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

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.

[1]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[2]  Yves Lecourtier,et al.  Recognition of handwritten words using stochastic models , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[3]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[4]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[5]  Yochai Konig,et al.  REMAP: Recursive Estimation and Maximization of A Posteriori Probabilities - Application to Transition-Based Connectionist Speech Recognition , 1995, NIPS.

[6]  Keinosuke Fukunaga,et al.  Introduction to Statistical Pattern Recognition , 1972 .

[7]  Michel Gilloux,et al.  A hybrid radial basis function network/hidden Markov model handwritten word recognition system , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[8]  L. R. Rabiner,et al.  An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition , 1983, The Bell System Technical Journal.

[9]  Hervé Bourlard,et al.  Connectionist Speech Recognition: A Hybrid Approach , 1993 .

[10]  Yoshua Bengio,et al.  LeRec: A NN/HMM Hybrid for On-Line Handwriting Recognition , 1995, Neural Computation.

[11]  Nikolai Gorski,et al.  The A2iA Intercheque System: Courtesy Amount and Legal Amount Recognition for French Checks , 1997, Int. J. Pattern Recognit. Artif. Intell..

[12]  Ching Y. Suen,et al.  Cursive script recognition applied to the processing of bank cheques , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[13]  Fumitaka Kimura,et al.  Segmentation-recognition algorithm for zip code field recognition , 2007, Machine Vision and Applications.

[14]  George Saon,et al.  Recognition of Unconstrained Handwritten Words using Markov Random Fields and HMMs , 1995 .