FPC board lamination deviation monitoring method based on image processing technology

Abstract

The invention relates to the field of FPC board lamination monitoring, in particular to an FPC board lamination deviation monitoring method based on an image processing technology, and the method comprises the steps: obtaining FPC board lamination real-time image data, and obtaining an FPC board lamination basic recognition result; obtaining an FPC board lamination image region division result based on an image processing technology by using the FPC board lamination basic identification result; according to the method, an FPC board lamination deviation monitoring result is obtained by utilizing an FPC board lamination image region division result, preliminary rapid screening is performed on collected FPC lamination real-time images, then a screening basis is set step by step, secondary processing is performed on the preliminarily screened images, a corresponding supervision and judgment means is provided for any part of the images monitored in real time, and the accuracy of the FPC lamination deviation monitoring is improved. The image recognition accuracy of a large-batch laminating process is ensured, and the method has relatively high feature pertinence.

Description

Technical Field

[0001] The invention relates to the field of FPC board lamination monitoring, and in particular to an FPC board lamination deviation monitoring method based on image processing technology. Background Art

[0002] When the FPC board is undergoing the bonding process, the bonding results of the FPC board need to be monitored to facilitate the normal operation of the process production line and the accurate processing of the next process. However, due to the bonding materials of the FPC board and the long-term use errors of the bonding machine, there are still certain errors in the final bonding output of large quantities of FPC boards, and a practical solution is needed for monitoring the fast process production line. Summary of the invention

[0003] In view of the shortcomings of the prior art, the present invention provides an FPC board fitting deviation monitoring method based on image processing technology, which performs multi-level monitoring processing based on multiple types of real-time image data to quickly and accurately obtain the final fitting deviation monitoring results.

[0004] To achieve the above object, the present invention provides a method for monitoring the lamination deviation of an FPC board based on image processing technology, comprising: Acquire the real-time image data of FPC board bonding to obtain the basic recognition result of FPC board bonding; Using the FPC board bonding basic recognition result, based on image processing technology, an FPC board bonding image area division result is obtained; The FPC board bonding image area division result is used to obtain the FPC board bonding deviation monitoring result.

[0005] Preferably, the acquiring of the real-time image data of the FPC board bonding to obtain the basic recognition result of the FPC board bonding includes: Get real-time image data of FPC board bonding; Determine whether the FPC board pasting real-time image data is abnormal, if so, obtain the FPC board pasting basic recognition result according to the abnormal data of the FPC board pasting real-time image data, otherwise, the FPC board pasting basic recognition result is normal; The real-time image data of the FPC board bonding include the FPC board bonding area, the FPC board bonding angle and the FPC board bonding type.

[0006] Further, the FPC board bonding basic recognition result is obtained according to the abnormal data of the FPC board bonding real-time image data, including: Determine whether the number of abnormal data in the FPC board pasting real-time image data is 1. If so, obtain the FPC board pasting basic recognition result according to the abnormal FPC board pasting real-time image data. Otherwise, the FPC board pasting basic recognition result is abnormal and the processing is abandoned.

[0007] Further, the basic recognition result of FPC board bonding obtained according to the abnormal FPC board bonding real-time image data includes: When the abnormal FPC board lamination real-time image data is the FPC board lamination area, it is determined whether there is an abnormal area in the FPC board lamination type. If so, the FPC board lamination basic recognition result is abnormal. Otherwise, the FPC board lamination basic recognition result is an abnormality to be processed. When the abnormal FPC board lamination real-time image data is the FPC board lamination angle, the FPC board lamination basic recognition result is abnormal; When the abnormal FPC board bonding real-time image data is of the FPC board bonding type, determine whether the FPC board bonding area exceeds 1.5 times the standard FPC board bonding area. If so, the FPC board bonding basic recognition result is abnormal; otherwise, the FPC board bonding basic recognition result is an exception to be processed.

[0008] Preferably, the FPC board bonding basic recognition result is used to obtain the FPC board bonding image area division result based on image processing technology, including: Obtain the basic recognition result of the FPC board bonding and perform area division processing to obtain the FPC board bonding image contour area data and the FPC board bonding image feature area data; Obtaining an FPC board fitting image contour area recognition result using the FPC board fitting image contour area data; Obtaining an FPC board bonding image feature area recognition result using the FPC board bonding image feature area data; The FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result are used as the FPC board bonding image area division result.

[0009] Furthermore, the acquisition of the FPC board bonding basic recognition result and performing area division processing to obtain the FPC board bonding image contour area data and the FPC board bonding image feature area data includes: Get the FPC board bonding basic recognition results; Using the FPC board bonding basic recognition result, based on image processing technology and according to the FPC board bonding standard, the FPC board bonding image contour area data is obtained; The FPC board pasting image contour area data in the FPC board pasting basic recognition result is removed as the FPC board pasting image feature area data.

[0010] Further, obtaining the FPC board fitting image contour area recognition result using the FPC board fitting image contour area data includes: Determine whether the FPC board laminating image contour area data is symmetrically corresponding, if so, the FPC board laminating image contour area recognition result is normal, otherwise, the FPC board laminating image contour area recognition result is abnormal; The contour area data of the same FPC board laminating image is the closed area data corresponding to the laminating material contour of the FPC board.

[0011] Further, obtaining the FPC board bonding image feature area recognition result using the FPC board bonding image feature area data includes: Determine whether the FPC board bonding image feature area data is single and complete, if so, the FPC board bonding image feature area recognition result is normal, otherwise, obtain the image feature overlapping data of the FPC board bonding image feature area data; The image feature overlapping data is used to obtain the FPC board fitting image feature area recognition result.

[0012] Furthermore, obtaining the FPC board lamination image feature area recognition result by using the image feature overlap data includes: Determine whether there is FPC board pasting image contour area data in the image feature overlap data, if so, obtain the number of FPC board pasting image contour area data, otherwise, the FPC board pasting image feature area recognition result is abnormal; It is determined whether the number of the FPC board fitting image contour area data is 1. If so, the FPC board fitting image feature area recognition result is an independent abnormality; otherwise, the FPC board fitting image feature area recognition result is a partial abnormality.

[0013] Preferably, obtaining the FPC board lamination deviation monitoring result by using the FPC board lamination image area division result includes: When the FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result of the FPC board bonding image area division result are both normal, the FPC board bonding deviation monitoring result is normal; When the FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result of the FPC board bonding image area division result are both abnormal, the FPC board bonding deviation monitoring result is abnormal; When the FPC board bonding image contour area recognition result of the FPC board bonding image area division result is normal, and the FPC board bonding image feature area recognition result is independently abnormal, the FPC board bonding deviation monitoring result is that the FPC board bonding position is abnormal; When the FPC board fitting image contour area recognition result of the FPC board fitting image area division result is normal, and the FPC board fitting image feature area recognition result is partially abnormal, the FPC board fitting deviation monitoring result is FPC board fitting overlap abnormality.

[0014] Compared with the closest prior art, the present invention has the following beneficial effects: The collected real-time FPC bonding images are initially and quickly screened, and then the screening criteria are set up step by step, and the initially screened images are processed for the second time. There are corresponding supervision and evaluation methods for any part of the real-time monitored images, and the image recognition accuracy of large-scale bonding processes is guaranteed, with strong feature targeting. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 The present invention provides a flow chart of a method for monitoring the lamination deviation of an FPC board based on image processing technology. 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 monitoring the lamination deviation of an FPC board based on image processing technology, such as Figure 1 As shown, including: S1, obtaining the real-time image data of FPC board bonding to obtain the basic recognition result of FPC board bonding; S2, using the FPC board bonding basic recognition result based on image processing technology to obtain the FPC board bonding image area division result; S3. Obtaining FPC board lamination deviation monitoring results using the FPC board lamination image area division results.

[0019] S1 specifically includes: S1-1, obtaining real-time image data of FPC board bonding; S1-2, judging whether the real-time image data of the FPC board bonding is abnormal, if so, obtaining the basic recognition result of the FPC board bonding according to the abnormal data of the real-time image data of the FPC board bonding, otherwise, the basic recognition result of the FPC board bonding is normal; The real-time image data of the FPC board bonding include the FPC board bonding area, the FPC board bonding angle and the FPC board bonding type.

[0020] S1-2 specifically includes: S1-2-1. Determine whether the number of abnormal data in the FPC board pasting real-time image data is 1. If so, obtain the FPC board pasting basic recognition result based on the abnormal FPC board pasting real-time image data. Otherwise, the FPC board pasting basic recognition result is abnormal and the processing is abandoned.

[0021] S1-2-1 specifically includes: S1-2-1-1, when the abnormal FPC board lamination real-time image data is the FPC board lamination area, determine whether there is an abnormal area in the FPC board lamination type, if so, the FPC board lamination basic recognition result is abnormal, otherwise, the FPC board lamination basic recognition result is an abnormality to be processed; S1-2-1-2, when the abnormal FPC board bonding real-time image data is the FPC board bonding angle, the FPC board bonding basic recognition result is abnormal; S1-2-1-3. When the real-time image data of the abnormal FPC board fitting is of the FPC board fitting type, determine whether the FPC board fitting area exceeds 1.5 times the standard FPC board fitting area. If so, the FPC board fitting basic recognition result is abnormal. Otherwise, the FPC board fitting basic recognition result is an exception to be processed.

[0022] S2 specifically includes: S2-1, obtaining the basic recognition result of FPC board bonding and performing area division processing to obtain the contour area data of FPC board bonding image and the feature area data of FPC board bonding image; S2-2, using the FPC board fitting image contour area data to obtain the FPC board fitting image contour area recognition result; S2-3, using the FPC board bonding image feature area data to obtain the FPC board bonding image feature area recognition result; S2-4, using the FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result as the FPC board bonding image area division result.

[0023] S2-1 specifically includes: S2-1-1, obtain the FPC board bonding basic recognition result; S2-1-2, using the FPC board bonding basic recognition result based on image processing technology and according to the FPC board bonding standard to obtain FPC board bonding image contour area data; S2-1-3, removing the FPC board pasting image contour area data in the FPC board pasting basic recognition result as the FPC board pasting image feature area data.

[0024] In the present embodiment, a method for monitoring the misalignment of an FPC board is provided based on image processing technology, wherein the image processing technology process is as follows: 1. grayscale conversion and noise reduction; 2. edge detection; 3. contour extraction; 4. re-execute step 3 to improve accuracy; 5. find the contour line, which is the outer closed line of the FPC board bonding material; 6. obtain the result.

[0025] S2-2 specifically includes: S2-2-1, judging whether the FPC board laminating image contour area data is symmetrically corresponding, if so, the FPC board laminating image contour area recognition result is normal, otherwise, the FPC board laminating image contour area recognition result is abnormal; The contour area data of the same FPC board laminating image is the closed area data corresponding to the laminating material contour of the FPC board.

[0026] S2-3 specifically includes: S2-3-1, determining whether the FPC board bonding image feature area data is single and complete, if so, the FPC board bonding image feature area recognition result is normal, otherwise, obtaining the image feature overlapping data of the FPC board bonding image feature area data; S2-3-2. Obtain the FPC board bonding image feature area recognition result using the image feature overlapping data.

[0027] S2-3-2 specifically includes: S2-3-2-1, determine whether there is FPC board pasting image contour area data in the image feature overlapping data, if so, obtain the number of FPC board pasting image contour area data, otherwise, the FPC board pasting image feature area recognition result is abnormal; S2-3-2-2. Determine whether the number of FPC board fitting image contour area data is 1. If so, the FPC board fitting image feature area recognition result is an independent exception. Otherwise, the FPC board fitting image feature area recognition result is a partial exception.

[0028] S3 specifically includes: S3-1, when the FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result of the FPC board bonding image area division result are both normal, the FPC board bonding deviation monitoring result is normal; S3-2, when the FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result of the FPC board bonding image area division result are both abnormal, the FPC board bonding deviation monitoring result is abnormal; S3-3, when the FPC board bonding image contour area recognition result of the FPC board bonding image area division result is normal, and the FPC board bonding image feature area recognition result is an independent abnormality, the FPC board bonding deviation monitoring result is an FPC board bonding position abnormality; S3-4, when the FPC board fitting image contour area recognition result of the FPC board fitting image area division result is normal, and the FPC board fitting image feature area recognition result is partially abnormal, the FPC board fitting deviation monitoring result is FPC board fitting overlap abnormality.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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 method for monitoring the lamination deviation of FPC boards based on image processing technology, characterized in that: include: Acquire the real-time image data of FPC board bonding to obtain the basic recognition result of FPC board bonding; Using the FPC board bonding basic recognition result, based on image processing technology, an FPC board bonding image area division result is obtained; The FPC board bonding image area division result is used to obtain the FPC board bonding deviation monitoring result.

2. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 1, characterized in that: The obtaining of the real-time image data of the FPC board bonding to obtain the basic recognition result of the FPC board bonding includes: Get real-time image data of FPC board bonding; Determine whether the FPC board pasting real-time image data is abnormal, if so, obtain the FPC board pasting basic recognition result according to the abnormal data of the FPC board pasting real-time image data, otherwise, the FPC board pasting basic recognition result is normal; The real-time image data of the FPC board bonding include the FPC board bonding area, the FPC board bonding angle and the FPC board bonding type.

3. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 2 is characterized in that: The basic recognition result of FPC board bonding obtained according to the abnormal data of the real-time image data of FPC board bonding includes: Determine whether the number of abnormal data in the FPC board pasting real-time image data is 1. If so, obtain the FPC board pasting basic recognition result according to the abnormal FPC board pasting real-time image data. Otherwise, the FPC board pasting basic recognition result is abnormal and the processing is abandoned.

4. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 3 is characterized in that: The basic recognition results of FPC board bonding obtained based on the abnormal FPC board bonding real-time image data include: When the abnormal FPC board lamination real-time image data is the FPC board lamination area, it is determined whether there is an abnormal area in the FPC board lamination type. If so, the FPC board lamination basic recognition result is abnormal. Otherwise, the FPC board lamination basic recognition result is an abnormality to be processed. When the abnormal FPC board lamination real-time image data is the FPC board lamination angle, the FPC board lamination basic recognition result is abnormal; When the abnormal FPC board bonding real-time image data is of the FPC board bonding type, determine whether the FPC board bonding area exceeds 1.5 times the standard FPC board bonding area. If so, the FPC board bonding basic recognition result is abnormal; otherwise, the FPC board bonding basic recognition result is an exception to be processed.

5. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 1, characterized in that: The FPC board bonding image area division results obtained by using the FPC board bonding basic recognition results based on image processing technology include: Obtain the basic recognition result of the FPC board bonding and perform area division processing to obtain the FPC board bonding image contour area data and the FPC board bonding image feature area data; Obtaining an FPC board fitting image contour area recognition result using the FPC board fitting image contour area data; Obtaining an FPC board bonding image feature area recognition result using the FPC board bonding image feature area data; The FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result are used as the FPC board bonding image area division result.

6. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 5, characterized in that: The method of obtaining the FPC board bonding basic recognition result and performing area division processing to obtain the FPC board bonding image contour area data and the FPC board bonding image feature area data includes: Get the FPC board bonding basic recognition results; Using the FPC board bonding basic recognition result, based on image processing technology and according to the FPC board bonding standard, the FPC board bonding image contour area data is obtained; The FPC board pasting image contour area data in the FPC board pasting basic recognition result is removed as the FPC board pasting image feature area data.

7. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 5, characterized in that: Obtaining the FPC board fitting image contour area recognition result using the FPC board fitting image contour area data includes: Determine whether the FPC board laminating image contour area data is symmetrically corresponding, if so, the FPC board laminating image contour area recognition result is normal, otherwise, the FPC board laminating image contour area recognition result is abnormal; The contour area data of the same FPC board laminating image is the closed area data corresponding to the laminating material contour of the FPC board.

8. The method for monitoring the lamination deviation of FPC boards based on image processing technology as claimed in claim 5, characterized in that: Obtaining the FPC board bonding image feature area recognition result using the FPC board bonding image feature area data includes: Determine whether the FPC board bonding image feature area data is single and complete, if so, the FPC board bonding image feature area recognition result is normal, otherwise, obtain the image feature overlapping data of the FPC board bonding image feature area data; The image feature overlapping data is used to obtain the FPC board fitting image feature area recognition result.

9. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 8, characterized in that: The FPC board lamination image feature area recognition result obtained by using the image feature overlapping data includes: Determine whether there is FPC board pasting image contour area data in the image feature overlap data, if so, obtain the number of FPC board pasting image contour area data, otherwise, the FPC board pasting image feature area recognition result is abnormal; It is determined whether the number of the FPC board fitting image contour area data is 1. If so, the FPC board fitting image feature area recognition result is an independent abnormality; otherwise, the FPC board fitting image feature area recognition result is a partial abnormality.

10. The FPC board lamination deviation monitoring method based on image processing technology as claimed in claim 1, characterized in that: The FPC board lamination deviation monitoring results obtained by using the FPC board lamination image area division results include: When the FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result of the FPC board bonding image area division result are both normal, the FPC board bonding deviation monitoring result is normal; When the FPC board bonding image contour area recognition result and the FPC board bonding image feature area recognition result of the FPC board bonding image area division result are both abnormal, the FPC board bonding deviation monitoring result is abnormal; When the FPC board bonding image contour area recognition result of the FPC board bonding image area division result is normal, and the FPC board bonding image feature area recognition result is independently abnormal, the FPC board bonding deviation monitoring result is that the FPC board bonding position is abnormal; When the FPC board fitting image contour area recognition result of the FPC board fitting image area division result is normal, and the FPC board fitting image feature area recognition result is partially abnormal, the FPC board fitting deviation monitoring result is FPC board fitting overlap abnormality.

Images