Writer Style Adaptation of On-line Handwriting Recognizers: A Fuzzy Mechanism Approach

Harold Mouchère 1, * Eric Anquetil 1 Nicolas Ragot 1
* Auteur correspondant
1 IMADOC - Interprétation et Reconnaissance d’Images et de Documents
UR1 - Université de Rennes 1, INSA Rennes - Institut National des Sciences Appliquées - Rennes, CNRS - Centre National de la Recherche Scientifique : UMR6074
Abstract : In this study we present an automatic on-line adaptation mechanism to the writer's handwriting style for the recognition of isolated handwritten characters. The classifier we use here is based on a Fuzzy Inference System (FIS) similar to those we have developed for handwriting recognition but simplified for this study. Doing so, the adaptation mechanisms presented here can be transposed to the original systems. In this FIS each premise rule is composed of a fuzzy prototype which represents intrinsic properties of a class. The consequent part of rules associates a score to the prototype for each class. The adaptation mechanism affects both the conclusions of the rules and the fuzzy prototypes by re-centering them thanks to a new approach inspired by the Learning Vector Quantization. Doing so, the FIS is automatically fitted to the handwriting style of the writer that currently uses the system. The adaptation mechanisms were tested with 8 different writers and the results illustrate the benefits of the method in term of error rate reduction (up to 80% and 69% in average). This allows such kind of simple classifiers to achieve up to 97.7% of recognition accuracy on the 26 Latin letters.
Type de document :
Communication dans un congrès
A. Marcelli and C. De Stefano. International Graphonomics Society, Jun 2005, Salerno, Italy. pp.193-197, 2005, Proceedings of the 12th Conference of the International Graphonomics Society (IGS)
Liste complète des métadonnées

https://hal.inria.fr/inria-00300474
Contributeur : Harold Mouchère <>
Soumis le : vendredi 18 juillet 2008 - 13:56:58
Dernière modification le : mercredi 16 mai 2018 - 11:23:01

Identifiants

  • HAL Id : inria-00300474, version 1

Citation

Harold Mouchère, Eric Anquetil, Nicolas Ragot. Writer Style Adaptation of On-line Handwriting Recognizers: A Fuzzy Mechanism Approach. A. Marcelli and C. De Stefano. International Graphonomics Society, Jun 2005, Salerno, Italy. pp.193-197, 2005, Proceedings of the 12th Conference of the International Graphonomics Society (IGS). 〈inria-00300474〉

Partager

Métriques

Consultations de la notice

259