Optimizing a Video Preprocessor for OCR

This paper describes how opt imal video preprocessor performance can be achieved using a software recogni t ion system and a set of control led exper iments. It basical ly involves opt imizing on a constant threshold and then using recognit ion logic designed f r om that threshold to optimize an adaptive threshold function or threshold operator. By using this technique, the video preprocessor can be optimized ear ly In the development of an OCR (Optical Character Recognition) machine. The software recognit ion system is described and experimental data is presented to i l lus t ra te the procedures.