Abstract
This paper describes a recognition system for on-line cursive handwriting that requires very little initial training and that rapidly learns, and adapts to, the handwriting style of a user. Key features arc a shape analysis algorithm that determines shapes in handwritten words, a linear segmentation algorithm that matches characters identified in handwritten words to characters of candidate words, and a learning algorithm thai adapts to the user writing style. Using a lexicon with 10K words, the system achieved an average recognition rate of 81.3% for lop choice and 91.7% for the top three choices,
This work is done as part of my Ph.D. study under Professor Klaus Truemper in the AI Lab of The University of Texas at Dallas, and funded by the Office of Naval Research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Bramall, P.E., Higgins, C.A.: A Cursive Script Recognition System Based on Human Reading Models. Machine Vision and Applications 8, 224–231 (1995)
Higgins, C.A., Ford, D.M.: On-Line Recognition of Connected Handwriting by Segmentation and Template Matching. In: Proceedings of 11th IAPR International Conference on Pattern Recognition, vol. 2, pp. 200–203 (1992)
Morasso, P., Limonceli, M., Morchio, M.: Incremental Learning experiments with SCRIPTOR: an Engine for On-line Recognition of Cursive Handwriting. Machine Vision and Applications 8, 206–214 (1995)
Powalka, R.K., Sherkat, N., Evett, L.J., Whitrow, R.J.: Multiple Word Segmentation with Interactive Look-up for Cursive Script Recognition. In: Proceedings of the second International Conference on Document Analysis and Recognition, pp. 196–199 (1993)
Qian, G.: The Kritzel System for On-line handwriting Interpretation. In: Proceedings of the Fourteenth National Conference on Artificial Intelligence, Portland, Oregon, p. 1403 (1996)
Schenkel, M., Guyon, I., Henderson, D.: On-line Cursive Script Recognition Using Time-Delay Neural Networks and Hidden Markov Models. Machine Vision and Applications 8, 215–223 (1995)
Schomaker, L.: Using Stroke- or Character-based Self-Organizing Maps in the Recognition of On-line, Connected Cursive Script. Pattern Recognition 26, 443–450 (1993)
Tappert, C.C.: Cursive Script Recognition by Elastic Matching. IBM Journal of Research and Development 26, 765–771 (1982)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Qian, G. (1999). An Adaptive Handwriting Recognition System. In: Zhong, N., Skowron, A., Ohsuga, S. (eds) New Directions in Rough Sets, Data Mining, and Granular-Soft Computing. RSFDGrC 1999. Lecture Notes in Computer Science(), vol 1711. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-48061-7_68
Download citation
DOI: https://doi.org/10.1007/978-3-540-48061-7_68
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66645-5
Online ISBN: 978-3-540-48061-7
eBook Packages: Springer Book Archive