Modelling imprints of pharmaceutical tablets for imprint quality visual inspection

Identification of pharmaceutical tablets plays a key role in preventing mix-ups among various types of tablets. Since identification of tablets is most frequently done by imprints, good imprint quality, a property that makes the imprint readable, is of utmost importance. In this paper, we propose a novel method for automated visual inspection of tablets for defect detection and imprint quality inspection. Performance of the method was evaluated on a real tablet image database of imprinted tablets. A "gold standard" was established by manually classifying the tablets into good and defective class. The ROC (receiver operating characteristics) analysis indicated that the proposed method yields better sensitivity and specificity than the previous defect detection method.