Writer Adaptation Techniques in Off-line Cursive Word Recognition

Vinciarelli, A. and Bengio, S. (2002) Writer Adaptation Techniques in Off-line Cursive Word Recognition. In: Proceedings Eighth International Workshop on Frontiers in Handwriting Recognition, 2002, pp. 287-291. (doi: 10.1109/IWFHR.2002.1030924)

Abstract

This work presents the application of HMM adaptation techniques to the problem of off-line cursive script recognition. Instead of training a new model for each writer one first creates a unique model with a mixed database and then adapts it for each different writer using his own small dataset. Experiments on a publicly available benchmark database show that an adapted system has an accuracy higher than 80% even when less than 30 word samples are used during adaptation, while a system trained using the data of the single writer only needs at least 200 words (the estimate is a lower bound) in order to achieve the same performance as the adapted models.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Vinciarelli, Professor Alessandro
• Authors: Vinciarelli, A., and Bengio, S.
• College/School: College of Science and Engineering > School of Computing Science