Using Segmentation Constraints in an Implicit Segmentation Scheme for On-line Word Recognition

Abstract : In this paper, we propose the introduction of a parametric weighting function to constrain the segmentation path which governs the training of a hybrid neuromarkovian scheme for an on-line word recognition system. Due to the parametric properties of this function, it is possible to modulate the constraints from imposing a strict balanced path with the same duration for every states to a totally free segmentation path. So far, during the initialization step of the training, when the neural network has little ability to correctly segment the word into its basic constituents, the constraints will be activated, and then, they will be relaxed to allow more flexibility to the segmentation-recognition process. Recognition experiments on the Ironoff database demonstrated that the proposed method allows to increase the word recognition rate when compared to a totally unconstrained segmentation training.
Type de document :
Communication dans un congrès
Guy Lorette. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006
Liste complète des métadonnées

Littérature citée [12 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00108320
Contributeur : Ist Rennes <>
Soumis le : vendredi 20 octobre 2006 - 14:23:10
Dernière modification le : mercredi 16 mai 2018 - 11:48:01
Document(s) archivé(s) le : mardi 6 avril 2010 - 18:25:24

Identifiants

  • HAL Id : inria-00108320, version 1

Collections

Citation

Émilie Caillault, Christian Viard-Gaudin. Using Segmentation Constraints in an Implicit Segmentation Scheme for On-line Word Recognition. Guy Lorette. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006. 〈inria-00108320〉

Partager

Métriques

Consultations de la notice

211

Téléchargements de fichiers

157