Abstract

According to recent advancements in manufacturing industries, Printed Circuit Boards and other components require depth inspection for better quality of product manufacturing. Electronic components are manufactured massively which require better quality assurance. Various approaches have been developed in recent years to provide support for manufacturing industries with the help of data mining or computer vision techniques. During image acquisition, images suffer from various occlusions and orientations which causes performance degradation in image inspection resulting in quality product manufacturing degradation and defective production. To overcome this issue, here we propose a computer vision based approach for defect detection in PCB and classification of defects. Classification is a significant stage to identify defective components. Main aim of this approach is to provide an automated system for PCB defect detection and classification with better accuracy and lower complexities. Proposed automated approach is carried out with the help of symbolic pattern analysis methodology. This approach is implemented on a given PCB image where initially image is transformed into symbolized form and features are extracted by dividing image into sub-regions i.e. background, foreground and shadow of defective region. Finally, a binary classifier is constructed with the help of symbolic dynamics to provide improved classification performance. Experimental study shows improved performance of proposed model when compared with existing state of art algorithms.

Authors and Affiliations