Arabic Character Recognition using Artificial Neural Networks and Statistical Analysis

Authors: Ahmad M. Sarhan, Omar I. Al Helalat

Abstract:

In this paper, an Arabic letter recognition system based on Artificial Neural Networks (ANNs) and statistical analysis for feature extraction is presented. The ANN is trained using the Least Mean Squares (LMS) algorithm. In the proposed system, each typed Arabic letter is represented by a matrix of binary numbers that are used as input to a simple feature extraction system whose output, in addition to the input matrix, are fed to an ANN. Simulation results are provided and show that the proposed system always produces a lower Mean Squared Error (MSE) and higher success rates than the current ANN solutions.

Keywords: ANN, Backpropagation, Gaussian, LMS, MSE, Neuron, standard deviation, Widrow-Hoff rule.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1082839

References:

[1] Amin and G. Masini, "Machine recognition of multifont printed Arabic texts", in Proc.8th Int. Conf. Patt. Recogn. (Paris, France), pp. 392-395, 1986.
[2] A.M. Sarhan and R. C. Hardie, "Partition-based filters", In Proceedings of the 1995 IEEE National Aerospace and Electronic Conference (NAECON), volume 2, Dayton, Ohio, May 1995.
[3] A.M. Sarhan, R. C. Hardie, and K. E. Barner, "Partition-based adaptive estimation of single-response evoked potentials", In Proceedings of the 1995 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 1995.
[4] A.M. Sarhan. Nonlinear partition-based filters for signal restoration. Ph.D. Thesis University of Dayton, July 1996.
[5] D. J. Hand. Discrimination and Classification. New York: Wiley, 1981.
[6] E. W. Brown, "Letter Recognition by Feature Point Extraction", Northeastern University internal paper, 1992.
[7] F. Hussain and J. Cowell, "Character Recognition of Arabic and Latin Scripts", Proceedings, IEEE International Conference on Information Visualization, pp. 51-56, 2000.
[8] H. Al-Yousefi and S. S. Udpa, "Recognition of handwritten Arabic characters," in Proc. SPIE 32nd Ann. Int. Tech. Symp. Opt. Optoelectric Applied Sci. Eng. (San Diego, CA), Aug. 1988.
[9] Haykin S.,Adaptive Filter Theory, Englewood Cli s.N.J: Prentice Hall(3ed), 1996.
[10] J.F Canny. "A Computational Approach to Edge Detection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI- 6, pp. 679-698, 1986.
[11] K. E. Barner, A. M. Sarhan, and R. C. Hardie. "Partition-based weighted sum filters for image restoration". IEEE Transactions on Image Processing, Vol. 8, No. 5, May 1999.
[12] K. Khatatneh ,"Probabilistic Artificial Neural Network for Recognizing the Arabic. Hand Written Characters", Journal of Computer Science 3 (12), 881-886, 2006.
[13] K. Badi and M. Shimura, "Machine recognition of Arabic Cursive Script" Trans. Inst. Electron. Commun. Eng., Vol. E65, no. 2, pp. 107- 114, Feb. 1982.
[14] K. Badi and M. Shimura, "Machine recognition of Arabic cursive scripts" in Pattern Recognition in Practice. Amsterdam: North Holland, 1980.
[15] L. Hammami and D. Berkani ,"Recognition system for printed multi-font and multi-size Arabic characters", The Arabian Journal for Science and Engineering, Volume 27, Number 1B, pp:57-72, April, 2002.
[16] M. Altuwaijri, M. A. Bayoumi, "Arabic Text Recognition Using Neural Network" ISCAS 94. IEEE International Symposium on Circuits and systems, Volume 6, 30 May-2 June 1994.
[17] N. Ben Amor, N. Essoukri Ben Amara: "A hybrid approach for Multifont Arabic Characters Recognition", 5th WSEAS Int. Conf. On Artificial Intelligence, Knowledge Engineering and Data Bases (AIKED'06) Madrid, Spain, February 15-17, 2006.
[18] R. A. Dosari, R. C. Hardie, and A. M. Sarhan. "Multi-channel nonlinear filters for signal restoration". In Proceedings of the 1997 IEEE National Aerospace and Electronic Conference (NAECON), Dayton, Ohio, May 1997.