Persian Printed Numeral Characters Recognition Using Geometrical Central Moments and Fuzzy Min-Max Neural Network

Authors: Hamid Reza Boveiri

Abstract:

In this paper, a new proposed system for Persian printed numeral characters recognition with emphasis on representation and recognition stages is introduced. For the first time, in Persian optical character recognition, geometrical central moments as character image descriptor and fuzzy min-max neural network for Persian numeral character recognition has been used. Set of different experiments on binary images of regular, translated, rotated and scaled Persian numeral characters has been done and variety of results has been presented. The best result was 99.16% correct recognition demonstrating geometrical central moments and fuzzy min-max neural network are adequate for Persian printed numeral character recognition.

Keywords: Fuzzy min-max neural network, geometrical centralmoments, optical character recognition, Persian digits recognition, Persian printed numeral characters recognition.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1070689

References:

[1] A. Darvish, E. Kabir, and H. Khosravi, "Application of Shape Matching in Persian Handwritten Digits Recognition," Modares Technology and Eng., vol. 22, pp. 37-47, Dec 2005.
[2] H. Ketabdar, "Persian Handwritten Digits Recognition with Structural Approach," in Proc. 6th Iranian Conf. on Electrical Engineering, Tehran, 1998, pp. 4.19-4.24.
[3] V. Johari and M. Razavi, "Fuzzy Recognition of Persian Handwritten Digits," in Proc. 1st Iranian Conf. on Machine Vision and Image Processing, Birjand, 2001, pp. 144-151.
[4] H. Mozafari, F. Rahgozar, and Sh. Sharif, "Online Recognition of Persian Handwritten Digits," in Proc. 2nd Computer Society of Iran Annu. Conf., Tehran, 1996, pp. 196-204.
[5] N. Sadati, E. Sheikhi, and B. Nazari, "Utilizing Fuzzy Logic in Recognition of Persian Handwritten Digits," in Proc. 3rd Iranian Conf. on Electrical Engineering, Tehran, 1995, pp. 241-248.
[6] K. Faez, E. Khotanzad, and M. H. Shiralishahreza, "Recognition of Persian Handwritten Letters and Digits Using Pseudo-Zernike Moments and Neural Networks," in Proc. 3rd Iranian Conf. on Electrical Engineering, Tehran, 1995, pp. 231-240.
[7] H. Nabavi, H. Sadoughi, E. Kabir, and Karlos, "Improvement of Persian Handwritten Digits Recognition Using Composition of Classifiers with ANFIS," in Proc. 5th Iranian Conf. on Fuzzy Systems, Tehran, 2004, pp. 337-345.
[8] K. Masrori and V. Pourmohseni, "Recognition of Persian Handwritten Digits Using DWT Algorithm," in Proc. 4th Nat. Computer Society of Iran Annu. Conf., Tehran, 1998, pp. 1-7.
[9] L. C. Liu and C. Y. Suen, "A new benchmark on the recognition of handwritten Bangla and Farsi numeral characters," Pattern Recognition, to be published.
[10] A. Harifi and A. Aghagolzadeh, "A New Pattern for Handwritten Persian/Arabic digit Recognition," Proc. of World Academy of Sci., Eng. and Technology, vol. 3, pp. 130-133, Jan. 2005.
[11] S. Mozaffari, K. Faez, and M. Ziaratban, "A Hybrid Structural/Statistical Classifier for Handwritten Farsi/Arabic Numeral Recognition," in IAPR Conf. on Machine Vision Application, Tsukuba, 2005, pp. 218-221.
[12] A. Mowlaei and K. Faez, "Recognition of Isolated Handwritten Persian/Arabic Characters and Numerals Using Support Vector Machine," IEEE XIII Workshop on Neural Networks for Signal Processing, 2003, pp. 547-554.
[13] J. Sadri, C. Y. Suen, and T. D. Bui, "Application of Support Vector Machines for Recognition of Handwritten Arabic/Persian Digits," in Proc. 2nd Conf. on Machine Vision and Image Processing, Tehran, 2003, pp. 300-307.
[14] H. Khosravi and E. Kabir, "Introducing a very large dataset of handwritten Farsi digits and a study on their varieties," Pattern Recognition Lett., vol. 28, pp. 1133-1141, Dec. 2007.
[15] F. Soleimanipour, J. Sadri, and C. Y. Suen, "Standard Databases for Recognition of Handwritten Digits, Numerical Strings, Legal Amounts, Letters and Dates in Farsi Language," in Proc. 10th Int. Workshop on Frontiers of Handwritten Recognition, La baule, 2006, pp. 3-7.
[16] S. Mozaffari, K. Faez, F. Faradji, M. Ziaratban, and S. M. Golzan, "A Comprehensive Isolated Farsi/Arabic Character Database for Handwritten OCR Research," in Proc. 10th Int. Workshop on Frontiers of Handwritten Recognition, La baule, 2006, pp. 379-384.
[17] H. Ebrahimnezhad and Gh. Montazer, "Presenting Improved Fuzzy Approach for Persian Numeral Fonts Using Entropy Function," in Proc. 11th Nat. Computer Society of Iran Conf., Tehran, 2006, pp. 883-889.
[18] H. Ebrahimnezhad, Gh. A. Montazer, and N. Jafari, "Recognition of Persian Numeral Fonts by Combining the Entropy Minimized Fuzzifier and Fuzzy Grammar," in Proc. 6th PWASET Int. Conf. on Artificial Intelligence, Knowledge Engineering and Data Bases, Corfu Island, 2007, pp. 22-27.
[19] M. K. Hu, "Visual Pattern Recognition by Moment Invariant," IRE Trans. Info. Theory, vol. IT - 8, pp. 179-187, Feb 1962.
[20] M. M. Gupta, L. Jin, and N. Homma, Static and Dynamic Neural Networks: From Fundamentals to Advance theory, New Jersey: John Wiley & Sons Inc., 2003.
[21] P. K. Simpson, "Fuzzy Min-Max Neural Networks- Part1: Classification," IEEE Trans. Neural Netw., vol. 3, no. 5, pp. 776-786, Sep. 1992.
[22] P. K. Simpson, "Fuzzy Min-Max Neural Networks- Part2: Clustering," IEEE Trans. Fuzzy Syst., vol. 1, no. 1, pp. 32-45, Feb. 1993.
[23] H. R. Boveiri, "Scanned Persian Printed Text Characters Recognition Using Fuzzy-Neural Networks," M. S. thesis, Islamic Azad Univ. Science and Research Branch, Ahvaz, 2009.
[24] C. R. Gonzalez and E. R. Woods, Digital Image Processing, 2nd Ed., New Jersey: Prentice-Hall Inc., 2002.
[25] A. Khotanzad and J-H. Lu, "Classification of Invariant Image Representations using a Neural Networks," IEEE Trans. on Acoust., Speech and Signal Process., vol. 38, no. 6, pp. 1028-1038, Jun. 1990.