A Hybrid Structural/Statistical Classifier for Handwritten Farsi/Arabic Numeral Recognition

In this paper a new Farsi/Arabic numeral recognition system, based on the combination of structural and statistical classifiers, is presented. The structural method cannot deal with broken characters well. A statistical classifier would be more suitable for these unconnected samples. Thanks to the combination of structural and statistical approaches, a complete description of the characters can be achieved thus providing significant improvements in classification performance. The recognition system has been tested on a database which includes 480 samples per digit (total of 6080). We used 280 samples of each digit for training and the rest (200) for test. According to experimental results,classification rate of 97.31% is achieved for numerals on the test sets.

[1]  V. K. Govindan,et al.  Character recognition - A review , 1990, Pattern Recognit..

[2]  Karim Faez,et al.  Off-line unconstrained Farsi handwritten word recognition using fuzzy vector quantization and hidden Markov word models , 2000, Proceedings 15th International Conference on Pattern Recognition. ICPR-2000.

[3]  E. Dubois,et al.  Digital picture processing , 1985, Proceedings of the IEEE.

[4]  R. J. Green,et al.  Recognition of Handwritten Cursive Arabic Characters , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  M. Dehghan,et al.  Farsi handwritten character recognition with moment invariants , 1997, Proceedings of 13th International Conference on Digital Signal Processing.

[6]  Mario Vento,et al.  Combining statistical and structural approaches for handwritten character description , 1999, Image Vis. Comput..

[7]  Pavel Pudil,et al.  Introduction to Statistical Pattern Recognition , 2006 .

[8]  Fumitaka Kimura,et al.  Handwritten word recognition using lexicon free and lexicon directed word recognition algorithms , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[9]  Fuad Rahman,et al.  Introducing New Multiple Expert Decision Combination Topologies: A Case Study using Recognition of Handwritten Characters , 1997, ICDAR.

[10]  K. Faez,et al.  Recognition of isolated handwritten Farsi/Arabic alphanumeric using fractal codes , 2004, 6th IEEE Southwest Symposium on Image Analysis and Interpretation, 2004..

[11]  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).

[12]  Saeed Mozaffari,et al.  Feature comparison between fractal codes and wavelet transform in handwritten alphanumeric recognition using SVM classifier , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[13]  Yves Lecourtier,et al.  A structural/statistical feature based vector for handwritten character recognition , 1998, Pattern Recognit. Lett..

[14]  Adam Krzyżak,et al.  Methods of combining multiple classifiers and their applications to handwriting recognition , 1992, IEEE Trans. Syst. Man Cybern..