Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

(453.06KB)
This is an Open Access publication published under CSC-OpenAccess Policy.
Publications from CSC-OpenAccess Library are being accessed from over 74 countries worldwide.
Two Methods for Recognition of Hand Written Farsi Characters
Mohammad Reza Jenabzadeh, Reza Azmi, Boshra Pishgoo, Samanesadat Shirazi
Pages - 512 - 520     |    Revised - 01-09-2011     |    Published - 05-10-2011
Volume - 5   Issue - 4    |    Publication Date - September / October 2011  Table of Contents
MORE INFORMATION
KEYWORDS
Optical Character Recognition, Hand Written Farsi Characters, Neural Networks, Wavelet Transform, Decision Tree
ABSTRACT
Optical character recognition (OCR) is one of the active bases of sample detection topics. The current study focuses on automatic detection and recognition of hand written Farsi characters. For this purpose; we proposed two different methods based on neural networks and a special post processing approach to improve recognition rate of Farsi uppercase letters. In the first method, we extracted wavelet features from borders of character images and learned a neural network based these patterns. In the second method, we divided input characters into five groups according to the number of their components and used a set of appropriate moment features in each group and classified characters by the Bayesian rule. In a post-processing stage, some structural and statistical features were employed by a decision tree classifier to reduce the misrecognition rate. Our experimental results show suitable recognition rate for both methods.
CITED BY (5)  
1 Shayegan, M. A. (2015). Dataset size and dimensionality reduction approaches for handwritten farsi digits and characters recognition (Doctoral dissertation, University of Malaya).
2 Safdar, Q. T. A., & Khan, K. U. (2014, December). Online Urdu Handwritten Character Recognition: Initial Half Form Single Stroke Characters. In Frontiers of Information Technology (FIT), 2014 12th International Conference on (pp. 292-297). IEEE.
3 Kchaou, M. G., Kanoun, S., Slimane, F., & Affes, S. B. Arabic Character Recognition based on Statistical Features.
4 Shayegan, M. A., Aghabozorgi, S., & Raj, R. G. Ensemble of Decision Stumps for Handwritten Farsi/Arabic Digit Recognition.
5 Kholladi, M. M. K., Chikhi, M. S., Mostefai, M. S., Zidani, M. A., & Mazouzi, M. S. Combinaison de classifieurs pour la reconnaissance de mots arabes manuscrits.
1 Google Scholar 
2 CiteSeerX 
3 Scribd 
4 SlideShare 
5 PdfSR 
1 Elmhurst, IL,”Optical Character Recognition and the Years Ahead”, The Business Press, 1969.
2 Pas d’auteur, “Auerbach on Optical Character Recognition”, Aurbach Publishers, Inc., Princeton, 1971.
3 G. Vamvakas, B. Gatos, I. Pratikakis, N. Stamatopoulos, A. Roniotis and S.J. Perantonis, "Hybrid Off-Line OCR for Isolated Handwritten Greek Characters", The Fourth IASTED International Conference on Signal Processing, Pattern Recognition, and Applications (SPPRA 2007), pp. 197-202, Austria, Feb. 2007.
4 W.R. Xu, H.G. Zhang, J. Guo, G. Chen, ”Discrimination Between Printed and Handwritten Characters for Check OCR System”, Proceedings of the first International Conference on Machine Learning and Cybernetics, Beijing, Nov. 2002.
5 M.D. Garris, D.L. Dimmick, “Form Design for High Accuracy Optical Character Recognition”, IEEE Transactions PAMI, June 1996.
6 R. Fox, W. Hartmann, “An Abductive Approach to Hand-written Character Recognition for Multiple Domains”, 2005.
7 B,Timsary, H.Fahimi, “Recognition Letters in Persian words typed using morphology”, MS thesis, Department of Electrical Engineering, Isfahan University of Technology,1992.
8 A. Aburas, S.M.A. Rehiel, “Off-line Omni-style Handwriting Arabic Character Recognition System Based on Wavelet Compression”, ARISER, Vol. 3, No. 4, pp. 123-135, 2007.
9 M. Liana, G. Venu, “Offline Arabic Handwriting Recognition: A Survey”, Transactions On Pattern Analysis and Machine Intelligence, IEEE, Vol. 28, No. 5, pp. 712-724, 2006.
10 Badie and M. Shimura, “Machine Recognition of Arabic Cursive Script “, Pattern recognition in Practice, E.S. Gelsema and L.N.Kanal (eds.), pp.315-323, North Holland publishing Company, 1980.
11 H. Al-Muallim and S. Yamaguchi, “A Method of Arabic Cursive Hand-Writing”, IEEE trans. Patt.Annal. and Machine Intel.,PAM1-9,No 5, pp. 715-722, sep. 1987.
12 T.S.Al-Sheikh and J.G. El-taweel, “ Real Time Arabic-Handwritten Character Recognition”, Proc. Int. Conf. Image Processing and its Application, pp. 212-216, Warwick, UK. July. 1989.
13 H.Al-Yousefi and S.S.Udpa, “Recognition of Arabic Characters”, IEEE Trans. Patt. Analysis and Machine Intell. Vol. 14, No. 8, pp. 853-857, 1992.
14 K. Masruri and E. Kabir, “Recognition of Hand-Printed Farsi Characters by a Fuzzy classifier”, Proc. Second Asia Conf. Computer Vision, ACCV’95, Singapore, pp. II.607- II.610, Dec. 1995.
15 S. Mori, H. Nishida, H. Yamada, “Optical Character Recognition”, JohnWiley & Sons, NY, 1999.
16 H. Almuallim, S. Yamaguchi, “A method of recognition of Arabic cursive handwriting”, Transactions on Pattern Analysis and Machine Intelligence, IEEE, Vol. PAMI-9, No. 5, Sept. 1987.
17 T. El-Sheikh, R. Guindi, “Computer recognition of Arabic scripts”, Pattern Recognition, Vol. 21, No. 4, pp. 293-302, 1988.
18 M. El-Wakil, A. Shoukry, “On-line recognition of handwritten isolated Arabic characters”, Pattern Recognition, Vol. 22, No. 2, pp. 97-105, 1989.
19 Ben Amor N., Essoukri N., “Combining a hybrid Approach for Features Selection and Hidden Markov Models in Multifont Arabic Characters Recognition”, Conferences on Document Image Analysis for Libraries, IEEE, 2006.
20 Saeed M., Karim F, Hamidreza R., “Feature Comparison between Fractal Codes and Wavelet Transform in Handwritten Alphanumeric Recognition Using SVM Classifier”, 7th International Conference on Pattern Recognition (ICPR’04), IEEE, 2004.
21 Saeed M., Karim F., Hamidreza R, “Recognition of Isolated Handwritten Farsi/Arabic Alphanumeric Using Fractal Codes”, 7th International Conference on Pattern Recognition (ICPR’04), IEEE, pp. 104-108, 2004.
22 A. Mowlaei, K. Faez, A.T. Haghighat, ”Feature Extraction with Wavelet Transform for Recognition of Isolated Handwritten Farsi/Arabic Characters and Numerals”, IEEE, pp. 923- 926, 2002.
23 http://www.icaen.uiowa.edu/~dip/LECTURE/Segmentation2.html
24 R.Azmi,” Recognition printed Farsi texts”, PhD thesis, Faculty of Engineering, Tarbiat Modarres University,1999.
25 Moller , Neural Networks, Vol. 6, 1993, pp. 525 to 533
26 A.K. Jain, “ Fundamental of Digital Image Processing”, Ch. 9, Prentice Hall, Englewood Cliffs, N.J. 1989.
27 A.N. Mucciardi and E.E. Gose, “ A Comparison of Seven Techniques for Choosing Subsets of Pattern Recognition properties”, IEEE Trans. Computers, Vol. C-20, No. 9,pp. 1023- 1031, Sept. 1971.
28 S. Khosravi, F. Razzazi, H. Rezaei, M. R. Sadigh, "a Comprehensive Handwritten Image Corpus of Isolated Persian/Arabic Characters for OCR Development and Evaluation, Signal Processing and Its Applications, 9th International Symposium on Volume , Issue , 12-15, PP.1 – 4, 2007
Dr. Mohammad Reza Jenabzadeh
- Iran
jenabzadeh@gmail.com
Dr. Reza Azmi
- Iran
Mr. Boshra Pishgoo
- Iran
Mr. Samanesadat Shirazi
- Iran