High Performance Unconstrained Word Recognition System Combining HMMs and Markov Random Field

George Saon (1) , Abdel Belaïd (1)

1 READ - READ

In this paper we present a system for the recognition of handwritten words on literal check amounts which advantageously combine HMMs and Markov random fields (MRFs). It operates at pixel level, in a holistic manner, on height normalized word images which are viewed as random field realizations. The HMM analyzes the image along the horizontal writing direction, in a specific state observation probability given by the column product of causal MRF-like pixel conditional probabilities. Aspects concerning definition, training and recognition via this type of model are developed throughout the paper. We report a 90.08% average word recognition rate on 2378 words and a 79.52% amount rate on 579 amounts of the SRTP (Service de Recherche Technique de la Poste) French postal check database (7031 words, 1779 amounts, different scriptors).

Mots clés: Hidden Markov model; Reconnaissance forme; Pattern recognition; Hand writing; Word; Markov model; Random field; Ecriture; Mot; Modèle Markov; Champ aléatoire; Chèque postal; Modèle Markov variable cachée

Domaines: Bibliothèque électronique [cs.DL]

George Saon, Abdel Belaïd. High Performance Unconstrained Word Recognition System Combining HMMs and Markov Random Field. International Journal of Pattern Recognition and Artificial Intelligence, 1997, 11 (5), pp.771-788. ⟨10.1142/S0218001497000342⟩. ⟨inria-00539591⟩