A CURSIVE SCRIPT-RECOGNITION SYSTEM BASED ON HUMAN READING MODELS

The human reading process is undoubtedly extremely complex; however, m uch work has been carried out in determining possible mechanisms behin d it. A computer recognition system that makes use of some of the prop osed models of human reading has been developed at the University of N ottingham. With it, we attempt to solve the problem of recognising han dwriting on-line, The system, called NuScript, is based on the blackbo ard paradigm of artificial intelligence (AI). It initially uses easily extracted features to reduce a large lexicon to a smaller list of can didate words. Later stages use increasingly sophisticated knowledge so urces, based on a diverse set of AI paradigms and other pattern-recogn ition techniques, to determine and subsequently refine a confidence va lue for each candidate. A description of the elements of the human rec ognition models on which the system is based is followed by a general description of the computer recognition system as a whole.