This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Recognition of Arabic Characters
August 1992 (vol. 14 no. 8)
pp. 853-857

A statistical approach for the recognition of Arabic characters is introduced. As a first step, the character is segmented into primary and secondary parts (dots and zigzags). The secondary parts of the character are then isolated and identified separately, thereby reducing the number of classes from 28 to 18. The moments of the horizontal and vertical projections of the remaining primary characters are then calculated and normalized with respect to the zero-order moment. Simple measures of the shape are obtained from the normalized moments. A 9-D feature vector is obtained for each character. Classification is accomplished using quadratic discriminant functions. The approach was evaluated using isolated, handwritten, and printed characters from a database established for this purpose. The results indicate that the technique offers better classification rates in comparison with existing methods.

[1] A. Amin, "Machine recognition of handwritten Arabic words by IRAC II," inProc. 6th Int. Conf. Patt. Recogn.(Munich, Germany), Oct. 1982.
[2] A. Amin, A. Kaced, J. P. Haton, and R. Mohr, "Handwritten Arabic character recognition by IRAC system," inProc. 5th Int. Conf. Patt. Recogn.(Miami, FL), Dec. 1980, pp. 721-731.
[3] A. Amin and G. Masini, "Machine recognition of Arabic words and sentences," inProc. SPIE 26th Int. Symp. Instrument Display(San Diego, CA), Aug. 1982.
[4] A. Amin, G. Masini, and J. P. Haton, "Recognition of Arabic words and sentences," inProc. 7th Int. Conf. Patt. Recogn.(Montreal), 1984.
[5] K. Badi and M. Shimura, "Machine recognition of Arabic cursive scripts," inPattern Recognition in Practice. Amsterdam: North Holland, 1980.
[6] 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.
[7] A. Amin and G. Masini, "Machine recognition of multifont printed Arabic texts," inProc. 8th Int. Conf. Patt. Recogn.(Paris, France), 1986, pp. 392-395.
[8] H. Almuallim and S. Yamaguchi, "A method of recognition of Arabic cursive handwriting,"IEEE Trans. Patt. Anal. Machine Intell., vol. PAMI-9, no. 5, Sept. 1987.
[9] A. Nouh, A. Sultan, and R. Tolba, "On feature extraction end selection for Arabic character recognition,"Arab Gulf J. Scient. Res., vol. 2, no. 1, pp. 329-347, 1984.
[10] B. Parhami and M. Taraghi, "Automatic recognition of printed Farsi texts,"Patt. Recogn., vol. 14, nos. 1-6, pp. 395, 403, 1981.
[11] M. N. Al-Tikriti and S. K. Al-Ramchi, "Fuzzy approach for some Arabic handwritten characters computer recognition," Comput. Processing Arabic Language Workshop Papers, pp. 1-14, Apr. 14-16, 1985.
[12] T. El-Sheikh and R. Guindi, "Computer recognition of Arabic scripts,"Patt. Recogn., vol. 21, no. 4, pp. 293-302, 1988.
[13] M. El-Wakil and A. Shoukry, "On line recognition of handwritten isolated Arabic characters,"Patt. Recogn., vol. 22, no. 2, pp. 97-105, 1989.
[14] G. A. Kubba, "The impact of computers on Arabic writing, character processing and teaching," inProc. I.F.I.P. Cong., Oct. 1980.
[15] A. M. Seflan, "The need for a standard Arabic character set," inProc. Second Comput. Conf.(Riyadh, Saudi Arabia), 1975.
[16] A. Dewachi, "Standardization of Arabic alphabet and numbers," Rep. Iraqi Nat. Comput. Center, Jan. 1975.
[17] M. K. Hu, "Visual pattern recognition by moment invariants,"IRE Trans. Inform. Theory, pp. 179-187, 1962.
[18] P. R. Madhvapathy, "Pattern recognition using simple measures of projections," M.S. thesis, Colorado State Univ., Fort Collins, 1986.
[19] H. Al-Yousefi and S. S. Udpa, "Recognition of handwritten Arabic characters," inProc. SPIE 32nd Ann. Int. Tech. Symp. Opt. Optoelectric Applied Sci. Eng.(San Diego, CA), Aug. 1988.
[20] D. J. Hand,Discrimination and Classification. New York: Wiley, 1981.

Index Terms:
Arabic character recognition; segmentation; horizontal projection; vertical projections; zero-order moment; 9-D feature vector; quadratic discriminant functions; classification rates; character recognition; statistical analysis
Citation:
H. Al-Yousefi, S.S. Upda, "Recognition of Arabic Characters," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 8, pp. 853-857, Aug. 1992, doi:10.1109/34.149585
Usage of this product signifies your acceptance of the Terms of Use.