Abstract
An architecture based on neural modules of the Adaptive Resonance Theory (ART) is proposed, for recognizing handwritten symbols employed in an on-line mathematical editor. The dynamic information generated during the handwriting process is used by the system, thus defining a run-on time discrete symbol as a sequence of strokes. An ART2 module is used to classify each individual stroke, while a Recurrent Competitive Field (RCF) is employed in order to classify the sequence of the strokes. ARTMAP modules are also proposed for the association of the different versions of strokes and symbols. Preliminary results of the application are very encouraging.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
6 References
Carpenter, C.A., and Grossberg, S., ”ART2: Self-organization of stable category organization codes for analog input patterns”, Applied Optics, 26, pp. 4919–4930
Carpenter, C.A., and Grossberg, S., “The ART of adaptive pattern recognition by a self-organizing neural network”, IEEE Computer, Special issue on artificial neural systems, Vol. 21, pp. 77–88, March 1988
Carpenter, C.A., Grossberg, S., and Reynolds J.H. ”ARTMAP real-time learning and classification of nonstationary data by a self-organizing neural network”, IEEE Expert, 1991
Dimitriadis Y.A., “Design and implementation of a mathematical editor, that uses on-line handwritten symbol recognition” Ph.D. thesis, University of Valladolid, to be defended, 1991
Dimitriadis Y.A., Lopez-Coronado J. ”A new mathematical editor, using an on-line symbol recognition”, 4th International Conference on Human-Computer Interaction, Sep. 1–6, 1991, Stuttgart, F.R. Germany, accepted for publication.
Dimitriadis Y.A., Lopez-Coronado J., De la Maza C. ”A new interactive mathematical editor, using on-line handwritten symbol recognition, and error detection-correction with an attribute grammar”, 1st International Conference on Document Analysis and Recognition, Sep. 30–Oct. 2, 1991, Saint-Malo, France, accepted for publication.
Grossberg S., ”How does a brain build a cognitive code?”, First published in Psychological Review 87(1980), pp. 1–51.
Grossberg S., ”Studies of Mind and Brain, Neural principles of learning, perception, development, cognition and motor control”, D. Reidel Pub. Company, Netherlands, 1982, Chapters 8,12 for RCF and Chapter 1 for ART
Quint, V., ”Une approche de l' edition structuree de documents“, Ph.D. thesis, University of Grenoble, May 1987
Le Cun Y, et al, ”Handwritten digit recognition: Applications of neural network chips and automatic learning“, IEEE Communications magazine, pp. 41–46, Nov. 89
Suen C.Y., Berthod M., Mori S., ”Automatic recognition of handprinted characters — The state of the art“, Proceedings of the IEEE, vol. 68, pp. 469–487, Apr. 1980
Suen C.Y. ”Handwriting generation, perception, and recognition“, Acta Psychologica, vol. 54, pp. 295–312, 1983
Tappert C.C., ”Adaptive on-line handwriting recognition“, Proceedings of the 7th Int. Conf. on Pattern Recognition, 1984, pp. 1004–1007
Tappert C.C., Suen C.Y., Wakahara T., ”The state of the art in on-line handwriting recognition“, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 12, pp. 787–808, August 1990
Toussaint G.T., ”The use of context in pattern recognition“, Pattern Recognition“, vol. 10, pp. 189–204, 1978
Tsai W.H., Fu K.S., ”Attributed grammar — A tool for combining syntactic and statistical approaches to pattern recognition“, IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-10, pp. 873–885, Dec 1980
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dimitriadis, Y.A., Coronado, J.L., Vidal, J.L.C. (1991). An adaptive resonance theory architecture for the automatic recognition of on-line handwritten symbols of a mathematical editor. In: Prieto, A. (eds) Artificial Neural Networks. IWANN 1991. Lecture Notes in Computer Science, vol 540. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0035898
Download citation
DOI: https://doi.org/10.1007/BFb0035898
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54537-8
Online ISBN: 978-3-540-38460-1
eBook Packages: Springer Book Archive