Abstract
In this paper, the problem of handwritten digits recognition is addressed using swarm based optimization methods. These latter have been shown to be useful for a wide range of applications such as functional optimization. The proposed work places specific swarm based optimization methods that are the particle swarm optimizer and variations of the bees’ colony optimization in handwritten Arabic numerals recognition so that to improve the generalization ability of a recognition system through the use of two alternatives. In the first one, swarm based methods have been used as statistical classifiers whereas in the second one a combination of the famous gradient descent back-propagation learning method and the bees algorithm has been proposed to allow better accuracy and speediness. Comparative study on a variety of handwritten digits has shown that high recognition rates (99.82%) have been obtained.
This is a preview of subscription content, log in via an institution to check access.
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
Arnaud, A.L., Adeodato, P.J.L., Vasconcelos, C.G.: MLP Neural Networks Optimization through Simulated Annealing in a Hybrid Approach for Time Series Prediction. In: SBC ENIA 2005 - V Encontro Nacional de Inteligência Artificial, pp. 1110–1113 (2005)
Branke, J.: Evolutionary algorithms for neural network design and training. Technical Report No. 322, University Karlsruhe, Institute AIFB (1995)
Bloomberg, D., et al.: Extraction of Text-Related Features for Condensing Image Documents. In: SPIE, vol. 2660, pp. 72–88 (1996)
Vesely, A.: Neural networks in data mining. AGRIC. ECON. – CZECH 49(9), 427–431 (2003)
Harnett, J.: Developments in OCR for automatic data entry. In: Picken, C. (ed.) Proceedings of a conference on Translating and the Computer, November 14-15, 1985, vol. 7, pp. 109–117. CBI Conference Centre, London (1986)
Karaboga, D.: An Idea Based On Honey Bee Swarm for Numerical Optimization. Techn. Rep. TR06, Erciyes Univ. Press, Erciyes (2005)
Rojas, R.: A Graph Labelling Proof of the Backpropagation Algorithm. ACM Commun. 39(12es), 207–215 (1996)
Karaboga, D., Akay, B.: Artificial Bee Colony (ABC), Harmony Search and Bees Algo-rithms on Numerical Optimization. In: IPROMS 2009, Innovative Production Machines and Systems Virtual Conference, Cardiff, UK (2009)
Gorgel, P., Oztas, O.: Handwritten Character Recognition System Using Artifıcial Neural Networks. Istanbul University – Journal of Electrical & Electronics Engineering 7(1), 309–313 (2007)
Makhoul, J., Starner, T., Schwartz, R.M., Chou, G.: On-Line Cursive Handwriting Recogni-tion Using Hidden Markov Models and Statistical Grammars. In: Proceedings of Human Language Technology Conference HLT 1994, pp. 432–436 (1994)
Park, J.: Hierarchical Character Recognition and its uses in handwritten word/phrase recognition, PHD thesis (1999)
Pham, D.T., Ghanbarzadeh, A., Koc, E., Otri, S., Rahim, S., Zaidi, M.: The Bees Algorithm. Technical Note, Manufacturing Engineering Centre, Cardiff University, UK (2005)
Pham, D.T., Ghanbarzadeh, A., Koç, E., Otri, S., Rahim, S., Zaidi, M.: The Bees Algorithm – A Novel Tool for Complex Optimisation Problems. In: Proceedings of IPROMS 2006 Conference, pp. 454–461 (2006)
Su, T., Jhang, J., Hou, C.: A hybrid artificial neural networks and particle swarm optimization for function approximation. International Journal of Innovative Computing, Information and Control 4(9), 2363–2374 (2008)
Tan, C.L., Chia, H.W.K.: Neural Logic Network Learning using Genetic Programming. In: Proc. 17th Int’l Joint Conf. Artificial Intelligence (IJCAI ’01), vol. 2, pp. 803–808 (2001)
Wu, P., Shieh, C.S., Kao, J.H.: The Development of Neural Network Models by Revised Particle Swarm Optimization. In: JCIS 2006, pp. 1951–6851 (2006), http://cui.unige.ch/AI-group/teaching/dmc/07-08/cours/dm06-mlp-handouts.pdf
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Nebti, S., Boukerram, A. (2010). Handwritten Digits Recognition Based on Swarm Optimization Methods. In: Zavoral, F., Yaghob, J., Pichappan, P., El-Qawasmeh, E. (eds) Networked Digital Technologies. NDT 2010. Communications in Computer and Information Science, vol 87. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-14292-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-642-14292-5_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-14291-8
Online ISBN: 978-3-642-14292-5
eBook Packages: Computer ScienceComputer Science (R0)