Abstract
The purpose of this study is to investigate handwritten online character recognition by Kohonen neural networks which learn class conditional Gibbs densities from training samples. The characters are represented by histograms (empirical distributions) of features. The Kohonen network learning algorithm implements a gradient ascent which maximizes an entropy criterion under constraints. Using a database of handwritten online Arabic characters produced without constraints by a large number of writers, we conducted extensive experiments which show the advantage of this Gibbsian Kohonen network over other classifiers such as a regular Kohonen neural network and a Gibbsian Bayes classifier.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Al-Sheikh, T., El-Taweel, S.: Real-time Arabic handwritten character recognition. Pattern recognition 23, 1323–1332 (1990)
Schenkel, M., Guyon, I., Henderson, D.: On-line script recognition using time delay neural networks and hidden markov models. In: International Conference on Acoustics, Speech, and Signal Processing, Adelaide, Austrailia, vol. 2, pp. 637–640 (1994)
Mezghani, N., Cheriet, M., Mitiche, A.: Combination of pruned kohonen maps for on-line Arabic characters recognition. In: Seventh International Conference on Document Analysis and Recognition, Edinburgh, Scotland, vol. 2, pp. 900–905 (2003)
Plamondon, R.: A model-based segmentation framework for computer processing of handwriting. In: Proceedings of the Eleventh IAPR International Conference on Pattern Recognition, pp. 303–307 (1992)
Kavianifar, M., Amin, A.: Preprocessing and structural feature extraction for a multi-fonts arabic/persian ocr. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition, pp. 213–216 (1999)
Klassen, T.: Towards neural network recognition of handwritten Arabic letters. Master’s thesis, Dalhousie University, Halifax (2001)
Alimi, A.: A neuro-fuzzy approch to recognize on-line Arabic handwritting. In: International Conference on Neural Networks, vol. 3, pp. 1397–1400 (1997)
Mahmoud, S.A.: Arabic character-recognition using fourier descriptors and character contour encoding. Pattern Recognition 27, 815–824 (1994)
Mezghani, N., Mitiche, A., Cheriet, M.: A new representation of character shape and its use in on-line character recognition by a self-organizing map. In: IEEE International Conference on Image Processing, ICIP, Singapore, vol. 3, pp. 2123–2126 (2004)
Zhu, S.C., Wu, Y., Mumford, D.: Minimax entropy principle and its application to texture modeling. Neural Comput. 9, 1627–1660 (1997)
Zhu, S.: Embedding gestalt laws in markov random fields. IEEE Transactions on Pattern Analysis and Machine Intelligence 21, 1170–1187 (1999)
Duda, P.O., Hart, P.E., Stork, D.G.: Pattern Classification, New York (2001)
Bail, E.L., Mitiche, A.: Quantification vectorielle d’images par le réseau neuronal de kohonen. Traitement du Signal 6, 529–539 (1989)
Anouar, F., Badran, F., Thiria, S.: Probabilistic self-organizing map and radial basis function. Journal of Neurocomputing 20, 83–96 (1998)
Mezghani, N., Mitiche, A., Cheriet, M.: Bayes classification of online arabic characters by gibbs modeling of class conditional densities. IEEE Transactions on Pattern Analysis and Machine Intelligence 30, 1121–1131 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mezghani, N., Mitiche, A. (2008). A Gibbsian Kohonen Network for Online Arabic Character Recognition. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2008. Lecture Notes in Computer Science, vol 5359. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-89646-3_48
Download citation
DOI: https://doi.org/10.1007/978-3-540-89646-3_48
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-89645-6
Online ISBN: 978-3-540-89646-3
eBook Packages: Computer ScienceComputer Science (R0)