Lamp panel detection method, device, equipment, storage medium and program product

Abstract

The invention relates to a lamp panel detection method and device, equipment, a storage medium and a program product. The method comprises the following steps: acquiring multiple groups of to-be-detected area standard images and multiple groups of to-be-detected area scanning images of a target lamp panel, wherein the to-be-detected area standard images and the to-be-detected area scanning images are in one-to-one correspondence; a target area standard image is positioned from the to-be-detected area standard images, and a target area scanning image corresponding to the target area standard image is positioned from the to-be-detected area scanning images; aligning the standard image of the target area with the scanning image of the target area; and detecting the target area scanning image based on the aligned target area standard image. By adopting the method, false detection can be reduced.

Description

Technical Field

[0001] The present application relates to the technical field of printed circuit boards, and in particular to a method, device, equipment, storage medium and program product for detecting a light board. Background Art

[0002] With the rapid development of display technology, the quality and reliability of PCB (Printed Circuit Board) light board, as the core component of display technology, have become important concerns in the manufacturing process.

[0003] In traditional technology, before defect detection of PCB light board is carried out, it is usually necessary to align the entire board first.

[0004] However, when there are local defects on the light board, it may cause the positions of other areas on the light board without defects to shift as a whole. In this way, when defect detection is performed after the entire board is aligned, a large number of false detections will occur. Summary of the invention

[0005] Based on this, it is necessary to provide a light board detection method, device, equipment, storage medium and program product that can reduce false detection in response to the above technical problems.

[0006] In a first aspect, the present application provides a light board detection method, comprising:

[0007] Acquire multiple groups of standard images of the area to be tested and multiple groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one;

[0008] Locate the target area standard image from each of the test area standard images, and locate the target area scan image corresponding to the target area standard image from each of the test area scan images;

[0009] Aligning the target area standard image with the target area scanned image;

[0010] The target area scanned image is detected based on the aligned target area standard image.

[0011] In one embodiment, the target area standard image includes a plurality of standard images of pads to be tested, the target area scan image includes a plurality of scan images of pads to be tested, and the standard images of pads to be tested correspond to the scan images of pads to be tested one by one;

[0012] The detection of the target area scanned image based on the aligned target area standard image includes:

[0013] Selecting a target pad standard image from each of the pad standard images to be tested, and selecting a target pad scanning image corresponding to the target pad standard image from each of the pad scanning images to be tested;

[0014] Perform pad alignment between the target pad standard image and the target pad scan image;

[0015] The target pad scanning image is detected based on the target pad standard image after the pad is aligned.

[0016] In one embodiment, obtaining a plurality of groups of standard images of the area to be tested and a plurality of groups of scanned images of the area to be tested of the target light board includes:

[0017] Acquire standard image and scanned image of target light board;

[0018] Perform global alignment between the whole standard image and the whole scanned image;

[0019] Perform missing detection on the scanned image based on the standard image after global alignment to obtain missing position information;

[0020] The position information of the test area of ​​each standard image of the test area in the standard image after global alignment is obtained, and based on the missing position information and the position information of the test area, the scanned image is divided into multiple scanned images of the test area, and the scanned images of the test area correspond to the standard images of the test area one by one.

[0021] In one embodiment, globally aligning the entirety of the standard image with the entirety of the scanned image includes:

[0022] Based on the standard image, the standard position of the vertex of the target light board is detected, and based on the scanned image, the scanning position of the vertex of the target light board is detected;

[0023] Based on the standard position of the light board vertex and the scanning position of the light board vertex, the entire standard image and the entire scanned image are globally aligned.

[0024] In one of the embodiments, the target light board includes a plurality of solder pads;

[0025] Align the target area standard image with the target area scanned image, including:

[0026] Based on the standard image after global alignment, detecting the standard position of the pad center of at least one pad, and based on the scanned image after global alignment, detecting the pad center scanned position of at least one pad;

[0027] Based on the pad center standard position and the pad center scan position, the target area standard image and the target area scan image are aligned.

[0028] In one embodiment, after detecting the target area scanned image based on the aligned target area standard image, the method further includes:

[0029] The target area standard image is determined as the inspected area standard image, and the process returns to the step of locating the target area standard image from among the inspected area standard images.

[0030] In a second aspect, the present application also provides a light board detection device, comprising:

[0031] An acquisition module is used to acquire multiple groups of standard images of the area to be tested and multiple groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one;

[0032] A positioning module, used to locate the target area standard image from each of the test area standard images, and to locate the target area scanned image corresponding to the target area standard image from each of the test area scanned images;

[0033] An alignment module, used for aligning the target area standard image with the target area scanned image;

[0034] The detection module is used to detect the target area scanned image based on the aligned target area standard image.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0036] Acquire multiple groups of standard images of the area to be tested and multiple groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one;

[0037] Locate the target area standard image from each of the test area standard images, and locate the target area scan image corresponding to the target area standard image from each of the test area scan images;

[0038] Aligning the target area standard image with the target area scanned image;

[0039] The target area scanned image is detected based on the aligned target area standard image.

[0040] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the following steps are implemented:

[0041] Acquire multiple groups of standard images of the area to be tested and multiple groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one;

[0042] Locate the target area standard image from each of the test area standard images, and locate the target area scan image corresponding to the target area standard image from each of the test area scan images;

[0043] Aligning the target area standard image with the target area scanned image;

[0044] The target area scanned image is detected based on the aligned target area standard image.

[0045] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0046] Acquire multiple groups of standard images of the area to be tested and multiple groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one;

[0047] Locate the target area standard image from each of the test area standard images, and locate the target area scan image corresponding to the target area standard image from each of the test area scan images;

[0048] Aligning the target area standard image with the target area scanned image;

[0049] The target area scanned image is detected based on the aligned target area standard image.

[0050] The above-mentioned light board detection method, device, equipment, storage medium and program product first obtain multiple groups of standard images of the target light board's test area and multiple groups of scanned images of the test area. The standard images of the test area can represent the detection standard of the target light board, and the scanned images of the test area can represent the actual situation of the target light board; then, by aligning the standard images of the target area with the scanned images of the target area, independent alignment of the sub-areas is achieved; then, the scanned images of the target area are detected based on the aligned standard images of the target area. In this way, compared with the method of aligning the entire board and then performing defect detection, the method of independent alignment of the sub-areas can effectively correct the overall offset of each area due to the influence of other areas, reduce mutual interference between areas, thereby improving the accuracy of light board detection, and reducing good products being mistakenly detected as defective products, thereby reducing unnecessary rework operations caused by false detection, saving human resources and time resources, and reducing the situation where good products are discarded due to false detection, reducing waste, and reducing costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 is a schematic flow chart of a light board detection method in one embodiment;

[0053] Figure 2 is a schematic flow chart of a light board detection method in another embodiment;

[0054] Figure 3 is a schematic diagram of a standard image in one embodiment;

[0055] Figure 4 is a schematic diagram of a scanned image in one embodiment;

[0056] Figure 5 is a structural block diagram of a light board detection device in one embodiment;

[0057] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0059] In an exemplary embodiment, Figure 1 As shown, a light board detection method is provided. This embodiment takes the method applied to a terminal as an example, wherein the terminal may be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things devices may be smart speakers, smart TVs, smart air conditioners, smart car-mounted devices, projection devices, etc. Portable wearable devices may be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted devices may be virtual reality (VR) devices, augmented reality (AR) devices, smart glasses, etc. It can be understood that the method can also be applied to servers, and can also be applied to systems including terminals and servers, and implemented through the interaction between terminals and servers. In this embodiment, the method includes the following steps S10-S40. Among them:

[0060] Step S10, obtaining multiple groups of standard images of the area to be tested and multiple groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one.

[0061] It should be noted that the PCB light board refers to the PCB board used to connect lamp beads. Light board detection is mainly achieved by comparing the scanned image of the light board captured by the camera with the standard image of the light board. Since a light board usually contains thousands of pads (pads), these pads are arranged in an array row by row and column by column, and the shapes of pads at different positions in the array may be different. Therefore, before performing light board detection, the scanned image and the standard image can be aligned. The alignment method can be: aligning the standard image and the scanned image as a whole. However, when there are local defects in the light board, for example, when the light board has a warping defect, or when a local area in the light board is deformed, the position of other areas on the light board that do not have defects may be shifted as a whole. In this way, a large number of false detections will occur after the entire board is aligned and then defect detection is performed.

[0062] The standard image may be a design drawing of a target light board, and as an example, the scanned image may be a Gerber (a file format) image. The target light board can be obtained by processing based on the design drawing, but due to various errors or deviations during the processing, the actual processed target light board may be different from the design drawing. The scanned image is the image of the actual processed target light board, which can be obtained by capturing the image of the actual processed target light board through an image acquisition device.

[0063] Exemplarily, a standard image and a scanned image of the target light board can be obtained. Furthermore, the target light board can be divided into a plurality of areas to be tested according to a preset area division rule, the standard image can be divided according to the area division rule, or the standard image of the area to be tested corresponding to each area to be tested can be determined from the standard image through image recognition; synchronously, the scanned image can also be divided according to the area division rule, or the scanned image of the area to be tested corresponding to each area to be tested can be determined from the scanned image through image recognition. The standard image of the area to be tested corresponds one-to-one to the scanned image of the area to be tested, and the area to be tested and the pad displayed in the corresponding pair of the standard image of the area to be tested and the scanned image of the area to be tested are the same.

[0064] Step S20 , locating the target area standard image from each of the test area standard images, and locating the target area scanned image corresponding to the target area standard image from each of the test area scanned images.

[0065] Exemplarily, a target area standard image can be selected from each of the target area standard images, and the area feature information corresponding to the target area standard image can be determined, wherein the area feature information can include at least one of area arrangement information, pad arrangement information, area position information, etc. The area arrangement information is used to characterize the arrangement position of the target area to be tested corresponding to the target area standard image in the global area of ​​the light board. For example, the area arrangement information can be the first row and the second column, which means that the target area standard image is the standard image of the target area to be tested in the first row and the second column; the pad arrangement information is used to characterize the arrangement position of the target pads to be tested corresponding to the target area standard image in the global area of ​​the light board. For example, the pad arrangement information can be the fifth to tenth rows and the first to the third columns, which means that the target area standard image is the standard image of the target area to be tested including the pads to be tested whose rows belong to the fifth to the tenth rows and the columns belong to the first to the third columns; the area position information can be the position information of the vertices of the target area to be tested, the position information of the geometric center of the target area to be tested, etc. After determining the area feature information corresponding to the target area image, the target area scan image can be located from the scan image of the target area to be tested based on the area feature information.

[0066] It is understandable that when performing lamp board inspection, the entire lamp board is usually required to be inspected, that is, the entire scanned image of the area to be inspected needs to be inspected. The inspection process of the scanned image of the area to be inspected can be performed synchronously or in sequence, and this embodiment does not limit this.

[0067] As an example, if the area feature information corresponding to the target area standard image is the area arrangement information or pad arrangement information of the target area standard image, the area arrangement information or pad arrangement information of the target area standard image can be matched with the area arrangement information or pad arrangement information of the scanned image of the area to be tested to determine the target area scanned image corresponding to the target area standard image.

[0068] As an example, if the area feature information corresponding to the target area standard image is the area position information of the target area standard image, then the coordinate system of the target area scanned image that is unified with the standard can be established based on the coordinate system of the target area standard image. For example, both can use the lower left corner of the image as the origin to establish a two-dimensional coordinate system; then determine the area position information of each scanned image of the area to be tested, and calculate the distance between the area position information of each scanned image of the area to be tested and the area position information of the standard image of the target area, and determine the scanned image of the area to be tested corresponding to the minimum distance as the scanned image of the target area.

[0069] Step S30, aligning the target area standard image with the target area scanned image.

[0070] As an example, the method of aligning the target area standard image with the target area scanned image includes: moving the target area scanned image or the target area standard image until the geometric center of the target area standard image coincides with the geometric center of the target area scanned image.

[0071] As an example, the method of aligning the target area standard image with the target area scanned image also includes: selecting multiple first target alignment points from the target area standard image, and selecting multiple second target alignment points from the target area scanned image, the first target alignment points and the second target alignment points corresponding to each other one by one, for example, all are the upper left vertices, all are the upper right vertices, all are the geometric center points, etc.; then calculating the regional alignment distance between the corresponding two first target alignment points and the second target alignment points, and solving the positions of each first target alignment point and the second target alignment point that minimizes the sum of each regional alignment distance.

[0072] Step S40 , detecting the target area scanned image based on the aligned target area standard image.

[0073] Among them, the lamp board detection refers to the defect detection of the processed lamp board, and the defects include missing, deformation, color difference, offset, misprint, pollution, etc. The defect detection method may include defect feature recognition, detection of similarity with the standard image, area detection of non-overlapping area with the standard image, etc., which can be determined according to actual conditions and test results, etc., and this embodiment does not limit this.

[0074] Exemplarily, after the alignment, defect detection is performed on the scanned image of the aligned target area based on the standard image of the aligned target area.

[0075] In the above-mentioned lamp board detection method, first, multiple groups of standard images of the target lamp board's test area and multiple groups of scanned images of the test area are obtained. The standard images of the test area can represent the detection standard of the target lamp board, while the scanned images of the test area can represent the actual situation of the target lamp board; then, by aligning the standard images of the target area with the scanned images of the target area, independent alignment of each area is achieved; then, the scanned images of the target area are detected based on the aligned standard images of the target area. In this way, compared with the method of aligning the entire board and then performing defect detection, the method of independent alignment of each area can effectively correct the overall offset of each area due to the influence of other areas, reduce mutual interference between areas, thereby improving the accuracy of lamp board detection, and reducing the misdetection of good products as defective products, thereby reducing unnecessary rework operations caused by misdetection, saving human resources and time resources, and reducing the situation where good products are discarded due to misdetection, reducing waste, and reducing costs.

[0076] In an exemplary embodiment, the target area standard image includes a plurality of standard images of pads to be tested; the target area scan image includes a plurality of scan images of pads to be tested, and the standard images of pads to be tested correspond to the scan images of pads to be tested one by one; and the target area scan image is detected based on the aligned target area standard image, including steps S41 to S43. Wherein:

[0077] Step S41 , selecting a target pad standard image from each of the pad standard images to be tested, and selecting a target pad scanning image corresponding to the target pad standard image from each of the pad scanning images to be tested.

[0078] It should be noted that the target light board contains multiple pads. After the test area is divided, each test area also contains multiple pads. Since the number of pads on the target light board is usually tens of thousands, the workload of aligning them one by one is large and consumes more resources. By dividing the area and aligning and detecting each area separately, the mutual interference between defects can be greatly reduced, the detection error caused by alignment deviation can be reduced, and the detection accuracy can be improved. However, the area of ​​the pad is small and the number is large, so a small alignment deviation will have a great impact on the detection result. In other words, for the detection of defects of the pad itself other than the missing pad, such as deformation, color difference, misprinting and other defects of the pad, the accuracy of detection after alignment is still low, and the false detection rate is still very high.

[0079] Among them, the pad scanning image is a scanning image of the pad, and for the missing pad, the corresponding pad scanning image can be a null value. As an example, the detection method of the missing pad scanning image can be: determine the number of columns of the target light board based on the standard image, detect whether the number of pads in each row in the scanning image is equal to the number of columns, or determine the number of rows of the target light board based on the standard image, detect whether the number of pads in each column in the scanning image is equal to the number of rows, or determine the number of rows and columns of the target light board based on the standard image, detect whether the number of pads in each row in the scanning image is equal to the number of columns, and whether the number of pads in each column in the scanning image is equal to the number of rows; for ease of understanding, the following description is made by taking the detection of whether the number of pads in each row in the scanning image is equal to the number of columns as an example. If a target row with a number of pads less than the number of columns is detected, the spacing distance between each pad in the target row is detected, and based on two target pads whose spacing distance exceeds a preset spacing distance threshold, the missing pad arrangement information of the missing pad is determined, and the pad scanning image corresponding to the missing pad arrangement information is set to a null value. Wherein, the number of missing pads may be multiple, and the number of missing pads may be determined based on the difference between the number of columns and the number of pads. In this way, by setting a null value for the pad scan image corresponding to the missing pad, the technical defect of alignment deviation caused by missing pads can be overcome.

[0080] Exemplarily, a target pad standard image can be selected from each of the pad standard images to be tested, and pad feature information corresponding to the target pad standard image can be determined, wherein the pad feature information can include at least one of pad arrangement information, pad position information, etc. The pad arrangement information is used to characterize the arrangement position of the target pad to be tested corresponding to the target pad standard image in the global area of ​​the light board. For example, the pad arrangement information can be the first row and second column, that is, it indicates that the target pad standard image is the standard image of the pad to be tested in the first row and second column; the pad position information can be the position information of the vertex of the pad to be tested, the position information of the geometric center of the pad to be tested, etc. After determining the pad feature information corresponding to the target pad image, the target pad scanning image can be located from the pad scanning image to be tested based on the pad feature information.

[0081] Step S42, performing pad alignment between the target pad standard image and the target pad scan image.

[0082] As an example, the method of aligning the target pad standard image with the target pad scan image includes: moving the target pad scan image or the target pad standard image until the geometric center of the target pad standard image coincides with the geometric center of the target pad scan image.

[0083] As an example, a method for aligning a target pad standard image with a target pad scan image also includes: selecting multiple third target alignment points from the target pad standard image, and selecting multiple fourth target alignment points from the target pad scan image, the third target alignment points and the fourth target alignment points corresponding one to one, for example, all are the upper left vertices, all are the upper right vertices, all are the geometric center points, etc.; then calculating the pad alignment distance between the corresponding two third target alignment points and the fourth target alignment point, and solving the positions of the first target alignment points and the second target alignment points that minimize the sum of the pad alignment distances.

[0084] Step S43 , detecting the target pad scan image based on the target pad standard image after pad alignment.

[0085] Among them, the light board inspection after the pad alignment refers to the pad defect inspection. The pad defect inspection refers to the inspection of the defects of the pad itself except the pad missing, including deformation, color difference, misprint and other defects of the pad.

[0086] Exemplarily, after the pads are aligned, pad defects detection is performed on the scanned image of the aligned target pads based on the standard image of the aligned target pads.

[0087] In this embodiment, for the defect detection of the pad itself except for pad missing, pad alignment can be performed for each pad, which can further reduce the mutual interference between pads, reduce the detection error caused by alignment deviation, and improve the detection accuracy; and for pad missing and other defects except for the defects of the pad itself, detection can be performed directly after alignment, which reduces the calculation amount of light board detection and saves computing power resources.

[0088] In an exemplary embodiment, Figure 2 As shown, obtaining multiple groups of standard images of the target light panel's area to be tested and multiple groups of scanned images of the area to be tested includes steps S101 to S104. Among them:

[0089] Step S101, obtaining a standard image and a scanned image of a target light board;

[0090] Step S102 , globally aligning the entire standard image with the entire scanned image.

[0091] It should be noted that before the standard image of the target area is aligned with the scanned image of the target area, the accuracy and consistency of the area division of the standard image and the scanned image must be ensured. The consistency means that the standard image of the area to be tested divided in the standard image should correspond one-to-one with the scanned image of the area to be tested divided in the scanned image, and the two corresponding standard images of the area to be tested and the scanned image of the area to be tested should correspond to the same area to be tested, so as to ensure the effectiveness and accuracy of the area alignment.

[0092] However, there may be pads missing on the light board, which will affect the accuracy of the regional features, resulting in regional displacement in the scanned image. When the displaced area is compared with the non-displaced area in the standard image, the detection result will obviously be inaccurate. For example, if the light board contains a 6×6 pad array, the pad array can be divided into 9 2×2 areas. The standard image of the light board is as follows: Figure 3 As shown, the scanned image of the light board is as follows Figure 4 As shown in FIG. 1 , if the pad in the third column of the first row is missing, since the pad image cannot be detected at the position of the third column of the first row of the scanned image, when dividing the area, the pad in the fourth column of the first row will be divided, resulting in the area on the scanned image starting from the third column of the first row being offset to the right relative to the area on the standard image. Taking the second area in the first row as an example, due to the area offset, the second area in the first row is determined based on the scanned image as follows: Figure 4Comparing area 21 with area 11 in the standard image will result in a detection result that the pad in the first row and third column is abnormal, while the true result should be that the pad in the first row and third column is missing and the pad in the first row and fourth column is abnormal. It can be found that the detection result deviates seriously from the true result.

[0093] Global alignment refers to the method of aligning the standard image and the scanned image as a whole.

[0094] Exemplarily, a standard image and a scanned image of the target light board may be acquired first, and the standard image may be taken as a whole and globally aligned with the scanned image as a whole.

[0095] As an example, methods for globally aligning the entire standard image with the entire scanned image include: moving the scanned image or the standard image until the geometric center of the standard image coincides with the geometric center of the scanned image, or the edge line of the standard image coincides with the edge line of the scanned image, or the vertices of the standard image coincide with the vertices of the scanned image.

[0096] As an example, a method for globally aligning the entire standard image with the entire scanned image also includes: selecting multiple fifth target alignment points from the standard image, and selecting multiple sixth target alignment points from the scanned image, the fifth target alignment points and the sixth target alignment points corresponding one to one, for example, all are the upper left vertices, all are the upper right vertices, all are the geometric center points, etc.; then calculating the global alignment distance between the corresponding two fifth target alignment points and the sixth target alignment points, and solving the positions of the first target alignment points and the second target alignment points that minimize the sum of the global alignment distances.

[0097] Step S103 , performing missing detection on the scanned image based on the globally aligned standard image to obtain missing position information.

[0098] Among them, missing detection refers to the detection of missing pads in the target light board. Missing position information refers to the position information of the missing pad in the scanned image, which can be arrangement position information or positioning information, wherein the arrangement position information refers to the row and column information of the missing pad in the pad array, such as the nth row and the mth column; positioning information refers to the specific position of the missing pad in the scanned image, which can be represented by the center point position of the missing pad in the standard image, or the position range of the vacant area corresponding to the missing pad, which can be determined according to actual conditions and test results, etc., and this embodiment does not limit this.

[0099] As an example, the missing detection method can be: overlapping the globally aligned standard image and the scanned image, detecting whether each pad standard image in the standard image overlaps with the pad scanned image in the scanned image; in the case where a missing pad standard image is detected, determining the missing position information of the missing pad in the scanned image based on the position information of the missing pad standard image. The missing pad standard image refers to a pad standard image that does not overlap with any pad scanned image.

[0100] As an example, the missing detection method can be: determine the number of columns of the target light board based on the standard image, detect whether the number of pads in each row of the scanned image is equal to the number of columns, or determine the number of rows of the target light board based on the standard image, detect whether the number of pads in each column of the scanned image is equal to the number of rows, or determine the number of rows and columns of the target light board based on the standard image, detect whether the number of pads in each row of the scanned image is equal to the number of columns, and whether the number of pads in each column of the scanned image is equal to the number of rows; for ease of understanding, the following description is made by taking the detection of whether the number of pads in each row of the scanned image is equal to the number of columns as an example. If a target row is detected in which the number of pads is less than the number of columns, the spacing distance between each pad in the target row is detected, and the missing position information of the missing pad is determined based on two target pads whose spacing distance exceeds a preset spacing distance threshold. Among them, the number of missing pads can be multiple, and the number of missing pads can be determined based on the difference between the number of columns and the number of pads.

[0101] Step S104, obtaining the position information of the test area of ​​each test area standard image in the standard image after global alignment, and dividing the scanned image into multiple test area scanned images based on the missing position information and the test area position information, and the test area scanned images correspond to the test area standard images one by one.

[0102] Among them, the content of the target area standard image after global alignment does not change compared with the target area standard image before global alignment, but the position of the image may change, such as translation, rotation, etc. The content of the target area scanned image after global alignment does not change compared with the target area scanned image before global alignment, but the position of the image may change, such as translation, rotation, etc.

[0103] Exemplarily, after acquiring the standard image, the standard image can be divided into regions according to preset region division rules to determine multiple standard images of the area to be tested and their position information of the area to be tested. The position information of the area to be tested may change with the change of the standard image during the global alignment process; further, after the global alignment, the position information of the area to be tested that has changed with the global alignment can be determined first, and then, based on the position information of the area to be tested and the missing position information, the scanned image of the area to be tested corresponding to each standard image of the area to be tested can be located from the scanned image after the global alignment.

[0104] The missing position information can be used to occupy the position of the missing pad in the scanned image during the positioning process, for example Figure 3 and Figure 4 In the scenario shown, the pad position corresponding to area 11 is located in the first to second rows and in the third to fourth columns, and it is determined that the missing position includes the first row and the third column. Then, a virtual pad image can be generated at the position of the first row and the third column in the scanned image. The virtual pad image can be the same as the standard pad image corresponding to the missing pad. The virtual pad image is only used for area division, and the virtual pad image occupies the position of the missing pad, thereby improving the accuracy of area division.

[0105] The missing position information can also be used to determine the region division row and region division column, where the region division row refers to the row used for region division and the region division column refers to the column used for region division. Figure 3 and Figure 4 In the scenario shown, the missing position is located in the third column of the first row. Therefore, the area division rows can be determined from rows other than the first row, and the area division columns can be determined from columns other than the third column. Area division can be performed based on the area division rows and area division columns. This will prevent area deviation due to missing pads.

[0106] In this embodiment, after the global alignment, missing detection is first performed to determine the missing position information, and then the area division is performed. Since the missing position information is known, it can be avoided that when performing area division, the missing pad is skipped due to failure to detect the pad image, resulting in area deviation. Therefore, the accuracy of area division can be effectively improved, thereby improving the accuracy of alignment. The higher the alignment accuracy, the higher the accuracy of light board detection will be.

[0107] In an exemplary embodiment, globally aligning the entire standard image with the entire scanned image includes steps S1011 to S1012.

[0108] Step S1011, based on the standard image, detecting the standard position of the vertex of the target light board, and based on the scanned image, detecting the scanning position of the vertex of the target light board.

[0109] Exemplarily, at least one light board vertex is identified from a standard image, and the standard position of each light board vertex in the standard image is determined; synchronously, at least one light board vertex can be identified from a scanned image, and the light board vertex scanning position of each light board vertex in the scanned image is determined.

[0110] Step S1012, based on the standard position of the vertex of the light board and the scanning position of the vertex of the light board, globally align the entire standard image with the entire scanned image.

[0111] Exemplarily, the standard position of the vertex of the light board and the scanning position of the vertex of the light board are unified into the same coordinate system, and the standard position of the vertex of the light board is made to coincide with the scanning position of the vertex of the light board by moving the standard image or the scanning image, or both. In the case where there are multiple vertices of the light board, the standard position of the vertex of the light board corresponds to the scanning position of the vertex of the light board one by one, and the standard image or the scanning image is moved, or both are moved, so that the corresponding two standard positions of the vertex of the light board coincide with the scanning position of the vertex of the light board.

[0112] In this embodiment, global alignment of vertices can effectively correct angular deviations that occur during image acquisition. For example, image acquisition may cause the scanned image to rotate relative to the standard image. Only after correcting the angular deviation can the accuracy of area division be guaranteed, thereby improving the accuracy of light board detection.

[0113] In an exemplary embodiment, the target light board includes a plurality of pads; aligning the target area standard image with the target area scan image includes steps S31 to S32. Among them:

[0114] Step S31 , based on the standard image after global alignment, detecting the standard position of the pad center of at least one pad, and based on the scanned image after global alignment, detecting the pad center scanned position of at least one pad.

[0115] It should be noted that for the target light board, the overall area of ​​the light board is fixed and unchanged, and its features are also obvious. For example, vertices and edges are easy to identify from the image, so global alignment can be performed based on these fixed and easily identifiable features. However, it is difficult to accurately determine the corresponding positions of features such as vertices or edges of the area to be tested from the scanned image. If the scanned image is aligned based on the vertex position or edge position of the area to be tested determined in the standard image, the inaccurate position of features such as vertices or edges will further affect the accuracy of alignment, ultimately resulting in a reduction in the accuracy of light board detection.

[0116] Exemplarily, from the standard image after global alignment, the pad standard image corresponding to the pad is identified, and the position of the geometric center of each pad standard image is detected to obtain the pad center standard position; synchronously, from the scanned image after global alignment, the pad scanning image corresponding to the pad is identified, and the position of the geometric center of each pad scanning image is detected to obtain the pad center scanning position. The pad standard image corresponding to the same pad corresponds to the pad scanning image one by one.

[0117] Step S32: aligning the target area standard image with the target area scanned image based on the pad center standard position and the pad center scanned position.

[0118] Exemplarily, the target area standard image or the target area scanned image, or both, may be moved until one or more pad center standard positions coincide with their corresponding pad center scanned positions.

[0119] In this embodiment, after global alignment, the rotation angle of the scanned image can be guaranteed to be consistent with the standard image, and then regional alignment is performed, which can reduce the detection error caused by 90° or 180° flipping during the regional alignment process; and by taking the soldering pad that can accurately determine the position information as the target, since the soldering pad is one of the detection targets of the light board detection, if the soldering pad is aligned, the accuracy of the light board detection will also be improved accordingly.

[0120] In an exemplary embodiment, after detecting the target area scanned image based on the aligned target area standard image, the method further includes:

[0121] Step S50, determining the target area standard image as the inspected area standard image, and returning to execute the step of locating the target area standard image from the inspected area standard images.

[0122] It should be noted that when inspecting a partial area or pad of a target light board, the images of each area or pad can be segmented from the global image, stored separately, and then aligned and inspected separately. However, this requires a lot of storage resources, and errors are prone to occur during the storage and extraction of a large amount of image data, thereby affecting the accuracy of the light board inspection results.

[0123] Exemplarily, after the area is divided, the label information of the standard image of the area to be tested can be set for each area standard image. In this way, when locating the standard image of the target area, it can be selected from the area standard images whose label information is the standard image of the area to be tested. Furthermore, after the target area scanned image is detected, the label information of the standard image of the target area can be modified from the standard image of the area to be tested to the standard image of the inspected area, and then the step of locating the standard image of the target area from the standard images of the area to be tested is returned to execute, and the standard image of the target area can be reselected from the area standard images that have not been detected, and this cycle is repeated until all area standard images have been detected.

[0124] As an example, the method of sequentially performing alignment and detection may not require segmentation and storage of the standard image and the scanned image. Exemplarily, the standard image and the scanned image may be globally aligned first to determine the initial state of the scanned image, and then the target area standard image may be determined in sequence. For each target area standard image, the scanned image may be moved until the target area scanned image corresponding to the target area standard image in the scanned image is aligned with the target area standard image, and the target area scanned image is detected based on the aligned target area standard image; after the target area scanned image is detected, the scanned image may be restored to its initial state, and the target area standard image may be re-determined, and the cycle may be repeated until all the areas to be tested in the scanned image are detected.

[0125] In this embodiment, by positioning the standard image of the target area in sequence, and performing alignment and detection in sequence, the process of image storage and extraction is omitted, and it is ensured that all areas to be tested are detected. This can save storage resources and reduce the number of operating steps, thereby reducing operational errors and improving the accuracy of the light board detection results.

[0126] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0127] Based on the same inventive concept, the embodiment of the present application also provides a light board detection device for implementing the light board detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more light board detection device embodiments provided below can refer to the limitations of the light board detection method above, and will not be repeated here.

[0128] In an exemplary embodiment, Figure 5 As shown, a light board detection device is provided, including: an acquisition module 502, a positioning module 504, an alignment module 506 and a detection module 508, wherein:

[0129] An acquisition module 502 is used to acquire multiple groups of standard images of the target light board and multiple groups of scanned images of the target light board, wherein the standard images of the target light board correspond to the scanned images of the target light board in a one-to-one manner;

[0130] A positioning module 504 is used to locate the target area standard image from each of the test area standard images, and locate the target area scan image corresponding to the target area standard image from each of the test area scan images;

[0131] An alignment module 506, used to align the target area standard image with the target area scanned image;

[0132] The detection module 508 is used to detect the target area scanned image based on the aligned target area standard image.

[0133] In an exemplary embodiment, the target area standard image includes a plurality of standard images of pads to be tested, the target area scan image includes a plurality of scan images of pads to be tested, and the standard images of pads to be tested correspond to the scan images of pads to be tested one by one; the detection module 508 is further used for:

[0134] Selecting a target pad standard image from each of the pad standard images to be tested, and selecting a target pad scanning image corresponding to the target pad standard image from each of the pad scanning images to be tested;

[0135] Perform pad alignment between the target pad standard image and the target pad scan image;

[0136] The target pad scanning image is detected based on the target pad standard image after the pad is aligned.

[0137] In an exemplary embodiment, the acquisition module 502 is further configured to:

[0138] Acquire standard image and scanned image of target light board;

[0139] Perform global alignment between the whole standard image and the whole scanned image;

[0140] Perform missing detection on the scanned image based on the standard image after global alignment to obtain missing position information;

[0141] The position information of the test area of ​​each standard image of the test area in the standard image after global alignment is obtained, and based on the missing position information and the position information of the test area, the scanned image is divided into multiple scanned images of the test area, and the scanned images of the test area correspond to the standard images of the test area one by one.

[0142] In an exemplary embodiment, the acquisition module 502 is further configured to:

[0143] Based on the standard image, the standard position of the vertex of the target light board is detected, and based on the scanned image, the scanning position of the vertex of the target light board is detected;

[0144] Based on the standard position of the light board vertex and the scanning position of the light board vertex, the entire standard image and the entire scanned image are globally aligned.

[0145] In an exemplary embodiment, the alignment module 506 is further configured to:

[0146] Based on the standard image after global alignment, detecting the standard position of the pad center of at least one pad, and based on the scanned image after global alignment, detecting the pad center scanned position of at least one pad;

[0147] Based on the pad center standard position and the pad center scan position, the target area standard image and the target area scan image are aligned.

[0148] In an exemplary embodiment, the light board detection device further includes a circulation module, and after detecting the target area scan image based on the aligned target area standard image, the circulation module is further used to:

[0149] The target area standard image is determined as the inspected area standard image, and the process returns to the step of locating the target area standard image from among the inspected area standard images.

[0150] Each module in the above-mentioned lamp board detection device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0151] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a light board detection method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0152] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0153] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0154] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0155] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0156] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0157] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0158] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0159] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A light board detection method, characterized in that: The method comprises: Acquire multiple groups of standard images of the area to be tested and multiple groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one; Locate a target area standard image from each of the test area standard images, and locate a target area scan image corresponding to the target area standard image from each of the test area scan images; Aligning the target area standard image with the target area scanned image; The target area scanned image is detected based on the aligned target area standard image.

2. The method according to claim 1, characterized in that: The target area standard image includes a plurality of standard images of pads to be tested, the target area scan image includes a plurality of scan images of pads to be tested, and the standard images of pads to be tested correspond to the scan images of pads to be tested one by one; The detecting the target area scanned image based on the aligned target area standard image comprises: Selecting a target pad standard image from each of the pad standard images to be tested, and selecting a target pad scanning image corresponding to the target pad standard image from each of the pad scanning images to be tested; Perform pad alignment between the target pad standard image and the target pad scan image; The target pad scanning image is detected based on the target pad standard image after the pads are aligned.

3. The method according to claim 1, characterized in that: The step of acquiring multiple groups of standard images of the target light board's area to be tested and multiple groups of scanned images of the target light board's area to be tested includes: Acquire a standard image and a scanned image of the target light board; Performing global alignment of the entire standard image and the entire scanned image; Performing missing detection on the scanned image based on the globally aligned standard image to obtain missing position information; The position information of the area to be tested of each standard image of the area to be tested in the standard image after global alignment is obtained, and based on the missing position information and the position information of the area to be tested, the scanned image is divided into multiple scanned images of the area to be tested, and the scanned images of the area to be tested correspond to the standard images of the area to be tested one by one.

4. The method according to claim 3, characterized in that The globally aligning the entire standard image with the entire scanned image includes: Based on the standard image, detecting a standard position of a vertex of the target light board, and based on the scanned image, detecting a scanned position of a vertex of the target light board; Based on the standard position of the vertex of the light board and the scanning position of the vertex of the light board, the entire standard image is globally aligned with the entire scanned image.

5. The method according to claim 3, characterized in that: The target light board includes a plurality of pads; The aligning the target area standard image with the target area scanned image includes: Based on the standard image after global alignment, detecting the standard position of the pad center of at least one pad, and based on the scanned image after global alignment, detecting the pad center scanned position of at least one pad; Based on the pad center standard position and the pad center scan position, the target area standard image and the target area scan image are aligned.

6. The method according to any one of claims 1 to 4, characterized in that: After detecting the target area scanned image based on the aligned target area standard image, the method further includes: The target area standard image is determined as the inspected area standard image, and the step of locating the target area standard image from the inspected area standard images is returned to be executed.

7. A light board detection device, characterized in that: The device comprises: An acquisition module, used for acquiring a plurality of groups of standard images of the area to be tested and a plurality of groups of scanned images of the area to be tested of the target light board, wherein the standard images of the area to be tested correspond to the scanned images of the area to be tested one by one; A positioning module, used for positioning a target area standard image from each of the target area standard images, and positioning a target area scan image corresponding to the target area standard image from each of the target area scan images; An alignment module, used for aligning the target area standard image with the target area scanned image; The detection module is used to detect the target area scanned image based on the aligned target area standard image.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images