The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.07 - July (2009 vol.31)
pp: 1165-1177
Ramy Al-Hajj Mohamad , Lebanese International University, Beirut
Laurence Likforman-Sulem , TELECOM ParisTech/TSI, Paris
Chafic Mokbel , University of Balamand, Tripoli
ABSTRACT
The problem addressed in this study is the offline recognition of handwritten Arabic city names. The names are assumed to belong to a fixed lexicon of about 1,000 entries. A state-of-the-art classical right-left hidden Markov model (HMM)-based recognizer (reference system) using the sliding window approach is developed. The feature set includes both baseline-independent and baseline-dependent features. The analysis of the errors made by the recognizer shows that the inclination, overlap, and shifted positions of diacritical marks are major sources of errors. In this paper, we propose coping with these problems. Our approach relies on the combination of three homogeneous HMM-based classifiers. All classifiers have the same topology as the reference system and differ only in the orientation of the sliding window. We compare three combination schemes of these classifiers at the decision level. Our reported results on the benchmark IFN/ENIT database of Arabic Tunisian city names give a recognition rate higher than 90 percent accuracy and demonstrate the superiority of the neural network-based combination. Our results also show that the combination of classifiers performs better than a single classifier dealing with slant-corrected images and that the approach is robust for a wide range of orientation angles.
INDEX TERMS
Arabic handwriting, word recognition, feature extraction, IFN/ENIT database, hidden Markov models, HMM, neural network, multilayer perceptron, classifier combination.
CITATION
Ramy Al-Hajj Mohamad, Laurence Likforman-Sulem, Chafic Mokbel, "Combining Slanted-Frame Classifiers for Improved HMM-Based Arabic Handwriting Recognition", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.31, no. 7, pp. 1165-1177, July 2009, doi:10.1109/TPAMI.2008.136
REFERENCES
[1] A. Abdulkader, “Two Tier Approach for Arabic Offline Handwriting Recognition,” Proc. Int'l Workshop Frontiers in Handwriting Recognition, pp. 42-47, 2006.
[2] H. Almuallim and S. Yamaguchi, “A Method of Recognition of Arabic Cursive Handwriting,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, pp. 715-722, 1987.
[3] A. Amin, “Off-Line Arabic Character Recognition: The State of the Art,” Pattern Recognition, vol. 31, no. 5, pp. 517-530, 1998.
[4] A. Amin, H. Al-Sadoun, and S. Fischer, “Hand-Printed Arabic Character Recognition System Using an Artificial Network,” Pattern Recognition, vol. 29, no. 4, pp. 663-675, 1996.
[5] N. Arica and F.T. Yarman-Vural, “Optical Character Recognition for Cursive Handwriting,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 24, no. 6, pp. 801-813, June 2002.
[6] I. Bazzi, R. Schwartz, and J. Makhoul, “An Omnifont Open Vocabulary OCR System for English and Arabic,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 6, pp. 495-504, June 1999.
[7] N. Ben Amara and F. Bouslama, “Classification of Arabic Script Using Multiple Sources of Information: State of the Art and Perspective,” Int'l J. Document Analysis and Recognition, vol. 5, pp.195-212, 2003.
[8] M. Blumenstein, C.K. Cheng, and X.Y. Liu, “New Pre-Processing Techniques for Handwritten Word Recognition,” Proc. Second IASTED Conf. Visualization, Imaging and Image Processing, pp. 480-484, 2002.
[9] M. Dehghan, K. Faez, M. Ahmadi, and M. Shridhar, “Handwritten Farsi (Arabic) Word Recognition: A Holistic Approach Using Discrete HMM,” Pattern Recognition, vol. 34, no. 5, pp. 1057-1065, 2001.
[10] R. Duin, “The Combining Classifier: To Train or Not to Train,” Proc. 16th Int'l Conf. Pattern Recognition, 2002.
[11] R. El-Hajj, L. Likforman-Sulem, and C. Mokbel, “Arabic Handwriting Recognition Using Baseline Dependent Features and Hidden Markov Modeling,” Proc. Eighth Int'l Conf. Document Analysis and Recognition, pp. 893-897, 2005.
[12] R. El-Hajj, C. Mokbel, and L. Likforman-Sulem, “Combination of HMM-Based Classifiers for the Recognition of Arabic Handwritten Words,” Proc. Ninth Int'l Conf. Document Analysis and Recognition, 2007.
[13] T.S. El-Sheikh and R.M. Guindi, “Recognition of Isolated Arabic Characters,” Signal Processing, vol. 14, pp. 177-184, 1988.
[14] T.S. El-Sheikh and R.M. Guindi, “Computer Recognition of Arabic Cursive Scripts,” Pattern Recognition, vol. 21, no. 4, pp. 293-302, 1988.
[15] M.S. El-Wakil and A. Shoukry, “On-Line Recognition of Handwritten Isolated Arabic Characters,” Pattern Recognition, vol. 22, pp. 97-105, 1989.
[16] A. El-Yacoubi, M. Gilloux, R. Sabourin, and C.Y. Suen, “An HMM-Based Approach for Off-Line Unconstrained Handwritten Word Modeling and Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 8, pp. 750-752, Aug. 1999.
[17] A. El-Yacoubi, R. Sabourin, M. Gilloux, and C. Suen, “Off-Line Handwritten Word Recognition Using Hidden Markov Models,” Knowledge-Based Intelligent Techniques in Character Recognition, L.C.Jain and B. Lazzerini, eds., pp. 191-229, CRC Press, 1999.
[18] N. Farah, M.T. Khadir, and M. Sellami, “Artificial Neural Network Fusion: Application to Arabic Words Recognition,” Proc. 13th European Symp. Artificial Neural Networks, 2005.
[19] F. Farooq, V. Govindaraju, and M. Perrone, “Pre-Processing Methods for Handwritten Arabic Documents,” Proc. Eighth Int'l Conf. Document Analysis and Recognition, pp. 267-271, 2005.
[20] T.K. Ho, J. Hull, and S.N. Srihari, “Decision Combination in Multiple Classifier Systems,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 1, pp. 66-75, Jan. 1994.
[21] Y. Huang and C. Suen, “A Method of Combining Multiple Experts for the Recognition of Unconstrained Handwritten Numerals,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 17, no. 1, pp. 90-94, Jan. 1995.
[22] J. Jin, H. Wang, X. Ding, and L. Peng, “Printed Arabic Document System,” Proc. IST/SPIE Electronic Imaging Conf., 2005.
[23] M.S. Khorsheed, “Recognizing Arabic Manuscripts Using a Single Hidden Markov Model,” Pattern Recognition Letters, vol. 24, pp.2235-2242, 2003.
[24] H.J. Kim, S.K. Kim, K.H. Kim, and J.K. Lee, “An HMM-Based Character Recognition Network Using Level Building,” Pattern Recognition, vol. 30, no. 3, pp. 491-502, 1997.
[25] F. Kimura, M. Shridhar, and Z. Chen, “Improvements of a Lexicon Directed Algorithm for Recognition of Unconstrained Handwritten Words,” Proc. Second Int'l Conf. Document Analysis and Recognition, pp. 18-22, 1993.
[26] J. Kittler, M. Hatef, R. Duin, and J. Matas, “On Combining Classifiers,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 3, pp. 239-266, Mar. 1998.
[27] D.S. Lee and S. Srihari, “A Theory of Classifier Combination: The Neural Network Approach,” Proc. Third Int'l Conf. Document Analysis and Recognition, pp. 42-45, 1995.
[28] L.M. Lorigo and V. Govindaraju, “Segmentation and Pre-Recognition of Arabic Handwriting,” Proc. Eighth Int'l Conf. Document Analysis and Recognition, pp. 605-609, 2005.
[29] L.M. Lorigo and V. Govindaraju, “Off-Line Arabic Handwriting Recognition: A Survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 28, no. 5, pp. 712-724, May 2006.
[30] V. Märgner, M. Pechwitz, and H. El-Abed, “Arabic Handwriting Word Recognition Competition,” Proc. Eighth Int'l Conf. Document Analysis and Recognition, pp. 70-74, 2005.
[31] V. Märgner, H. El-Abed, and M. Pechwitz, “Offline Handwritten Arabic Word Recognition Using HMM: A Character-Based Approach without Explicit Segmentation,” Proc. Colloque Int'l Francophone sur l'Ecrit et le Document, 2006.
[32] H. Miled, C. Olivier, M. Cheriet, and Y. Lecourtier, “Coupling Observation/Letter for a Markovian Modelization Applied to the Recognition of Arabic Handwriting,” Proc. Fourth Int'l Conf. Document Analysis and Recognition, pp. 580-583, 1997.
[33] M.A. Mohamed and P.D. Gader, “Handwritten Word Recognition Using Segmentation-Free Hidden Markov Modeling and Segmentation-Based Dynamic Programming Techniques,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 5, pp. 548-554, May 1996.
[34] C. Mokbel, H. Abi Akl, and H. Greige, “Automatic Speech Recognition of Arabic Digits over the Telephone Network,” Proc. Research Trends in Science and Technology, 2002.
[35] M. Pechwitz, S.S. Maddouri, V. Märgner, N. Ellouze, and H. Amiri, “IFN/ENIT-Database of Handwritten Arabic Words,” Proc. Colloque Int'l Francophone sur l'Ecrit et le Document, pp. 129-136, 2002.
[36] M. Pechwitz and V. Märgner, “HMM-Based Approach for Handwritten Arabic Word Recognition Using the IFN/ENIT-Database,” Proc. Seventh Int'l Conf. Document Analysis and Recognition, pp. 890-894, 2003.
[37] L.W. Rabiner, “A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,” Proc. IEEE, vol. 77, no. 2, pp. 257-285, 1989.
[38] A. Rahman and M. Fairhurst, “Multiple Classifier Decision Combination Strategies for Character Recognition: A Review,” Int'l J. Document Analysis and Recognition, vol. 5, pp. 166-194, 2003.
[39] Y.H. Tay, P.M. Lallican, M. Khalid, C. Viard-Gaudin, and S. Knerr, “An Off-Line Cursive Handwritten Word Recognition System,” Proc. IEEE Region 10 Int'l Conf. Electrical and Electronic Technology, 2001.
[40] The Unicode Consortium, The Unicode Standard, Version 5.0, Addison-Wesley, 2006.
[41] S.M. Touj and N. Ben Amara, “Arabic Handwritten Words Recognition Based on a Planar Hidden Markov Model,” Int'l Arab J. Information Technology, vol. 2, no. 4, pp. 318-325, 2005.
[42] A. Vinciarelli and J. Luettin, “Off-Line Cursive Script Recognition Based on Continuous Density HMM,” Proc. Int'l Workshop Frontiers in Handwriting Recognition, pp. 493-498, 2000.
[43] A. Yardeni, AventureLettres. Association Alphabets, Mar. 2004.
16 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool