A Statistical Shape Model and SVMs Based Scheme for Visual Inspection of Microdrill Bits in PCB Production

This paper proposes an automatic visual inspection scheme with phase identification of microdrill bits in printed circuit board (PCB) production. Our method mainly includes two procedures: firstly the statistical shape models of microdrill bit is built to get the shape subspace, and then the phase identification is performed in the shape subspace using some pattern recognition techniques. In this paper, we compared the performance of two statistical model methods, principal component analysis (PCA) and linear discriminate analysis (LDA) together with three classifiers, support vector machines (SVMs), neural networks (NNs) and k-nearest neighbors (kNN) respectively for phase identification of microdrill bits. The experimental results demonstrate that using low enlargement and resolution microdrill bit images the proposed method can measure up to high inspection accuracy, and provide an conclusion that the highest identification rates were obtained by PCA-SVMs.