Abstract
The objective of this work is the application of the spatio-temporal multilayer perceptron (ST-MLP) developed in our laboratory to the recognition of on-line handwritten characters. The ST-MLP integrates a spatio-temporal data coding defined in the complex domain. Starting from the stroke of a character produced by a digitizing tablet, we conduct the recognition process in two steps. This procedure which is classic in this domain, consist of a preprocessing step and a recognition one. The first step (segmentation step), identifies some elementary (basic) lines, called primitives, from the stroke of the character. Then we utilise the ST-MLP to recognize the traced character from the primitives provided.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Nasser Mozayyani, Veronique Alanou, Jean-François Dreyfus, and Gilles Vaucher. A spatio-temporal data-coding applied to kohonen maps. In International Conference on Artificial Neural Networks, volume 2, pages 75–79. EC2 et Compagnie, Oct. 1995.
Jean-Cédric Chappelier and Alain Grumbach. Time in neural networks. SIGART Bulletin, 5(3):3–11, Jul 1994.
Etienne Roche and Gilles Vaucher. Perceptron Multi-Couches Étendu aux Corps des Complexes. Valgo, ISSN 1243-4825, 94-2:23-37, dec 1994.
Gilles Vaucher. Contribution ä l'enrichissement du modele formel d'un neurone. Technical Report B-SI-GV-TH-A 1.1, Supelec, Cesson-Sévigné (35) France, juillet 1992.
Gilles Vaucher. Un modele de neurone artificiel conçu pour l'apprentissage nonsupervise de sequences d'événements asynchrones. Valgo, ISSN 1243-4825, 931:66-107, mai 1993.
Gilles Vaucher. A la recherche d'une algèbre neuronale spatio-temporal. PhD thesis, Université de Rennes I, dec 1996. Supelec.
Gordon R. Little, Steven C. Gustafson, and Robert A. Senn. Generalization of the backpropagation neural network learning algorithm to permit complex weights. Applied Optics, 29(11):1591–2, April 1990.
Timothy Masters. Signal and image processing with neural networks. John Wiley & Sons, Inc., 1994.
S. Bercu, B. Delyon, and G. Lorette. Segmentation pour une methode de reconnaissance d'écriture cursive “en-ligne”. In GRIN-CNRS GRCE Afcet, editor, Actes du Colloque CNED'92, Traitement de l'ecriture et des documents, pages 144–151, Juillet 1992.
Jacqueline Castaing, Pierre Brézellec, and Henry Soldano. Une methode symbolique pour la reconnaissance de I'écriture manuelle en ligne. In AFIA AFCET, editor, 10e congrès RFIA, Reconnaissance des Formes et Intelligence Artificielle, pages 580–587, Jan 1996.
A. Belaïd and Y. Belaïd.Reconnaissance des formes: Méthodes et Application. InterEdition, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mozayyani, N., Vaucher, G. (1997). A spatio-temporal perceptron for on-line handwritten character recognition. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020175
Download citation
DOI: https://doi.org/10.1007/BFb0020175
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive