Automatic recognition of printed arabic text using neural network classifier
The main theme of this paper is the automatic recognition of Arabic printed text using an artificial neural networks in addition to conventional techniques. This approach has a number of advantages: it combines rule-based (structural) and classification tests; and feature extraction is inexpensive and execution time is independent of character font and size. The technique can be divided into three major steps: The first step is pre-processing in which the original image is transformed into a binary image utilizing a 300 dpi scanner and then forming the connected component. Second, global features of the input Arabic word are then extracted such as number subwords, number of peaks within the subword, number and position of the complementary character, etc.. Finally, an artificial neural networks is used for character classification. The algorithm was implemented on a powerful MS-DOS based microcomputer and written in C.
Unable to display preview. Download preview PDF.
- 1.A. Amin, A. Kaced, J. P. Haton and R. Mohr, Handwritten Arabic characters recognition by the IRAC system, 5th Int. Conf. on Pattern Recognition, Miami, USA, 1980, 729–731.Google Scholar
- 2.A. Amin, Machine recognition of handwritten Arabic word by the IRAC II system, 6th Int. _Conf. on Pattern Recognition, Munich, 1982, 34–36.Google Scholar
- 3.A. Amin, IRAC: Recognition and understanding systems, Applied Arabic Linguistic and Signal and Information Processing, ed. R. Descout, Hemisphere, New York, 1987, 159–170.Google Scholar
- 7.A. Amin and G. Masini, Machine recognition of muti-fonts printed Arabic texts, 8th Int. Conf. on Pattern Recognition, Paris, 1986, 392–395.Google Scholar
- 9.A. Amin and S. Al-Fedaghi, Machine recognition of printed Arabic text utilising a natural language morphology, Int. J. of Man-Machine Studies 35, 6 (1991) 769–788.Google Scholar
- 10.H. Almuallim and S. Yamaguchi, A method of recognition of Arabic cursive handwriting, IEEE, Trans. Pattern Anal. and Machine Intell. PAMI-9 (1987) 715–722.Google Scholar
- 15.A. Amin, Arabic Character Recognition. Handbook of Character Recognition and Document Image Analysis edited by H Bunke and P S P Wang, 1996.Google Scholar
- 16.N. Otsu, A threshold selection method from gray level histogram, IEEE Trans. Syst. Man Cybernet. SMC-9 (1) (1979), 62–66.Google Scholar
- 17.J. S. Weszka and A. Rosenfeld, Histogram modification from threshold selection, IEEE Trans. Syst. Man Cybernet. SMC-9 (1) (1979), 38–52.Google Scholar
- 19.R. Schwartz, C. LaPre, J. Makhoul, C. Raphael, and Y. Zhao, Language independent OCR using a continuous speech recognition system, International Conf. On Pattern Recognition, 99–103, (1996).Google Scholar
- 20.D. E. Rumelhart, G. E. Hinton and R. J. Williams, Parallel Distributed Processing, Vol. 1, Bradford Books, MIT Press, Massachussetts (1986).Google Scholar