A Lexicon Driven Method for Unconstrained Bangla Handwritten Word Recognition

Abstract : In this paper a lexicon driven segmentationrecognition scheme for unconstrained Bangla handwritten word recognition is proposed for Indian postal automation. In the proposed method, at first, binarization of the input document is done and slant correction of the individual words is performed. Next, using water reservoir concept words are pre-segmented into possible primitive components (characters or its parts). In order to merge these primitive components into characters and to find optimum character segmentation, dynamic programming (DP) is applied using total likelihood of characters as the objective function. To compute the likelihood of a character, modified quadratic discriminant function (MQDF) is used for the purpose. The features used in the MQDF are mainly based on the directional features of the contour points of the components. We tested our system on Bangla city-name images and at present an overall accuracy of 87.21% is obtained from the proposed system.
Type de document :
Communication dans un congrès
Guy Lorett. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006
Liste complète des métadonnées

Littérature citée [14 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00104048
Contributeur : Anne Jaigu <>
Soumis le : jeudi 5 octobre 2006 - 16:31:49
Dernière modification le : samedi 28 juillet 2018 - 14:54:01
Document(s) archivé(s) le : mardi 6 avril 2010 - 18:35:04

Identifiants

  • HAL Id : inria-00104048, version 1

Collections

Citation

U. Pal, K. Roy, F. Kimura. A Lexicon Driven Method for Unconstrained Bangla Handwritten Word Recognition. Guy Lorett. Tenth International Workshop on Frontiers in Handwriting Recognition, Oct 2006, La Baule (France), Suvisoft, 2006. 〈inria-00104048〉

Partager

Métriques

Consultations de la notice

178

Téléchargements de fichiers

314