OpenCV-based FPC board black and white anti-re-pasting rapid identification method

Abstract

The invention relates to the field of FPC board anti-re-pasting identification, in particular to an OpenCV-based FPC board black and white anti-re-pasting rapid identification method, which comprises the following steps: S1, carrying out basic data verification processing by using a black and white anti-re-pasting real-time image of an FPC board to obtain a basic data verification processing result of the black and white anti-re-pasting real-time image; s2, performing identification region division processing according to the basic data verification processing result to obtain a primary and secondary region division result of the basic data verification processing result; and S3, according to the primary and secondary area division result and the FPC board black and white anti-repasting rapid identification result, establishing a multi-stage analysis, research and judgment means by collecting real-time images, rapidly obtaining the black and white anti-repasting identification result, improving a conventional image processing means due to the black and white two-image display characteristic of the surface content of the anti-repasting, establishing a processing reference, and rapidly obtaining the black and white anti-repasting identification result. And different technological processes or production points are separately calibrated, so that the anti-re-pasting identification accuracy and identification efficiency on the FPC board are improved.

Description

Technical Field

[0001] The invention relates to the field of FPC board anti-re-sticking identification, and in particular to an OpenCV-based FPC board black and white anti-re-sticking fast identification method. Background Art

[0002] During the process production, the real-time status of the FPC board needs to be monitored. A common method is to stick black and white anti-restickers on the FPC board to identify the process stage, which is convenient for the process production line and the circulation of each FPC board. Due to the reasons of anti-restickers themselves, simply detecting whether the FPC has anti-restickers cannot fully grasp the status of the process production process. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides a black and white anti-re-sticking fast identification method for FPC boards based on OpenCV, which collects real-time images and quickly analyzes and screens the anti-re-sticking detection results on the FPC boards.

[0004] To achieve the above object, the present invention provides a method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV, comprising: S1, using the black and white anti-re-sticking real-time image of the FPC board to perform basic data verification processing to obtain the basic data verification processing result of the black and white anti-re-sticking real-time image; S2, performing identification area division processing according to the basic data verification processing result to obtain the primary and secondary area division result of the basic data verification processing result; S3, quickly identifying the black and white anti-re-sticking results of the FPC board according to the primary and secondary area division results.

[0005] Preferably, the basic data verification processing using the black and white anti-re-pasting real-time image of the FPC board to obtain the basic data verification processing result of the black and white anti-re-pasting real-time image includes: Collect multi-point real-time images of FPC board; The multi-point real-time images are used to perform superposition and splicing processing based on OpenCV to obtain a black and white anti-re-sticking real-time image of the FPC board; Obtain the black and white anti-re-sticking corresponding anti-re-sticking edge size data of the FPC board; Determine whether the anti-re-sticking edge size data is abnormal, if so, obtain the basic data verification processing result of the black and white anti-re-sticking real-time image according to the anti-re-sticking edge size data corresponding to the abnormal data, otherwise, the basic data verification processing result of the black and white anti-re-sticking real-time image is normal; Among them, the anti-re-sticking edge size data includes the anti-re-sticking length, the anti-re-sticking width and the anti-re-sticking surface reflectivity.

[0006] Further, the basic data verification processing result of obtaining the black and white anti-re-pasting real-time image according to the anti-re-pasting edge size data corresponding to the abnormal data includes: When the anti-repaste edge size data is abnormal, determine whether the number of the anti-repaste edge size data is 1. If so, obtain the basic data verification processing result of the black and white anti-repaste real-time image according to the data type of the anti-repaste edge size data. Otherwise, the basic data verification processing result of the black and white anti-repaste real-time image is abnormal and the processing is abandoned.

[0007] Further, the basic data verification processing result of the black and white anti-re-pasting real-time image is obtained according to the data type of the anti-re-pasting edge size data, including: When the data type of the anti-re-sticking edge size data is the anti-re-sticking length, it is determined whether there is an abnormal area of ​​the anti-re-sticking surface reflectivity of the black-and-white anti-re-sticking real-time image, if so, the basic data verification processing result of the black-and-white anti-re-sticking real-time image is abnormal, otherwise, the basic data verification processing result of the black-and-white anti-re-sticking real-time image is an abnormality to be processed; When the basic size abnormal data type of the black and white anti-re-pasting real-time image is the anti-re-pasting width, the basic data verification processing result of the black and white anti-re-pasting real-time image is abnormal; When the basic size abnormal data type of the black and white anti-repaste real-time image is the anti-repaste surface reflectivity, determine whether the anti-repaste length of the black and white anti-repaste real-time image exceeds 1.5 times the standard anti-repaste length. If so, the basic data verification processing result of the black and white anti-repaste real-time image is abnormal. Otherwise, the basic data verification processing result of the black and white anti-repaste real-time image is an exception to be processed.

[0008] Further, the identification area division processing is performed according to the basic data verification processing result to obtain the primary and secondary area division results of the basic data verification processing result, including: Performing initial area division processing according to the basic data verification processing result to obtain an initial division area of ​​the basic data verification processing result; Using the initial divided area to obtain a black and white anti-re-sticking contour recognition result as a main area division result; Using the black and white anti-re-pasting contour recognition result, a black and white anti-re-pasting feature recognition result is obtained as a secondary area division result; The primary and secondary area division results are used as the primary and secondary area division results of the basic data verification processing results.

[0009] Further, the initial area division processing is performed according to the basic data verification processing result to obtain the initial division area of ​​the basic data verification processing result, including: Use black and white anti-re-pasting standard image as the reference for area division; Acquire image data of black and white anti-re-pasting real-time image; Using the image data of the black and white anti-repasting real-time image, image contour data of the black and white anti-repasting real-time image is obtained based on opencv according to a region division benchmark; Removing image contour data of the black-and-white anti-re-pasting real-time image from the image data of the black-and-white anti-re-pasting real-time image as image feature data of the black-and-white anti-re-pasting real-time image; Using the image contour data and image feature data of the black and white anti-re-pasting real-time image as basic data to verify the initial division area of ​​the processing result; The standard value of the paper outline is the edge outline of the black and white anti-re-sticking real-time image, and does not occupy the black and white anti-re-sticking center area.

[0010] Further, using the initial divided area to obtain a black and white anti-re-pasting contour recognition result as a main area division result includes: Determine whether the image contour data of the black-and-white anti-repaste real-time image is symmetrically corresponding, if so, the image contour recognition result of the black-and-white anti-repaste real-time image is normal, and use the image contour recognition result of the black-and-white anti-repaste real-time image as the main area division result, otherwise, the image contour recognition result of the black-and-white anti-repaste real-time image is abnormal; Among them, the image contour data of the same black and white anti-repaste real-time image includes the image upper contour data of the black and white anti-repaste real-time image, the image lower contour data of the black and white anti-repaste real-time image, the image left contour data of the black and white anti-repaste real-time image and the image right contour data of the black and white anti-repaste real-time image.

[0011] Further, using the black and white anti-re-pasting contour recognition result to obtain a black and white anti-re-pasting feature recognition result as a secondary area division result includes: Determine whether the image feature data of the black-and-white anti-re-pasting real-time image is independent and complete; if so, the image feature recognition result of the black-and-white anti-re-pasting real-time image is normal, and use the image feature recognition result of the black-and-white anti-re-pasting real-time image as the secondary area division result; otherwise, obtain the feature duplication data corresponding to the image feature data of the black-and-white anti-re-pasting real-time image; The image feature recognition result of the black and white anti-re-pasting real-time image is obtained by using the feature repetition data.

[0012] Furthermore, the image feature recognition result of the black and white anti-re-pasting real-time image obtained by using the feature duplication data includes: Determine whether there is image contour data of the black-and-white anti-re-pasting real-time image in the feature duplication data, if so, obtain the amount of image contour data of the black-and-white anti-re-pasting real-time image, otherwise, the image feature recognition result of the black-and-white anti-re-pasting real-time image is abnormal; It is determined whether the number of image contour data of the black-and-white anti-re-pasting real-time image is 1. If so, the image feature recognition result of the black-and-white anti-re-pasting real-time image is a single abnormality; otherwise, the image feature recognition result of the black-and-white anti-re-pasting real-time image is a partial abnormality.

[0013] Further, according to the primary and secondary area division results, the black and white anti-re-sticking fast identification results of the FPC board include: When the image contour recognition result of the black and white anti-re-pasting real-time image of the black and white anti-re-pasting real-time image partition result and the image feature recognition result of the black and white anti-re-pasting real-time image are both normal, the black and white anti-re-pasting real-time image rapid recognition result is normal; When the image contour recognition result of the black and white anti-re-pasting real-time image of the black and white anti-re-pasting real-time image partition result and the image feature recognition result of the black and white anti-re-pasting real-time image are both abnormal, the black and white anti-re-pasting real-time image rapid recognition result is abnormal; When the image contour recognition result of the black-and-white anti-repaste real-time image of the black-and-white anti-repaste real-time image partition result is normal, and the image feature recognition result of the black-and-white anti-repaste real-time image is individually abnormal, the black-and-white anti-repaste real-time image rapid recognition result is an independent black-and-white anti-repaste real-time image position abnormality; When the image contour recognition result of the black and white anti-repaste real-time image of the black and white anti-repaste real-time image partition result is normal, and the image feature recognition result of the black and white anti-repaste real-time image is partially abnormal, the black and white anti-repaste real-time image rapid recognition result is that the non-independent black and white anti-repaste real-time image is abnormal.

[0014] Compared with the closest prior art, the present invention has the following beneficial effects: By collecting real-time images and establishing multi-level analysis and judgment methods, the black and white anti-re-sticking recognition results can be quickly obtained. Due to the black and white dual-image display characteristics of the anti-re-sticking surface content, the conventional image processing methods are improved, and a processing benchmark is established. Different process flows or production points are calibrated separately to improve the accuracy and efficiency of anti-re-sticking recognition on FPC boards. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention provides a flow chart of a method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV. DETAILED DESCRIPTION

[0016] The specific implementation modes of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0017] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1: The present invention provides a method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV, such as Figure 1 As shown, including: S1, using the black and white anti-re-sticking real-time image of the FPC board to perform basic data verification processing to obtain the basic data verification processing result of the black and white anti-re-sticking real-time image; S2, performing identification area division processing according to the basic data verification processing result to obtain the primary and secondary area division result of the basic data verification processing result; S3, quickly identifying the black and white anti-re-sticking results of the FPC board according to the primary and secondary area division results.

[0019] S1 specifically includes: S1-1, collect multi-point real-time images of FPC board; S1-2, using the multi-point real-time images to perform superposition and splicing processing based on OpenCV to obtain a black and white anti-re-sticking real-time image of the FPC board; S1-3, obtaining the anti-re-sticking edge size data corresponding to the black and white anti-re-sticking of the FPC board; S1-4, judging whether the anti-re-sticking edge size data is abnormal, if so, obtaining the basic data verification processing result of the black and white anti-re-sticking real-time image according to the anti-re-sticking edge size data corresponding to the abnormal data, otherwise, the basic data verification processing result of the black and white anti-re-sticking real-time image is normal; Among them, the anti-re-sticking edge size data includes the anti-re-sticking length, the anti-re-sticking width and the anti-re-sticking surface reflectivity.

[0020] S1-4 specifically includes: S1-4-1. When the anti-repaste edge size data is abnormal, determine whether the number of the anti-repaste edge size data is 1. If so, obtain the basic data verification processing result of the black-and-white anti-repaste real-time image according to the data type of the anti-repaste edge size data. Otherwise, the basic data verification processing result of the black-and-white anti-repaste real-time image is abnormal and the processing is abandoned.

[0021] S1-4-1 specifically includes: S1-4-1-1, when the data type of the anti-re-sticking edge size data is the anti-re-sticking length, determine whether there is an abnormal area of ​​the anti-re-sticking surface reflectivity of the black-and-white anti-re-sticking real-time image, if so, the basic data verification processing result of the black-and-white anti-re-sticking real-time image is abnormal, otherwise, the basic data verification processing result of the black-and-white anti-re-sticking real-time image is an abnormality to be processed; S1-4-1-2, when the basic size abnormal data type of the black and white anti-re-pasting real-time image is the anti-re-pasting width, the basic data verification processing result of the black and white anti-re-pasting real-time image is abnormal; S1-4-1-3. When the basic size abnormal data type of the black and white anti-repaste real-time image is the anti-repaste surface reflectivity, determine whether the anti-repaste length of the black and white anti-repaste real-time image exceeds 1.5 times the standard anti-repaste length. If so, the basic data verification processing result of the black and white anti-repaste real-time image is abnormal. Otherwise, the basic data verification processing result of the black and white anti-repaste real-time image is an exception to be processed.

[0022] S2 specifically includes: S2-1, performing initial area division processing according to the basic data verification processing result to obtain an initial division area of ​​the basic data verification processing result; S2-2, using the initial divided area to obtain a black and white anti-re-sticking contour recognition result as a main area division result; S2-3, using the black and white anti-re-sticking contour recognition result to obtain a black and white anti-re-sticking feature recognition result as a secondary area division result; S2-4. Use the primary and secondary area division results as the primary and secondary area division results of the basic data verification processing results.

[0023] S2-1 specifically includes: S2-1-1, using the black and white anti-re-sticking standard image as the reference for area division; S2-1-2, obtaining image data of a black and white anti-re-sticking real-time image; S2-1-3, using the image data of the black and white anti-re-pasting real-time image to obtain image contour data of the black and white anti-re-pasting real-time image based on opencv according to the region division standard; S2-1-4, removing the image contour data of the black-and-white anti-re-pasting real-time image from the image data of the black-and-white anti-re-pasting real-time image as the image feature data of the black-and-white anti-re-pasting real-time image; S2-1-5, using the image contour data and image feature data of the black and white anti-re-pasting real-time image as basic data to verify the initial division area of ​​the processing result; The standard value of the paper outline is the edge outline of the black and white anti-re-sticking real-time image, and does not occupy the black and white anti-re-sticking center area.

[0024] S2-2 specifically includes: S2-2-1, judging whether the image contour data of the black-and-white anti-re-pasting real-time image are symmetrically corresponding, if so, the image contour recognition result of the black-and-white anti-re-pasting real-time image is normal, and the image contour recognition result of the black-and-white anti-re-pasting real-time image is used as the main area division result, otherwise, the image contour recognition result of the black-and-white anti-re-pasting real-time image is abnormal; Among them, the image contour data of the same black and white anti-repaste real-time image includes the image upper contour data of the black and white anti-repaste real-time image, the image lower contour data of the black and white anti-repaste real-time image, the image left contour data of the black and white anti-repaste real-time image and the image right contour data of the black and white anti-repaste real-time image.

[0025] S2-3 specifically includes: S2-3-1, determining whether the image feature data of the black-and-white anti-re-pasting real-time image is independent and complete; if so, the image feature recognition result of the black-and-white anti-re-pasting real-time image is normal, and using the image feature recognition result of the black-and-white anti-re-pasting real-time image as the secondary area division result; otherwise, obtaining feature duplication data corresponding to the image feature data of the black-and-white anti-re-pasting real-time image; S2-3-2. Obtain image feature recognition results of the black and white anti-re-pasting real-time image using the feature repetition data.

[0026] S2-3-2 specifically includes: S2-3-2-1, determine whether there is image contour data of the black-and-white anti-re-pasting real-time image in the feature duplication data, if so, obtain the number of image contour data of the black-and-white anti-re-pasting real-time image, otherwise, the image feature recognition result of the black-and-white anti-re-pasting real-time image is abnormal; S2-3-2-2. Determine whether the number of image contour data of the black-and-white anti-repaste real-time image is 1. If so, the image feature recognition result of the black-and-white anti-repaste real-time image is a single exception. Otherwise, the image feature recognition result of the black-and-white anti-repaste real-time image is a partial exception.

[0027] S3 specifically includes: S3-1, when the image contour recognition result of the black and white anti-re-pasting real-time image of the black and white anti-re-pasting real-time image partition result and the image feature recognition result of the black and white anti-re-pasting real-time image are both normal, the black and white anti-re-pasting real-time image rapid recognition result is normal; S3-2, when the image contour recognition result of the black and white anti-re-pasting real-time image of the black and white anti-re-pasting real-time image partition result and the image feature recognition result of the black and white anti-re-pasting real-time image are both abnormal, the black and white anti-re-pasting real-time image rapid recognition result is abnormal; S3-3, when the image contour recognition result of the black and white anti-re-paste real-time image of the black and white anti-re-paste real-time image partition result is normal, and the image feature recognition result of the black and white anti-re-paste real-time image is individually abnormal, the black and white anti-re-paste real-time image rapid recognition result is an independent black and white anti-re-paste real-time image position abnormality; S3-4, when the image contour recognition result of the black and white anti-repaste real-time image of the black and white anti-repaste real-time image partition result is normal, and the image feature recognition result of the black and white anti-repaste real-time image is partially abnormal, the black and white anti-repaste real-time image rapid recognition result is that the non-independent black and white anti-repaste real-time image is abnormal.

[0028] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0029] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of the processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0030] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0031] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0032] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A black and white anti-re-sticking fast identification method for FPC board based on OpenCV, characterized in that: include: S1, using the black and white anti-re-sticking real-time image of the FPC board to perform basic data verification processing to obtain the basic data verification processing result of the black and white anti-re-sticking real-time image; S2, performing identification area division processing according to the basic data verification processing result to obtain the primary and secondary area division result of the basic data verification processing result; S3, quickly identifying the black and white anti-re-sticking results of the FPC board according to the primary and secondary area division results.

2. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 1, characterized in that: The basic data verification processing using the black and white anti-re-sticking real-time image of the FPC board to obtain the basic data verification processing result of the black and white anti-re-sticking real-time image includes: Collect multi-point real-time images of FPC board; The multi-point real-time images are used to perform superposition and splicing processing based on OpenCV to obtain a black and white anti-re-sticking real-time image of the FPC board; Obtain the black and white anti-re-sticking corresponding anti-re-sticking edge size data of the FPC board; Determine whether the anti-re-sticking edge size data is abnormal, if so, obtain the basic data verification processing result of the black and white anti-re-sticking real-time image according to the anti-re-sticking edge size data corresponding to the abnormal data, otherwise, the basic data verification processing result of the black and white anti-re-sticking real-time image is normal; Among them, the anti-re-sticking edge size data includes the anti-re-sticking length, the anti-re-sticking width and the anti-re-sticking surface reflectivity.

3. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 2, characterized in that: The basic data verification processing result of obtaining the black and white anti-re-sticking real-time image according to the anti-re-sticking edge size data corresponding to the abnormal data includes: When the anti-repaste edge size data is abnormal, determine whether the number of the anti-repaste edge size data is 1. If so, obtain the basic data verification processing result of the black and white anti-repaste real-time image according to the data type of the anti-repaste edge size data. Otherwise, the basic data verification processing result of the black and white anti-repaste real-time image is abnormal and the processing is abandoned.

4. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 3, characterized in that: The basic data verification processing result of the black and white anti-re-pasting real-time image obtained according to the data type of the anti-re-pasting edge size data includes: When the data type of the anti-re-sticking edge size data is the anti-re-sticking length, it is determined whether there is an abnormal area of ​​the anti-re-sticking surface reflectivity of the black-and-white anti-re-sticking real-time image, if so, the basic data verification processing result of the black-and-white anti-re-sticking real-time image is abnormal, otherwise, the basic data verification processing result of the black-and-white anti-re-sticking real-time image is an abnormality to be processed; When the basic size abnormal data type of the black and white anti-re-pasting real-time image is the anti-re-pasting width, the basic data verification processing result of the black and white anti-re-pasting real-time image is abnormal; When the basic size abnormal data type of the black and white anti-repaste real-time image is the anti-repaste surface reflectivity, determine whether the anti-repaste length of the black and white anti-repaste real-time image exceeds 1.5 times the standard anti-repaste length. If so, the basic data verification processing result of the black and white anti-repaste real-time image is abnormal. Otherwise, the basic data verification processing result of the black and white anti-repaste real-time image is an exception to be processed.

5. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 4, characterized in that: The primary and secondary area division results of the basic data verification processing result obtained by performing identification area division processing according to the basic data verification processing result include: Performing initial area division processing according to the basic data verification processing result to obtain an initial division area of ​​the basic data verification processing result; Using the initial divided area to obtain a black and white anti-re-sticking contour recognition result as a main area division result; Using the black and white anti-re-pasting contour recognition result, a black and white anti-re-pasting feature recognition result is obtained as a secondary area division result; The primary and secondary area division results are used as the primary and secondary area division results of the basic data verification processing results.

6. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 5, characterized in that: The initial area division process is performed according to the basic data verification process result to obtain the initial area division result of the basic data verification process result, including: Use black and white anti-re-pasting standard image as the reference for area division; Acquire image data of black and white anti-re-pasting real-time image; Using the image data of the black and white anti-repasting real-time image, image contour data of the black and white anti-repasting real-time image is obtained based on opencv according to a region division benchmark; Removing image contour data of the black-and-white anti-re-pasting real-time image from the image data of the black-and-white anti-re-pasting real-time image as image feature data of the black-and-white anti-re-pasting real-time image; Using the image contour data and image feature data of the black and white anti-re-pasting real-time image as basic data to verify the initial division area of ​​the processing result; The standard value of the paper outline is the edge outline of the black and white anti-re-sticking real-time image, and does not occupy the black and white anti-re-sticking center area.

7. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 6, characterized in that: The black and white anti-re-sticking contour recognition result obtained by using the initial divided area as the main area division result includes: Determine whether the image contour data of the black-and-white anti-repaste real-time image is symmetrically corresponding, if so, the image contour recognition result of the black-and-white anti-repaste real-time image is normal, and use the image contour recognition result of the black-and-white anti-repaste real-time image as the main area division result, otherwise, the image contour recognition result of the black-and-white anti-repaste real-time image is abnormal; Among them, the image contour data of the same black and white anti-repaste real-time image includes the image upper contour data of the black and white anti-repaste real-time image, the image lower contour data of the black and white anti-repaste real-time image, the image left contour data of the black and white anti-repaste real-time image and the image right contour data of the black and white anti-repaste real-time image.

8. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 7, characterized in that: Obtaining a black and white anti-re-pasting feature recognition result using the black and white anti-re-pasting contour recognition result as a secondary area division result includes: Determine whether the image feature data of the black-and-white anti-re-pasting real-time image is independent and complete; if so, the image feature recognition result of the black-and-white anti-re-pasting real-time image is normal, and use the image feature recognition result of the black-and-white anti-re-pasting real-time image as the secondary area division result; otherwise, obtain the feature duplication data corresponding to the image feature data of the black-and-white anti-re-pasting real-time image; The image feature recognition result of the black and white anti-re-pasting real-time image is obtained by using the feature repetition data.

9. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 8, characterized in that: The image feature recognition results of the black and white anti-re-pasting real-time image obtained by using the feature duplication data include: Determine whether there is image contour data of the black-and-white anti-re-pasting real-time image in the feature duplication data, if so, obtain the amount of image contour data of the black-and-white anti-re-pasting real-time image, otherwise, the image feature recognition result of the black-and-white anti-re-pasting real-time image is abnormal; It is determined whether the number of image contour data of the black-and-white anti-re-pasting real-time image is 1. If so, the image feature recognition result of the black-and-white anti-re-pasting real-time image is a single abnormality; otherwise, the image feature recognition result of the black-and-white anti-re-pasting real-time image is a partial abnormality.

10. A method for quickly identifying black and white anti-re-sticking of FPC boards based on OpenCV as claimed in claim 9, characterized in that: According to the primary and secondary area division results, the FPC board black and white anti-re-sticking rapid identification results include: When the image contour recognition result of the black and white anti-re-pasting real-time image of the black and white anti-re-pasting real-time image partition result and the image feature recognition result of the black and white anti-re-pasting real-time image are both normal, the black and white anti-re-pasting real-time image rapid recognition result is normal; When the image contour recognition result of the black and white anti-re-pasting real-time image of the black and white anti-re-pasting real-time image partition result and the image feature recognition result of the black and white anti-re-pasting real-time image are both abnormal, the black and white anti-re-pasting real-time image rapid recognition result is abnormal; When the image contour recognition result of the black-and-white anti-repaste real-time image of the black-and-white anti-repaste real-time image partition result is normal, and the image feature recognition result of the black-and-white anti-repaste real-time image is individually abnormal, the black-and-white anti-repaste real-time image rapid recognition result is an independent black-and-white anti-repaste real-time image position abnormality; When the image contour recognition result of the black and white anti-repaste real-time image of the black and white anti-repaste real-time image partition result is normal, and the image feature recognition result of the black and white anti-repaste real-time image is partially abnormal, the black and white anti-repaste real-time image rapid recognition result is that the non-independent black and white anti-repaste real-time image is abnormal.

Images