characterized in that: The preset parameters also include a second preset area, which is a set area of ​​the window opening area; The method further comprises: Acquire a second area of ​​the window area according to an external graphic of the window area in the pad group; The second area of ​​the window opening region is compared with the second preset area.

3. The method for detecting pads of a flexible circuit board according to claim 1, characterized in that: The dividing the detection image into at least one region of interest comprises: Performing threshold segmentation on the detection image according to a preset threshold; Morphological processing is performed on the detection image after the threshold segmentation to divide the detection image into at least one region of interest.

4. The method for detecting pads of a flexible circuit board according to claim 1, characterized in that: The collecting of the detection image of the flexible circuit board comprises: capturing at least two images based on the movement of the photographing unit; The images are spliced ​​to obtain the detection image.

5. The method for detecting pads of a flexible circuit board according to claim 4, characterized in that: The shooting unit moves along a first direction and a second direction to capture an image of the flexible circuit board, the first direction is perpendicular to the second direction, and the images are spliced ​​to obtain the detection image, including: Establishing a rectangular coordinate system with a specific point of the first image captured by the photographing unit as the origin and the moving direction of the photographing unit as the coordinate axis; Taking the corresponding positions in each of the images as feature points, and obtaining the coordinates of the feature points of the first image; Obtaining coordinates of feature points of other images in the rectangular coordinate system according to the size of each image and the coordinates of feature points of the first image; Each of the images is spliced ​​in the rectangular coordinate system according to the coordinates of the feature points of each of the images.

6. The method for detecting pads of a flexible circuit board according to claim 4, characterized in that: The collecting of the detection image of the flexible circuit board also includes: Performing smoothing filtering on the image to remove noise; The contrast of the image is enhanced.

7. The method for detecting pads of a flexible circuit board according to claim 1, characterized in that: The flexible circuit board is provided with identification points, and a coordinate system is established according to the identification points to obtain the first center coordinates and the second center coordinates.

8. The method for detecting pads of a flexible circuit board according to claim 1, characterized in that: Also includes: A Gerber file of the flexible circuit board is imported, wherein the Gerber file includes the preset parameters.

9. A flexible circuit board pad detection system, used to execute the flexible circuit board pad detection method according to claim 1, characterized in that: include: An acquisition module, wherein the acquisition module is used to acquire a detection image of the flexible circuit board; An image processing module, wherein the image processing module is used to divide the detection image into at least one region of interest, wherein the region of interest includes a pad group, and the pad group includes at least two pads arranged at a linear interval; A boundary extraction module, the boundary extraction module is used to extract the boundary of each pad in each region of interest, and obtain the external graphics of each pad in each region of interest according to the extracted boundary; A processing module, the processing module is used to calculate the first area and the first center coordinate of the circumscribed figure of each of the pads in each of the regions of interest, calculate the area ratio between the circumscribed figures of the pads in the pad group to obtain the symmetry of the pads, and calculate the second center coordinate of the pad group according to the first center coordinate of the pad in the pad group; A judgment module, the judgment module is used to compare the first area, the first center coordinate, the symmetry and the second center coordinate with preset parameters to determine the pad quality of the area of ​​interest, wherein the preset parameters include a first preset area and a first preset center coordinate of the external graphic of the pad, a preset symmetry of the pad in the pad group, and a second preset center coordinate of the pad group.

Images