Matching Images of Imprinted Tablets

Various types of tablets produced by pharmaceutical industry must be easily and accurately identified by customers. Besides tablet's shape, size and colour, additional visual features such as tablet imprints are necessary for unique identification and, at the same time, the tablets should comply with the high visual quality standards. We focused on visual quality inspection of imprinted tablets by means of automated image analysis that requires registration of tablet images. Three different registration methods, based on direct matching of pixel intensities, principal axes matching, and circular profile matching, were compared on a large image database comprising various types of tablets. The circular profile matching method proved to be a powerful image analysis tool for improving visual quality inspection of imprinted tablets in real-time.