Abstract
SCRIPTOR is an engine for on-line recognition of cursive script able to learn individual writing features and/or user-defined pen gestures in an incremental way. In this paper we describe experiments for characterizing the learning process in an interactive environment and an automatic allograph segmentation mechanism capable of supporting incremental learning.
Similar content being viewed by others
References
Kohonen T (1982) Self-organizing formation of topologically correct feature maps. Biol Cybern 43:59–69
Kohonen T (1989) Self-organization and associative memory. Springer, Berlin Heidelberg New York
Morasso P, (1990) Connectionist methods for the analysis of cursive handwriting. In: Kindermann J, Linden A (eds) Distributed adaptive neural information processing. Oldenbourg, Munich/Vienna pp 103–120
Morasso P, Mussa Ivaldi FA (1982) Trajectory formation and handwriting: a computational model. Biological Cybernetics 45:131–142
Morasso P, Sanguineti V, Pareto A (1992) SOC — a self-organizing classifier. In: Aleksander I Taylor J (eds) Artificial neural networks. North-Holland, Amsterdam, pp 1123–26
Morasso P, Pareto A Sanguineti V (1993a) Incremental category formation. Proceedings World Congress of Neural Networks WCNN'93 Portland L. Erlbaum Associates, Hillsdale, N.J., 3:71–74
Morasso P, Barberis L, Pagliano S, Vergano D (1993b) Recognition experiments of cursive dynamic handwriting with self-organizing networks. Patt Recogn 26:451–460
Morasso P, Gismondi L., Musante E, Pareto A (1993c) SCRIPTOR: an on-line recognition engine of cursive handwriting with incremental learning capabilities. Preproceedings International Workshop on Frontiers in Handwriting 3, Buffalo, NY, pp 431–436
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Morasso, P.G., Limoncelli, M. & Morchio, M. Incremental learning experiments with SCRIPTOR: an engine for on-line recognition of cursive handwriting. Machine Vis. Apps. 8, 206–214 (1995). https://doi.org/10.1007/BF01219588
Issue Date:
DOI: https://doi.org/10.1007/BF01219588