An Algorithm to Group Defects on Printed Circuit Board for Automated Visual Inspection

Due to disadvantages in manual inspection, an automated visual inspection system is needed to eliminate subjective aspects and provides fast and quantitative assessment of printed circuit board (PCB). Up to the present, there has been a lot of work and research concentrated on PCB defect detection. PCB defects detection is necessary for verification of the characteristics of PCB to make sure it is in conformity with the design specifications. However, besides the need to detect the defects, it is also essential to classify these defects so that the source of these defects can be identified. Unfortunately, this area has been neglected and not been given enough attention. Hence, this study proposes an algorithm to group the defects found on bare PCB. Using a synthetically generated PCB image, the algorithm is able to group 14 commonly known PCB defects into five groups. The proposed algorithm includes several image processing operations such as image subtraction, image adding, logical XOR and NOT, and flood fill operator.