Generation of Learning Samples for Historical Handwriting Recognition Using Image Degradation

Abstract : Historical documents pose challenging problems for training handwriting recognition systems. Besides the high variability of character shapes inherent to all handwriting, the image quality can also differ greatly, for instance due to faded ink, ink bleed-through, wrinkled and stained parchment. Especially when only few learning samples are available, it is difficult to incorporate this variability in the morphological character models. In this paper, we investigate the use of image degradation to generate synthetic learning samples for historical handwriting recognition. With respect to three image degradation models, we report significant improvements in accuracy for recognition with hidden Markov models on the medieval Saint Gall and Parzival data sets.
Type de document :
Communication dans un congrès
2nd International Workshop on Historical Document Imaging and Processing, Aug 2013, Washington, DC, USA, United States
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01006088
Contributeur : Van Cuong Kieu <>
Soumis le : vendredi 13 juin 2014 - 16:41:30
Dernière modification le : jeudi 9 février 2017 - 16:58:38
Document(s) archivé(s) le : samedi 13 septembre 2014 - 11:30:39

Fichier

fischer13hip.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01006088, version 1

Collections

Citation

Andreas Fischer, Muriel Visani, Van Cuong Kieu, Ching Y. Suen. Generation of Learning Samples for Historical Handwriting Recognition Using Image Degradation. 2nd International Workshop on Historical Document Imaging and Processing, Aug 2013, Washington, DC, USA, United States. <hal-01006088>

Partager

Métriques

Consultations de
la notice

188

Téléchargements du document

143