Visual Detection of FPC Connector Defects Based on Improved Canny Operator

In order to improve the detection accuracy and stability of FPC connector defects, a machine vision detection method based on an improved Canny operator was proposed in this paper. Firstly, perform line detection through point fitting to calculate the tilt angle, and then perform rotation correction on FPC image. Next, Otsu algorithm was used to segment the filtered image, and an improved Canny operator was proposed to achieve edge detection, which can effectively suppress the effects of pseudo edges and edge fractures by utilizing sub-pixel information in the gradient direction. Based on the characteristics such as size, area, and position of the detection target, the defect target was segmented by subtracting it from the original image through opening operation. Moreover, a improved shape matching was used for detecting damaged defects, and the number of missing pin angles can be obtained simultaneously through position information. Finally, a corresponding FPC connector defect visual inspection device was developed. The experimental results show that the proposed method can achieve automatic detection and classification of common defects with a detection accuracy of over 95%.