Abstract
This paper introduces a novel design for handwritten letter recognition by employing a hybrid back-propagation neural network with an enhanced evolutionary algorithm. Feeding the neural network consists of a new approach which is invariant to translation, rotation, and scaling of input letters. Evolutionary algorithm is used for the global search of the search space and the back-propagation algorithm is used for the local search. The results have been computed by implementing this approach for recognizing 26 English capital letters in the handwritings of different people. The computational results show that the neural network reaches very satisfying results with relatively scarce input data and a promising performance improvement in convergence of the hybrid evolutionary back-propagation algorithms is exhibited.
The original version of this chapter was revised: The copyright line was incorrect. This has been corrected. The Erratum to this chapter is available at DOI: 10.1007/978-3-642-02312-5_25
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
Mahmoudi, F., Parviz, M.: Visual Hand Tracking Algorithms. In: IEEE Proc. Geometric Modeling and Imaging–New Trends, pp. 228–232 (July 2006)
Meinagh, M.A., Isazadeh, A., Ayar, M., Mahmoudi, F., Zareie, B.: Database Replication with Availability and Consistency Guarantees through Failure-Handling. In: IEEE Proc. International Multi-Conference on Computing in the Global Information Technology (ICCGI 2007), p. 14 (2007)
Mangal, M., Singh, M.P.: Handwritten English Vowels Recognition Using Hybrid Evolutionary Feed-Forward Neural Network. Malaysian Journal of Computer Science 19(2), 169–187 (2006)
Mangal, M., Singh, M.P.: Patterns Recalling Analysis of Hopfield Neural Network with Genetic Algorithms. International Journal of Innovative Computing, Information and Control (JAPAN) (2007) (accepted for publication)
Mahmoudi, F., Shanbehzadeh, J., Eftekhari, A., Soltanian-Zadeh, H.: Image retrieval based on shape similarity by edge orientation autocorrelogram. Journal of Pattern Recognition 36(8), 1725–1736 (2003)
Gao, W.: New Evolutionary Neural Networks. In: Proc. of International Conference on Neural Interface and Control, May 26-28 (2005)
Goldberg, D.: Genetic Algorithms. Addison-Wesley, Reading (1989)
Pal, S.K., Wang, P.P.: Genetic Algorithm for Pattern Recognition. CRC Press, Boca Raton (1996)
Gelsema, E.S.: Editorial Special Issue On Genetic Algorithms. Pattern Recognition Letters 16(8) (1995)
Auwatanamongkol, S.: Pattern recognition using genetic algorithm. In: IEEE Proc. of the 2000 Congress on Evolutionary Computation (2000)
Murthy, B.V.S.: Handwriting Recognition Using Supervised Neural Networks. In: Joint Conference on Neural network vol. 4 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 ICST Institute for Computer Science, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Mahmoudi, F., Mirzashaeri, M., Shahamatnia, E., Faridnia, S. (2009). A Novel Handwritten Letter Recognizer Using Enhanced Evolutionary Neural Network. In: Sorell, M. (eds) Forensics in Telecommunications, Information and Multimedia. e-Forensics 2009. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 8. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-02312-5_1
Download citation
DOI: https://doi.org/10.1007/978-3-642-02312-5_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-02311-8
Online ISBN: 978-3-642-02312-5
eBook Packages: Computer ScienceComputer Science (R0)