MS-TDNN with Global Discriminant Trainings

Authors:
Emilie CAILLAULT;Christian VIARD-GAUDIN;Abdul Rahim AHMAD
Affiliations:
Laboratoire IRCCyN UMR CNRS Polytech Nantes, France;Laboratoire IRCCyN UMR CNRS Polytech Nantes, France;Laboratoire IRCCyN UMR CNRS Polytech Nantes, France
Venue:
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Year:
2005

Citing 5
Cited 1

The IRESTE On/Off (IRONOFF) Dual Handwriting Database

ICDAR '99 Proceedings of the Fifth International Conference on Document Analysis and Recognition
Integration of an On-Line Handwriting Recognition System in a Smart Phone Device

ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
An Analytical Handwritten Word Recognition System with Word-level Discriminant Training

ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
An Activation-Verification Model for On-Line Texts Recognition

IWFHR '04 Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition
Initialization of hidden Markov models for unconstrained on-line handwriting recognition

ICASSP '96 Proceedings of the Acoustics, Speech, and Signal Processing, 1996. on Conference Proceedings., 1996 IEEE International Conference - Volume 06

Combining diverse on-line and off-line systems for handwritten text line recognition

Pattern Recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This article analyses the behavior of various hybrid architectures based on a multi-state neuro-markovian scheme (MS-TDNN HMM) applied to online handwriting word recognition systems. We have considered different cost functions, including maximal mutual information criteria with discriminant training and maximum likelihood estimation, to train the systems globally at the word level and also we varied the number of states from one up to three model basic hidden markov models at the letter levekl. We report experimental results for non constrained, write independent, word recognition obtained on the IRONOFF database.