Abstract
Automated visual inspection is an important step to assure the quality of printed circuit boards (PCB). Component placement errors such as missing, misaligned or incorrectly rotated component are major causes of defects on surface mount PCB. This paper proposes a novel automated visual inspection method for PCB. The proposed method uses a sequence of image processing techniques inspired by the theory of inventive problem solving (TRIZ) with Affine-SIFT image matching techniques to enhance the component placement inspection. Only analytic discussions are presented in this paper to support the potential of the proposed method.