Maximum mutual information training for an on-line neural predictive word recognition system - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue International Journal on Document Analysis and Recognition Année : 2001

Maximum mutual information training for an on-line neural predictive word recognition system

Sonia Garcia-Salicetti
Bernadette Dorizzi
Zsolt Wimmer
  • Fonction : Auteur

Résumé

In this paper, we present a hybrid online handwriting recognition system based on hidden Markov models (HMMs). It is devoted to word recognition using large vocabularies. An adaptive segmentation of words into letters is integrated with recognition, and is at the heart of the training phase. A word-model is a left-right HMM in which each state is a predictive multilayer perceptron that performs local regression on the drawing (i.e., the written word) relying on a context of observations. A discriminative training paradigm related to maximum mutual information is used, and its potential is shown on a database of 9,781 words.

Dates et versions

hal-01184330 , version 1 (14-08-2015)

Identifiants

Citer

Sonia Garcia-Salicetti, Bernadette Dorizzi, Patrick Gallinari, Zsolt Wimmer. Maximum mutual information training for an on-line neural predictive word recognition system. International Journal on Document Analysis and Recognition, 2001, 4 (1), pp.56-68. ⟨10.1007/PL00013574⟩. ⟨hal-01184330⟩
57 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More