Development of defect detection technology for flexible printed circuit board
FPC defect detection algorithm, multi PCB detection algorithms, but by the unique restriction, FPC defect requires higher accuracy, detection of sample size is bigger, the model of imaging distortion, the defect detection algorithm for PCB plate detection algorithm directly applied to the FPC board, according to the detection algorithm with suitable the actual line features of FPC plate making.
China Jiliang University for the traditional template matching algorithm of slow speed and low accuracy rate of the problem, FPC plate line defects are divided into global and local defects of two kind of defects, the eight connected domain area method based on histogram matching method to capture global image defects, and local defects by projection matching and correlation coefficient method based on image recognition. This method is faster and more accurate than the traditional detection algorithm, but the classification of the related defect categories is not enough.
Analysis of defect detection method for flexible printed circuit board
In order to solve the problem of template matching in the global scope, the local range template matching method is used to detect FPC defects. Based on the outline of the template matching method, contour template should have distinct characteristics of conventional lines on the FPC is to rule, but no significant shape features, and conventional lines are distributed in the whole image, large format template matching time is too slow, is not conducive to the line detection.
Irregular lines belong to the irregular shape of the FPC, including LED lights, S type circle, etc., due to the shape of the peripheral, the wiring is generally related to the structure of the FPC to be checked. In this line, consider the implementation of template matching detection: first, using the template matching method to locate each step coarse line in the whole FPC shaped posture, line shaped access profile; then based on morphological theory for defect detection.
FPC defect detection method is studied from the global and local scope, and the experimental results are obtained:
(1) due to the deformation of the FPC image, the template matching line based on the global range can not locate the defect information on the image correctly.
(2) the local scope of template matching based on the first cut line region on the FPC board relative to the conventional line has significant shape features, as the template source; case detection template in the search area near the corresponding image, compressing the search space; then based on morphological theory line defect detection information.
In short, as the most basic part of the electronic circuit, circuit board greatly affects the quality of the electronic products. Therefore, how to achieve precise PCB defect detection is an important step to ensure the quality of products, while most domestic enterprises generally rely on artificial visual defect detection of FPC, high cost and low efficiency, and because there is no relative standard quality inspection standards, the staff because of the subjective consciousness or visual fatigue and other reasons easily missed and false detection; abroad excellent testing equipment imported by enterprises, equipment price, technical support, customer service and other services limited, it is difficult to adapt to the modern technology of low cost and mass production requirements. Therefore, it is urgent to develop a rapid and efficient FPC defect detection system to meet the domestic market demand.