Abstract
In the study of letter recognition, the recognition accuracy is impacted by fonts and styles, which is the main bottleneck that the technology is applied. In order to enhance the accuracy, a letter recognition algorithm based artificial immune, referred to as LEBAI, is presented. Inspired by nature immune system, antibody cell (B-cell) population is evolved until the B-cell population is convergent through the learning of each training antigen and the memory cells pool is updated by the optimal B-cell. Finally, recognition is accomplished by memory cells. It is tested by the well-known letter recognition data set of UCI (University of California at Irvine). Compared with HSAC (Letter Recognition Using Holland-Style Adaptive Classifiers), LEBAI showed that recognition accuracy is increased from 82.7% to 95.58%. LEBAI achieves the same recognition accuracy for the letters of different fonts and styles, or stretched and distorted randomly.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Albert, R., Jeong, H., Barabasi, A.: Attack and Error Tolerance of Complex Networks. Nature 406, 378–382 (2002)
Li, T.: Dynamic Detection for Computer Virus based on Immune System, Science In China. Series F: Information Science 51(10), 1475–1486 (2008)
Omkar, S., Khandelwal, R., Yathindra, S., et al.: Artificial Immune System For Multi-Objective Design Optimization of Composite Structures. Engineering Applications of Artificial Intelligence 21(8), 1416–1429 (2008)
Vijayalakshmi, K., Radhakrishnan, S.: Artificial Immune based Hybrid GA for QoS based Multicast Routing in Large Scale Networks (AISMR). Computer Communications 31(17), 3984–3994 (2008)
Wang, L., Singh, C.: Population-based Intelligent Search in Reliability Evaluation of Generation Systems with Wind Power Penetration. IEEE Transactions on Power Systems 23(3), 1336–1345 (2008)
Ye, F., Xu, S., **ong, Y.: Two-step Image Registration by Artificial Immune System and Chamfer Matching. Chinese Optics Letters 6(9), 651–653 (2008)
Frey, P.W., Slate, D.J.: Letter Recognition Using Holland-style Adaptive Classifiers. Machine Learning 6(2), 161–182 (1991)
Fogarty: First Nearest Neighbor Classification on Frey and Slate’s Letter Recognition Problem. Machine Learning 9(4), 387–388 (1992)
Zhu, L., Sun, G.: Character Recognition Adaptive Learning Algorithm based on SVM and Sigmoid Function. Application of Electronic Technique 32(4), 16–17 (2006)
Li, X., Yang, J.: Container’s Character Recognition Algorithm based on Neural Networks. Computer and Communications 19(z1), 89–91 (2001)
Wu, L., Mo, Y.: Character Recognition based on Independent Component Analysis. Journal of Shanghai University 9(3), 193–196 (2003)
Li, Z., Wang, S., Cai, S.: Character Recognition Approach based on Feature Line necessary-sufficient condition detection. Journal of Software 13(1), 85–91 (2002)
Frey, P.W., Slate, D.J.: UCI Repository of Machine Learning Databases, Letter Recognition Datasets (1991), http://archive.ics.uci.edu/ml/datasets/Letter+Recognition
Ahluwalia, M., Bull, L.: Coevolving Functions in Genetic Programming. Systems Architecture 47 (2001)
Daqi, G., Chao, X., et al.: Combinative Neural-network-based Classifiers for Optical Handwritten Character and Letter Recognition. International Joint Conference on Neural Networks 3, 2232–2237 (2003)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Liang, C., Peng, L., Hong, Y., Wang, J. (2009). An English Letter Recognition Algorithm Based Artificial Immune. In: Yu, W., He, H., Zhang, N. (eds) Advances in Neural Networks – ISNN 2009. ISNN 2009. Lecture Notes in Computer Science, vol 5553. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-01513-7_40
Download citation
DOI: https://doi.org/10.1007/978-3-642-01513-7_40
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-01512-0
Online ISBN: 978-3-642-01513-7
eBook Packages: Computer ScienceComputer Science (R0)