On-demand inspection recipe to detect defects of interest using Mahalanobis distance

This paper introduces a rapid inspection recipe-setup method to detect defects of interest (DOI). Concept of the method is one-pass operation without repeating adjustments to set a recipe immediately as needed. The method applies Maharanobis distance, one of the multivariate analysis techniques, to recognize DOI-like defects. The proposed method enables inspection tool managers to rapidly select an appropriate recipe which detects the most DOI.