Automated inspection of IC wafer contamination

摘要

This paper addresses the task of automating the visual inspection of contamination on the surface of integrated circuits (IC) wafers arising from the dicing process. Using a set of multi-spectral optical filters and a charged coupled device (CCD) video camera, several images are acquired from each IC wafer under different illumination conditions, from which feature space data are then generated. Three conventional classification methods – an artificial neural network (ANN) using a back-propagation (BP) technique, a minimum distance algorithm, and a maximum likelihood classifier are evaluated, and their performances are compared. In addition, important elements of the feature space, i.e., the optimal illumination condition and appropriate optical spectrum are investigated. The results show that the image-acquisition technique developed is effective in discriminating feature elements, and that the employed ANN–BP classifier can accurately achieve the required binary (clean/contaminated IC wafers) decisions.