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

Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01184330
Contributor : Lip6 Publications <>
Submitted on : Friday, August 14, 2015 - 11:02:22 AM
Last modification on : Friday, May 24, 2019 - 5:25:39 PM

Links full text

Identifiers

Citation

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, Springer Verlag, 2001, 4 (1), pp.56-68. ⟨10.1007/PL00013574⟩. ⟨hal-01184330⟩

Share

Metrics

Record views

125