Open Access Open Access  Restricted Access Subscription or Fee Access

Offline Arabic Handwriting Recognition System Based on the Combination of Multiple Semi-Continuous HMMs


(*) Corresponding author


Authors' affiliations


DOI: https://doi.org/10.15866/irecos.v10i7.6229

Abstract


In this paper, we present a multi-classifier approach for off-line handwritten Arabic word recognition system. The main objective of this paper is to develop a handwriting recognition system that can be learned and applied to different Arabic writing styles. We propose an approach that combines multiple classifiers based on semi-continuous Hidden Markov Model using different feature extraction methods. The following process consists of several phases: pre-processing, extraction of pertinent characteristics and modeling. The role of the pre-processing phase is to prepare the input image text, i.e, binarization, normalization, segmentation and skeletonization. The obtained images are then used to extract features using a mixture of geometrical and statistical characteristics, namely, the intensities of gray level of the pixel, the densities and the concavities of the pixels, the VH2D projections and the invariants Hu moments. The modeling phase is based on the Hidden Markov Model using the HTK tools for the training and the recognition phase. Each character is modeled by a semi-continuous HMMs, and each set of feature has its own HMM. To improve the performance of our Arabic handwriting recognition system, we propose to combine parallel methods of HMMs having the same architecture, but training phase using four different types of primitive vectors. Our system was evaluated using the ENIT/IFN the base Arabic data. Results Obtained show that the combination of four semi-continuous HMM classifiers gives a significant improvement of our off-line handwriting recognition system compared to results obtained when using individual classifiers.
Copyright © 2015 Praise Worthy Prize - All rights reserved.

Keywords


Off-line Recognition of Arabic Handwriting; Sliding Windows; the Moments Invariant of Hu; VH2D Approach; HMMTK Hidden Markov Model Tools; Combining Classifiers

Full Text:

PDF


References


A. F. Rahman and M. A. Airhurst, study of some multi-expert recognition strategies forindustrial applications, issues of processing speed and implemen tability . In Vision Interfac. - 1999.

H. Zouari, Contribution à l’évaluation des méthodes de combinaison parallèle de classifieurs par simulation: Thèse de Doctorat, Université de Rouen, 2004.

L. Prevost, C. Michel-Sendis, A. Moises, L. Oudot, And M. Milgram, Combining model-based and discriminative classifiers: application to handwritten character recognition. In 7th International Conference on Document Analysis and Recognition, volume 1, p. 31-35, 2003.
http://dx.doi.org/10.1109/icdar.2003.1227623

R. El-Hajj L. Likforman, and C. Mokbel, Combining slanted-frame classifiers for improved HMM-based Arabic handwriting recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, vol. 31, no. 7 - pp. 1165-1177, 2009.
http://dx.doi.org/10.1109/tpami.2008.136

Rafael M.O. Cruz G.D.C. Gavalcanti and T.I. Ren, Handwritten Digit Recognition Using Multiple Feature Extraction Techniques and Classifier Ensemble. IWSSIP'10, 17 th International Conference on Systems, Signals and Image Processing. - 2010.

N. Azizi N. Farah, M.T. Khadir, and M. Sellami, Arabic handwritten word recognition using classifiers selection and feature extraction/selection. Recent Advances in Intelligent Information Systems. - pp. 735-742- 2009.

L. R. Rabiner, A Tutorial on Hidden Markov Models and Selected applications in speech Recognition, A. Wailbel, Lee K.-F., Readings in Speech Recognition, pp. 267-296, Kauf-mann, San Mateo, CA, 1990.
http://dx.doi.org/10.1016/b978-0-08-051584-7.50027-9

M. Pechwitz, S. Maddouri, V. Mârgner, N. Ellouze, H. Amiri, IFN/ENIT-Databas of handwritten arabic words. CIFED’02, Colloque International Francophone sur l’Ecrit et le Document, Hammament, Tunisie, p. 129-136, 2002.

M. S. Khorsheed, Off-line arabic character recognition– a review, Pattern Analysis and Applications, 5: 31–45, 2002.
http://dx.doi.org/10.1007/s100440200004

S. Theodoridis and K.Koutroumbs. Pattern Recognition, Second Edition. Copyright 2003, Elsevier(USA). Academic Press. 2003.

F. Menasri, Contributions à la reconnaissance de l’écriture arabe manuscrite. Descartes University-Paris V : Thèse de doctorat, Mathematics and Computer Science Department, 2008.

A. Maqqor, A. Halli, K. Satori, and H. Tairi, Using HMM Toolkit (HTK) for Recognition of Arabic Manuscripts Characters , In 4th Internat. Conf. on Multimedia Computing and Systems : ICMCS’14, April 14-16, Marrakesh-Morocco, IEEE Xplore, 2014.
http://dx.doi.org/10.1109/icmcs.2014.6911316

R. El-Hajj, Reconnaissance hors ligne de textes manuscrits cursifs par l’utilisation de sys-tèmes hybrides et de techniques d’apprentissage automatique: Thèse de Doctorat, Ecole Nationale Supérieure de Télécommunications, Paris 2007.

T.M. Hamdani and A. M. Alimi. Artificial Neural Networks and Genetic Algorithms, chapter β –SVM a new support vector machine, pages 63-68, Springer, 2003.
http://dx.doi.org/10.1007/978-3-7091-0646-4_13

A. Maqqor, A. Halli, K. Satori, H. Tairi, Off-line Recognition Handwriting Arab-ic Words Using Combination of Multiple classifiers, 3rd International IEEE Colloquium On Information Science and Technology-Session Arabic Natural Language Processing, ANLP-CIST'14, Tetuan-Chefchaouen, Morocco, October 20-22, IEEE Xplore, 2014.
http://dx.doi.org/10.1109/cist.2014.7016629

Baghdadi. Hadj. Ali M. Senouci, réseaux de neurones: théorie et pratique: édition O. P. U. office des publication universitaires, 2005.

M. Senouci A. Liazid, H. A. Beghdadi and D. Benhamamouch, A Neuro-Euclidian Approach to Handwritten Word Recognition. Information Technology Journal, Vol.5 - pp. 958-963 – 2006.
http://dx.doi.org/10.3923/itj.2006.958.963

A. Maqqor, A. Halli, K. Satori, and H. Tairi, A Slippery window and VH2D Approach to Recognition Offline Arabic Words, pages 269-279. Spring, 2013.
http://dx.doi.org/10.1007/978-3-319-00951-3_26

H. Ming-Kuei, “Visual pattern recognition by moment invariants”, information Theory, IRE Transactions on, vol. 8, pp. 179-187, 1962.
http://dx.doi.org/10.1109/tit.1962.1057692

S. Al-Ma’adeed D. Elliman, C. Higgins, Off-line recognition of handwritten Arabic words using multiple hidden Markov models. Knowledge-Based Systems, Vol. 17, N°.2-4 - pp.75-79- May , 2004.
http://dx.doi.org/10.1016/j.knosys.2004.03.002

B.Farou S. Hallaci, H. Seridi, Systéme Neuro-Merkovienne pour la Reconnaissance de l’écriture arabe à Vocabulaire limité. conférence: Procceding of the 2nd conference Internationale sur ’informatique et ses applications (CIIA’09). - Saida, Algeria : - May 3-4, 2009.

AL-Shatnawi, A.Mahmoud, AL-Salaimeh, S.AL-Zawaideh, F.Hanna, O.Khairuddin, Offline arabic text recognition an overview, World Comput. Sci. Inform. Technol. J. 1 (5), 184–192, 2011.

AlKhateeb, Jawad H., Ren, J.Jiang, Jianmin, H.Al-Muhtaseb, Offline handwritten arabic cursive text recognition using hidden markov models and re-ranking, Pattern Recognition Lett. 32 (8), 1081–1088, 2011.
http://dx.doi.org/10.1016/j.patrec.2011.02.006

Al-Muhtaseb, A. Husni, Mahmoud, A. Sabri, Qahwaji, Rami S., Recognition of off-line printed Arabic text using hidden markov models. Signal Process. 88 (12), 2902–2912, 2008.
http://dx.doi.org/10.1016/j.sigpro.2008.06.013

S. Young, G. Evermann, D. Kershaw, D. Moore, J. Odell, D. Ollason, V. Valtchev, P. Woodland. The HTK Book. Cambridge University Engineering Dept, 2001.

R. El-Hajj, L. Likforman-Sulem, C. Mokbel, Arabic handwriting recognition using baseline dependent features and Hidden Markov Modeling, Seoul, Corée du Sud, ICDAR 2005.
http://dx.doi.org/10.1109/icdar.2005.53

L. Rabiner et B. H. Juang, Fundamentals of speech recognition. Prentice Hall PTR, 1993.


Refbacks

  • There are currently no refbacks.



Please send any question about this web site to info@praiseworthyprize.com
Copyright © 2005-2023 Praise Worthy Prize