Exploiting Collection Level for Improving Assisted Handwritten Words Transcription of Historical Documents

Abstract : Transcription of handwritten words in historical documents is still a difficult task. When processing huge amount of pages, document-centered approaches are limited by the trade-off between automatic recognition errors and the tedious aspect of human user annotation work. In this article, we investigate the use of inter page dependencies to overcome those limitations. For this, we propose a new architecture that allows the exploitation of handwritten word redundancies over pages by considering documents from a higher point of view, namely the collection level. The experiments we conducted on handwritten word transcription show promising results in terms of recognition error and human user work reductions.
Type de document :
Communication dans un congrès
Document Analysis and Recognition (ICDAR), 2011 International Conference on, Sep 2011, China. pp.875 -879, 2011, 〈10.1109/ICDAR.2011.179〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00644950
Contributeur : Joseph Chazalon <>
Soumis le : vendredi 25 novembre 2011 - 15:43:41
Dernière modification le : jeudi 22 février 2018 - 01:25:29
Document(s) archivé(s) le : dimanche 26 février 2012 - 02:32:25

Identifiants

Citation

Laurent Guichard, Joseph Chazalon, Bertrand Coüasnon. Exploiting Collection Level for Improving Assisted Handwritten Words Transcription of Historical Documents. Document Analysis and Recognition (ICDAR), 2011 International Conference on, Sep 2011, China. pp.875 -879, 2011, 〈10.1109/ICDAR.2011.179〉. 〈hal-00644950〉

Partager

Métriques

Consultations de la notice

370

Téléchargements de fichiers

122