Abstract

Optical Character Recognition (OCR) is an area of research that has attracted the interest of researchers for the past forty years. Although the subject has been the center topic for many researchers for years, it remains one of the most challenging and exciting areas in pattern recognition. Because of the cursive nature of Persian language, recognition of its characters is more difficult than Latin or Chinese language. In this paper we propose a novel method to recognize the isolated characters of Persian language using decision tree based on structural features of characters. The system has been tested on a database including all letters of Persian language and a recognition rate of 90. 56% has been achieved. Our experimental recognition results are encouraging and confirm our expectation that the use of structural features is an interesting issue of Persian character recognition.

References

• J. Mantas, "An Overview of Character Recognition Methodologies", Pattern Recognition 19, 1986, pp. 425-430.
• R. M. Bozinovic and S. N. Shihari, "Off Line Cursive Script Word Recognition", IEEE Trans. Pattern Anal. Mach. Intell. PAMI 11, 1989, pp. 68-83.
• R. Casey and G. Nagy, "Automatic Reading Machine", IEE Trans. Comput. 17, 1968, pp. 492-503.
• Amin, A. : Off-line Arabic character recognition: the state of the art. Pattern Recognition. 1998, 31(5), 517–530
• Gouda, A. M. , Rashwan, M. A. : Segmentation of connected Arabic characters using hidden Markov models. IEEE International Conference on Computational Intelligence for Measurement Systems and Applications, USA 2004, pp. 115–119
• Kurdy, B. , AlSabbagh, M. : Omnifont Arabic optical character recognition system. In: Proceedings of International Conference on Information and Communication Technologies: From Theory to Applications, pp. 2004, 469–470
• Khosravi, H. , Kabir, E. : Introducing a very large dataset of handwritten Farsi digits and a study on their varieties. Pattern Recognit. Lett. 2007, 28(10), 1133–1141
• Mansoory, S. , Hassibi, H. , Rajabi, F. : A heuristic Persian handwritten digit recognition with neural network. In: The 6th Iranian Conference on Electrical Engineering, 1998, pp. 131–135
• Soltanzadeh, H. , Rahmati, M. : Recognition of Persian handwritten digits using image profiles of multiple orientations. Pattern Recognit. Lett. 2004, 25(14), 1569–1576
• Mozaffari, S. and H. Soltanizadeh, 2009. ICDAR 2009. handwritten Farsi/Arabic character recognition competition. Proceedings of the 10th International Conference on Document Analysis and Recognition, July 26-29, IEEE Xplore, Barcelona, 2009, pp: 1413-1417. DOI: 10. 1109/ICDAR. 283
• M. Alipour, "A New Approach to Segmentation of Persian Cursive Script based on Adjustment the Fragments," International Journal of Computer Applications 2013, Vol. 64, No 11, pp. 21–26.
• Azmi, R. , Kabir, E. : A new segmentation technique for omnifont Farsi text. Pattern Recognit. Lett. 2001, 22, 97–104
• Ebrahimi, A. , Kabir, E. : A pictorial dictionary for printed Farsi subwords. Pattern Recognit. Lett. 2008, 29(5), 656–663
• Mehran, R. , Pirsiavash, H. , Razzaziy, F. : A front-end OCR for omni-font Persian/Arabic cursive printed documents. Digital Imaging Computing: Techniques and Applications, 2005, pp. 385–392
• Parhami, B. , Taraghi, M. : Automatic recognition of printed Farsi texts. Pattern Recognit. Lett. 1981, 14, 395–403
• N. Otsu, A threshold selection method from Gray-level histogram, IEEE Trans. Systems Man Cybernet. 9 (1) 1979, 62-66.
• W. H. Tsai, Moment-preserving thresholding: a new approach, Comput. Vision Graphics Image Process. 29, 1985, 377-393.
• C. Gonzales. Rafael and E. Richard,Woods. , Digital Image Processing. 2nd ed. Englewood Cliffs, NJ: Prentice-Hall, 2002.
• A. Amin, W. H. Wilson, Hand-printed character recognition system using artificial neural network, Proceeding of second International Conference on Document Analysis and Recognition, 1993, pp. 943-946.
• B. K. Jang and R. T. Chin, "Analysis of thinning algorithms using mathematical morphology,"IEEE Trans. Patt. Anal. Machine Intell. , 1990, vol. PAMI-12, no. 6, pp. 541-551.
• B. Timsari, Character recognition in typed Persian words: a morphological approach, M. S. thesis, Isfahan Univ. of Tech. 1992, Iran.
• R. Safabakhsh, and P. Adibi. Nastaaligh Handwritten Word Recognition Using a Continuous-Density Variable-Duration HMM. The Arabian Journal for Science and Engineering. 2005, 30: 95-118. April.
• H. Goraine, M. Usher, and S. Al-Emami. Off-Line Arabic Character Recognition,? Computer, 1992, vol. 25, pp. 71-74.
• B. AL -Badr and S. Mahmoud. Survey and bibliography of Arabic optical text recognition. Signal Processing, 1995, 41(1): 49-77.
• F. Zaki, S. Elkonyaly, A. Elfattah, and Y. Enab. A new technique for arabic handwriting recognition. Proceedings of the 11th International Conference for Statistics and Computer Science, Cairo, Egypt, 1986, pp; 171–180.
• A. Rosenfeld and A. Kak, Digital Picture Processing, Academic Press, New York, 1976.
• R. El-Hajj , L. Likforman-Sulem, C. Mokbel, "Arabic Handwriting Recognition Using Baseline Dependant Features and Hidden Markov Modeling", Proceedings of the 8th International Conference on Document Analysis and Recognition (ICDAR'05), Seoul, Korea, 2005
• Surhone, L. M. , M. T. Tennoe and S. F. Henssonow. Randomized Hough Transform. 1st Edn. , VDM Verlag Dr. Mueller AG and Co. Kg, Germany, ISBN-10: 6134695823, 2010, pp: 92.
• A. Dehghani, F . Shabani and P. Nava. Off-Line Recognition of Isolated Persian Handwritten Characters Using Multiple HiddenMarkov Models, Proc. Int'l Conf. Information Technology: Coding and Computing, 2001, pp. 506-510.