Abstract
Aiming at the complexity and limitations of traditional character recognition design method, an algorithm combined with genetic algorithms and neural network is proposed. Using this method, the advantages genetic algorithm which global optimal solution or a very good performance suboptimal solutions can easily be obtained is fully utilized. The shortcomings of neural network model such as slow convergence speed, entrapment in local optimum, unstable network structure etc. are solved. Combined neural network and genetic algorithm is to make full use of the advantages of both, so that the new algorithms both neural network learning capability and robustness, but also a strong genetic algorithms global random search capability, the neural network has self-evolutionary, adaptive capacity, so as to construct evolutionary neural network. The actual application in character recognition results show that, compared with the traditional method, this model has a strong feasibility and effectiveness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu Z, Sugisaka M (1999) A genetic algorithm approach used to generate the network structures[C]. In: Proceedings of the 1999 IEEE/RSJ international conference on intelligent robots and system, Kyongju, SouthKorea, vol 1, pp 763–768
Li M, Li S, Kou J (1999) Effective method of preventing premature of genetic algorithm [J]. Trans Tianjin Univ 5(l):31–35 (in Chinese)
Yu T, Tang YY (1999) The feature extraction of Chinese character based on contour information [J]. ICDAR vol 99. pp 637-640, Sept 1999
Cao J Ahmadi M, Shridhar M (1995) Recongnition of handwritten numerals with mu1tiple feature and multistage classifier [J]. Pattern Recognit 28(2):153–160 (in Chinese)
Fan JS, Tao Q, Fang TJ (2000) Genetic algorithm optimizes neural network based on structure risk minimization [C]. In: Proceedings of 3rd word congress on intelligent control and automation, pp 948–952, June 28–July 2
Srinvivas M, Patnail LM (1994) Adaptive probabilities of crossover and mutation in genetic algorithms [J]. IEEE Trans Syst Man Cybern 24(4):656–667
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cao, XY., Yu, HL., Zou, YY. (2013). Character Recognition Based on Genetic Algorithm and Neural Network. In: Lu, W., Cai, G., Liu, W., Xing, W. (eds) Proceedings of the 2012 International Conference on Information Technology and Software Engineering. Lecture Notes in Electrical Engineering, vol 211. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34522-7_96
Download citation
DOI: https://doi.org/10.1007/978-3-642-34522-7_96
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34521-0
Online ISBN: 978-3-642-34522-7
eBook Packages: EngineeringEngineering (R0)