Back Propagation Neural Network Arabic Characters Classification Module Utilizing Microsoft Word

Problem statement: Arabic character recognition has been one of the last major languages to receive attention. This may be attributed to the inherent complexity of both printed and handwritten Arabic characters. The objectives of this study were to: (i) summarize the main characteristics of Arabic language writing style. (ii) suggest a neural network recognition circuit. Approach: A Neural network with back propagation training mechanism for classification was designed and trained to recognize any set of character combinations, sizes or fonts used in Microsoft word. Results: The proposed network recognition behaviours were compared with perceptron-like net that combines perceptron with ADALINE features. These circuits were tested for three character sets combinations; 28 basic Arabic characters plus 10 numerals set, 52 Latin characters and 10 numerals only. Conclusions: The method was robust and flexible and can be easily extended to any character set. The network exhibited recognition rates approaching 100% with reasonable noise tolerance.

[1]  Karim Faez,et al.  Feature extraction with wavelet transform for recognition of isolated handwritten Farsi/Arabic characters and numerals , 2002, 2002 14th International Conference on Digital Signal Processing Proceedings. DSP 2002 (Cat. No.02TH8628).

[2]  Ching Y. Suen,et al.  Recognition of English and Arabic numerals using a dynamic number of hidden neurons , 1999, Proceedings of the Fifth International Conference on Document Analysis and Recognition. ICDAR '99 (Cat. No.PR00318).

[3]  Pervez Ahmed,et al.  Arabic Character Recognition: Progress and Challenges , 2000, J. King Saud Univ. Comput. Inf. Sci..

[4]  Xiaoli Yang,et al.  A comparative study of Fourier descriptors and Hu's seven moment invariants for image recognition , 2004, Canadian Conference on Electrical and Computer Engineering 2004 (IEEE Cat. No.04CH37513).

[5]  Simon M. Lucas,et al.  A Comparison of Syntactic and Statistical Techniques for Off-Line OCR , 1994, ICGI.

[6]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Ahmad M. Sarhan,et al.  Arabic Character Recognition using ANN Networks and Statistical Analysis , 2007 .

[8]  Mohammad S. Khorsheed,et al.  Off-Line Arabic Character Recognition – A Review , 2002, Pattern Analysis & Applications.

[9]  Muhammad Sarfraz,et al.  Offline Arabic text recognition system , 2003, 2003 International Conference on Geometric Modeling and Graphics, 2003. Proceedings.

[10]  Mohammad S. Khorsheed,et al.  Automatic Processing of Handwritten Arabic Forms using Neural Networks , 2005, IEC.

[11]  W. F. Clocksin,et al.  Structural Features of Cursive Arabic Script , 1999, BMVC.

[12]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[13]  Magdy A. Bayoumi,et al.  Arabic text recognition using neural networks , 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

[14]  Michel Fanton.  Finite State Automata and Arabic Writing , 1998, SEMITIC@COLING.