The Community for Technology Leaders
RSS Icon
Subscribe
Issue No.10 - October (2011 vol.33)
pp: 2066-2080
Farès Menasri , A2iA SA, Artificial Intelligence and Image Analysis, Paris
Rami Al-Hajj Mohamad , University of Balamand, Lebanon
Chafic Mokbel , University of Balamand, Lebanon
Anne-Laure Bianne-Bernard , A2iA SA, Artificial Intelligence and Image Analysis and Telecom ParisTech/TSI and CNRS LTCI, Paris
Laurence Likforman-Sulem , Telecom ParisTech/TSI and CNRS LTCI, Paris
ABSTRACT
This study aims at building an efficient word recognition system resulting from the combination of three handwriting recognizers. The main component of this combined system is an HMM-based recognizer which considers dynamic and contextual information for a better modeling of writing units. For modeling the contextual units, a state-tying process based on decision tree clustering is introduced. Decision trees are built according to a set of expert-based questions on how characters are written. Questions are divided into global questions, yielding larger clusters, and precise questions, yielding smaller ones. Such clustering enables us to reduce the total number of models and Gaussians densities by 10. We then apply this modeling to the recognition of handwritten words. Experiments are conducted on three publicly available databases based on Latin or Arabic languages: Rimes, IAM, and OpenHart. The results obtained show that contextual information embedded with dynamic modeling significantly improves recognition.
INDEX TERMS
Latin and Arabic handwriting recognition, context-dependent HMMs, neural-network combination.
CITATION
Farès Menasri, Rami Al-Hajj Mohamad, Chafic Mokbel, Anne-Laure Bianne-Bernard, Laurence Likforman-Sulem, "Dynamic and Contextual Information in HMM Modeling for Handwritten Word Recognition", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol.33, no. 10, pp. 2066-2080, October 2011, doi:10.1109/TPAMI.2011.22
REFERENCES
[1] R. Palacios, A. Gupta, and P. Wang, "Handwritten Bank Check Recognition of Courtesy Amounts," Int'l J. Image and Graphics, vol. 4, no. 2, pp. 203-222, 2004.
[2] W. Ding, C. Suen, and A. Krzyzak, "A New Courtesy Amount Recognition Module of a Check Reading System," Proc. 19th Int'l Conf. Pattern Recognition, pp. 1-4, 2008.
[3] C. Suen, L. Lam, D. Guillevic, N. Strathy, M. Cheriet, J. Said, and R. Fan, "Bank Check Processing System," Int'l J. Imaging Systems and Technology, vol. 7, no. 4, pp. 392-403, 1996.
[4] T. Paquet and Y. Lecourtier, "Automatic Reading of the Literal Amount of Bank Checks," Machine Vision and Applications, vol. 6, nos. 2/3, pp. 151-162, 1993.
[5] M. Wienecke, G.A. Fink, and G. Sagerer, "Toward Automatic Video-Based Whiteboard Reading," Int'l J. Document Analysis and Recognition, vol. 7, nos. 2/3, pp. 188-200, 2005.
[6] J.A. Rodriguez and F. Perronnin, "Local Gradient Histogram Features for Word Spotting in Unconstrained Handwritten Documents," Proc. First Int'l Conf. Frontiers in Handwriting Recognition, 2008.
[7] A. Vinciarelli and S. Bengio, "Offline Recognition of Unconstrained Handwritten Texts Using HMMs and Statistical Language Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 26, no. 6, pp. 709-720, June 2004.
[8] E. Kavallieratou, N. Fakotakis, and G.K. Kokkinakis, "An Unconstrained Handwriting Recognition System," Int'l J. Document Analysis and Recognition, vol. 4, no. 4, pp. 226-242, 2002.
[9] A. Vinciarelli and J. Luettin, "A New Normalization Technique for Cursive Handwritten Words," Pattern Recognition Letters, vol. 22, no. 9, pp. 1043-1050, 2001.
[10] A.H. Toselli, "Reconocimiento de Texto Manuscrito Continuo," PhD dissertation, Departamento de Sistemas Informaticos y Computacion, Universidad Politecnica de Valencia, 2004.
[11] R. Al-Hajj Mohamad, L. Likforman-Sulem, and C. Mokbel, "Combining Slanted-Frame Classifiers for Improved HMM-Based Arabic Handwriting Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 7, pp. 1165-1177, July 2009.
[12] T. Plötz and G. Fink, "Markov Models for Offline Handwriting Recognition: A Survey," Int'l J. Document Analysis and Recognition, vol. 12, pp. 269-298, 2009.
[13] C. Sirat, "Handwriting and the Writing Hand," Writing Systems and Cognition, vol. 6, 1994.
[14] R. Plamondon and W. Guerfali, "The Generation of Rapid Human Movements I, a Delta-Lognormal Law," Biological Cybernetics, vol. 78, nos. 93/94, pp. 119-132, 1998.
[15] P. Natarajan, S. Saleem, R. Prasad, E. MacRostie, and K. Subramanian, "Multi-Lingual Offline Handwriting Recognition Using Hidden Markov Models: A Script-Independent Approach," Proc. Summit on Arabic and Chinese Handwriting Recognition, 2006.
[16] M. Schussler and H. Niemann, "A HMM-Based System for Recognition of Handwritten Address Words," Proc. Int'l Workshop Frontiers in Handwriting Recognition, pp. 505-514, 1998.
[17] G. Fink and T. Plotz, "On the Use of Context-Dependent Modeling Units for HMM-Based Offline Handwriting Recognition," Proc. Int'l Conf. Document Analysis and Recognition, vol. 2, pp. 729-733, 2007.
[18] R. El-Hajj, C. Mokbel, and L. Likforman-Sulem, "Recognition of Arabic Handwritten Words Using Contextual Character Models," Proc. SPIE Document Recognition and Retrieval, 2008.
[19] E. Grosicki and H. El-Abed, "ICDAR 2009 Handwriting Recognition Competition," Proc. Int'l Conf. Document Analysis and Recognition, pp. 1398-1402, 2009.
[20] U. Marti and H. Bunke, "The IAM-Database: An English Sentence Database for Off-Line Handwriting Recognition," Int'l J. Document Analysis and Recognition., vol. 5, pp. 39-46, 2002.
[21] http://www.nist.gov/itl/iad/mighart2010.cfm , 2011.
[22] R. El-Hajj, L. Likforman-Sulem, and C. Mokbel, "Arabic Handwriting Recognition Using Baseline Dependant Features and Hidden Markov Modeling," Proc. Int'l Conf. Document Analysis and Recognition, pp. 893-897, 2005.
[23] N. Otsu, "A Threshold Seclection Method from Gray-Level Histograms," IEEE Systems, Man, and Cybernetics, vol. 9, no. 1, pp. 62-66, Jan. 1979.
[24] K.-F. Lee, "Context-Dependent Phonetic Hidden Markov Models for Speaker-Independent Continuous Speech Recognition," Readings in Speech Recognition, pp. 347-366, Morgan Kaufmann Publishers, 1990.
[25] C. Chelba and R. Morton, "Mutual Information Phone Clustering for Decision Tree Induction," Proc. Int'l Conf. Spoken Language Processing, 2002.
[26] S.J. Young, J.J. Odell, and P.C. Woodland, "Tree-Based State Tying for High Accuracy Acoustic Modelling," Proc. Workshop Human Language Technology, pp. 307-312, 1994.
[27] H. Zen, K. Tokuda, and T. Kitamura, "Decision Tree Based Simultaneous Clustering of Phonetic Contexts, Dimensions, and State Positions for Acoustic Modeling," Proc. European Conf. Speech Comm. and Technology, pp. 3189-3192, 2003.
[28] http://www.telecom-paristech.fr/~lauli/LatinScriptRules questionstree_accents.txt , 2011.
[29] A.F.R. Rahman and M.C. Fairhurst, "Multiple Classifier Decision Combination Strategies for Character Recognition: A Review," Int'l J. Document Analysis and Recognition, vol. 5, no. 4, pp. 166-194, 2003.
[30] J. Kittler, M. Hatef, R.P. Duin, and J. Matas, "On Combining Classifiers," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 3, pp. 226-239, Mar. 1998.
[31] R. Polikar, "Ensemble Based Systems in Decision Making," IEEE Circuits and Systems Magazine, vol. 6, no. 3, pp. 21-45, July-Sept. 2006.
[32] R. Al-Hajj, C. Mokbel, and L. Likforman-Sulem, "Combination of HMM-Based Classifiers for the Recognition of Arabic Handwritten Words," Proc. Int'l Conf. Document Analysis and Recognition, pp. 959-963, 2007.
[33] H. El-Abed and V. Märgner, "Reject Rules and Combination Methods to Improve Arabic Handwritten Word Recognizers," Proc. Int'l Conf. Frontiers in Handwriting Recognition, p. 6p, 2008.
[34] V. Frinken, T. Peter, A. Fischer, H. Bunke, T.-M.-T. Do, and T. Artieres, "Improved Handwriting Recognition by Combining Two Forms of Hidden Markov Models and a Recurrent Neural Network," Proc. 13th Int'l Conf. Computer Analysis of Images and Patterns, pp. 189-196, 2009.
[35] E. Augustin, M. Carre, E. Grosicki, J.-M. Brodin, E. Geoffrois, and F. Preteux, "Rimes Evaluation Campaign for Handwritten Mail Processing," Proc. Int'l Workshop Frontiers in Handwriting Recognition, pp. 231-235, 2006.
[36] http:/rimes.it sudparis.eu/, 2010.
[37] A.-L. Bianne, C. Kermorvant, and L. Likforman-Sulem, "Context-Dependent HMM Modeling Using Tree-Based Clustering for the Recognition of Handwritten Words," Proc. SPIE Document Recognition and Retrieval, 2010.
[38] R.P.W. Duin, "The Combining Classifier: To Train or Not to Train?" Proc. 16th Int'l Conf. Pattern Recognition, vol. 2, pp. 765-770, 2002.
[39] M. Zimmermann and H. Bunke, "Automatic Segmentation of the IAM Off-Line Database for Handwritten English Text," Proc. 16th Int'l Conf. Pattern Recognition, vol. 4, pp. 35-39, 2002.
[40] A. Graves, M. Liwicki, S. Fernandez, R. Bertolami, H. Bunke, and J. Schmidhuber, "A Novel Connectionist System for Unconstrained Handwriting Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 31, no. 5, pp. 855-868, May 2009.
[41] S. Espana-Boquera, M. Castro-Bleda, J. Gorbe-Moya, and F. Zamora-Martinez, "Improving Offline Handwritten Text Recognition with Hybrid HMM/ANN Models," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 33, no. 4, pp. 767-779, Apr. 2011.
[42] T. Caesar, J. Gloger, and E. Mandler, "Preprocessing and Feature Extraction for a Handwriting Recognition System," Proc. Second Int'l Conf. Document Analysis and Recognition, pp. 408-411, 1993.
[43] A. Kaltenmeier, T. Caesar, J. Gloger, and E. Mandler, "Sophisticated Topology of Hidden Markov Models for Cursive Script Recognition," Proc. Second Int'l Conf. Document Analysis and Recognition, pp. 139-142, 1993.
[44] M.-P. Schambach, "Model Length Adaptation of an HMM Based Cursive Word Recognition System," Proc. Seventh Int'l Conf. Document Analysis and Recognition, vol. 1, pp. 109-113, 2003.
[45] B. Issam, 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.
[46] Y. Kessentini, T. Paquet, and A. Benhamadou, "A Multi-Stream Hmm-Based Approach for Off-Line Multi-Script Handwritten Word Recognition," Proc. Int'l Conf. Frontiers in Handwriting Recognition, 2008.
[47] C. Choisy, "Dynamic Handwritten Keyword Spotting Based on the NSHP-HMM," Proc. Int'l Conf. Document Analysis and Recognition, pp. 242-246, 2007.
[48] S.J. Young, G. Evermann, M.J.F. Gales, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, and P.C. Woodland, "The HTK Book, Version 3.4," Cambridge Univ. Eng. Dept., 2006.
26 ms
(Ver 2.0)

Marketing Automation Platform Marketing Automation Tool