Generation of Learning Samples for Historical Handwriting Recognition Using Image Degradation

Andreas Fischer (1) , Muriel Visani (2) , van Cuong Kieu (2, 3) , Ching Y. Suen (4)

1 CENPARMI
2 L3I - Laboratoire Informatique, Image et Interaction - EA 2118
3 LaBRI - Laboratoire Bordelais de Recherche en Informatique
4 CENPARMI

Historical documents pose challenging problems for training handwriting recognition systems.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.

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]; Apprentissage [cs.LG]; Base de données [cs.DB]; Performance et fiabilité [cs.PF]

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of Learning Samples for Historical Handwriting Recognition Using Image Degradation. 2nd International Workshop on Historical Document Imaging and Processing, Aug 2013, Washington, DC, USA, United States.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⟩