Coarse Resolution Defect Localization Algorithm for an Automated Visual PCB Inspection

One of the backbones in electronic manufacturing industry is the printed circuit board(PCB) manufacturing. Current practice in PCB manufacturing requires an etching process. Thisprocess is an irreversible process. Printing process, which is done before the etching process, causedmost of the destructive detect found on the PCB. Once the laminate is etched, the defects, if exist wouldcause the PCB laminate to become useless. Due to the fatigue and speed requirement manual inspectionis ineffective to inspect every printed laminate. Therefore, manufacturers require an automated systemto detect the defects online which may occur during the printing process. The defect is detected byutilizing wavelet-based image difference algorithm. Hence, this paper proposes an algorithm for anautomated visual PCB inspection that is able to automatically locate and extract any defect on a PCBlaminate. The algorithm works on the come resolution differenced image in order to locate thedefective area on the fine resolution tested PCB image.