Hidden Markov Model Based Word Recognition and Its Application to Legal Amount Reading on French Checks

Abstract

A hidden Markov model (HMM) based word recognition algorithm for the recognition of legal amounts from French bank checks is presented. This algorithm is part of the A2iA INTERCHEQUE recognition system. The algorithm starts from images of handwritten words which have been automatically segmented from binary check images. After finding the lower-case zone on the complete amount, words are slant corrected and then segmented into graphemes. Then, features are extracted from the graphemes, and the feature vectors are vector quantized resulting in a sequence of symbols for each word. Likelihoods of all word classes are computed by a set of HMMs, which have been previously trained using either the Viterbi algorithm or the Baum–Welch algorithm. The various parameters of the system have been identified and their importance evaluated. Results have been obtained on large real-life data bases of French handwritten checks. The HMM-based system has been shown to outperform a holistic word recognizer and another HMM-type word recognizer from the A2iA INTERCHEQUE recognition system. Word recognition rates of about 89% for the 26-word vocabulary relevant for legal amount recognition on French bank checks have been obtained. More recently, a Neural Network–HMM hybrid has been designed, which produces even better recognition rates.