Hidden markov models (HMMs) approach for handwriting recognition

Abstract

Hidden Markov models (HMMs) are widely used in the field of pattern recognition. Their original application was in speech recognition (Rabiner and Juang, 1993). Because of the similarities between speech and cursive handwriting recognition, HMMs have become very popular in handwriting recognition as well (Kundu, 1997). During the last few years, HMMs is a frequent approach used in handwriting recognition. One of the reasons is their higher performance in medium to large vocabulary applications where segmentation–recognition methods are used to cope with the difficulties of segmenting words into characters. Many systems use HMMs to model sub–word units (characters) and the Viterbi algorithm to find the best match between a sequence of observations and the models (Chen, 1995).