Defect detection and recognition of bare PCB based on computer vision

Defect detection and recognition of bare PCB plays a significant role in computer vision applications. An accurate and efficient approach is implemented in this paper. The approach is based on the comparison between the standard PCB image and the target image. Multiple images of the qualified PCBs are acquired at the same position. We take an average of the images and consider it to be an initial standard image. The paper suggests the concept of dynamic updation which means we update the standard image during the detection process. The bilateral filtering method is used in the preprocessing phase. Then the target image is compared with the standard image to get the difference image. And a suitable threshold is obtained by analyzing the histogram of the difference image to distinguish potential defect regions. Using the boundary-length-range method, the authenticity of each potential defect region is preliminarily judged. After that, we can identify the bare PCBs which have no defect. Moreover, an improved region growing method is proposed to obtain the complete ranges of the real defect regions. Finally, a simple but effective method is presented to recognize the type of the defects. Experimental results show that the proposed method in this paper works well.