Share This Article:

A Comparison of Neural Classifiers for Graffiti Recognition

Abstract Full-Text HTML Download Download as PDF (Size:1856KB) PP. 94-112
DOI: 10.4236/jilsa.2014.62008    6,254 Downloads   7,369 Views   Citations

ABSTRACT

Technological advances and the enormous flood of papers have motivated many researchers and companies to innovate new technologies. In particular, handwriting recognition is a very useful technology to support applications like electronic books (eBooks), post code readers (that sort mails in post offices), and some bank applications. This paper proposes three systems to discriminate handwritten graffiti digits (0 to 9) and some commands with different architectures and abilities. It introduces three classifiers, namely single neural network (SNN) classifier, parallel neural networks (PNN) classifier and tree-structured neural network (TSNN) classifier. The three classifiers have been designed through adopting feed forward neural networks. In order to optimize the network parameters (connection weights), the back-propagation algorithm has been used. Several architectures are applied and examined to present a comparative study about these three systems from different perspectives. The research focuses on examining their accuracy, flexibility and scalability. The paper presents an analytical study about the impacts of three factors on the accuracy of the systems and behavior of the neural networks in terms of the number of the hidden neurons, the model of the activation functions and the learning rate. Therefore, future directions have been considered significantly in this paper through designing particularly flexible systems that allow adding many more classes in the future without retraining the current neural networks.

Conflicts of Interest

The authors declare no conflicts of interest.

Cite this paper

Al-Fatlawi, A. , Ling, S. and Lam, H. (2014) A Comparison of Neural Classifiers for Graffiti Recognition. Journal of Intelligent Learning Systems and Applications, 6, 94-112. doi: 10.4236/jilsa.2014.62008.

References

[1] Srihari, S.N. and Lam, S.W. (1995) Character Recognition.
[2] Jin, L.W., Chan, K. and Xu, B.Z. (1995) Off-Line Chinese Handwriting Recognition Using Multi-Stage Neural Network Architecture. IEEE International Conference on Neural Networks, Perth, 27 November 1995-1 December 1995, 3083-3088.
[3] Gu, L.X., Tanaka, N.K., Kaneko, T. and Haralick, R.M. (1999) The Extraction of Characters from Cover Images Using Mathematical Morphology. Systems and Computers in Japan, 29, 33-42.
[4] Suen, C.Y., Nadal, C., Legault, R., Mai, T.A. and Lam, L. (1992) Computer Recognition of Unconstrained Handwritten Numerals. The Proceedings of the IEEE, 80, 1162-1180.
[5] Zhang, P. (2006) Reliable Recognition of Handwritten Digits Using a Cascade Ensemble Classifier System and Hybrid Features. Doctor of Philosophy, The Department of Computer Science and Software Engineering, Concordia University, Montreal, Quebec.
[6] Kanungo, T. and Haralick, R.M. (1990) Character Recognition Using Mathematical Morphology. Proceeding of the United States Postal Service Advanced Technology Conference, Washington DC, November 1990, 973-986.
[7] Gu, L.X., Tanaka, N. and Kaneko, T. (1996) The Extraction of Characters from Scene Image Using Mathematical Morphology IAPR Workshop on Machine Vision Applications. Tokyo.
[8] Badr, A.-B. and Haralick, R.M. (1994) Symbol Recognition without Prior Segmentation. 303-314.
[9] Kumar, V.V., Srikrishna, A., Babu, B.R. and Mani, M.R. (2010) Classification and Recognition of Handwritten Digits by Using Mathematical Morphology. Indian Academy of Sciences, 35, 419-426.
[10] Li, X. and Yeung, D.Y. (1997) On-Line Handwritten Alphanumerics Character Recognition Using Domimnal Points h Stmkes. Rttem Recognition, 30, 3144.
[11] Casey, R. (1970) Moment Nomurliwtion of Handprinted Charoclers. IBM Joumd of Research Development, 10, 548557.
[12] Ling, S.H., Lam, H.K. and Leung, F.H.F. (2007) Input-Dependent Neural Network Trained by Improved Genetic Algorithm and Its Application. Soft Computing, 11, 1033-1052.
http://dx.doi.org/10.1007/s00500-007-0151-5
[13] Ling, S.H. (2010) A New Neural Network Structure: Node-to-Node-Link Neural Network. Journal of Intelligence Learning Systems and Application, 2, 1-11.
http://dx.doi.org/10.4236/jilsa.2010.21001
[14] Tayfur, G. (2012) Soft Computing in Water Resources Engineering: Artificial Neural Networks, Fuzzy Logic and Genetic Algorithms. WIT Press.
[15] Tebelskis, J. (1995) Speech Recognition Using Neural Networks. PhD Thesis, Carnegie Mellon, Pittsburgh.
[16] Yam, J.Y.F. and Chow, T. (2000) A Weight Initialization Method for Improving Training Speed in Feed forward Neural Network. Elsevier Science, 30, 219-232.
[17] Cybenko, G. (1989) Approximation by Superpositions of a Sigmoidal Function. Mathematics of Control, Signals and Systems, 2, 303-314.
http://dx.doi.org/10.s1007/BF02551274
[18] Zurada, J.M. (1992) Introduction to Artificial Neural Systems. West Publishing Company, St. Paul.

  
comments powered by Disqus

Copyright © 2019 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.