Abstract The arab writing is originally cursive, difficult to segment and has a great variability. To overcome these problems, we propose two holistic approaches for the recognition of the handwritten arabic words in a limited vocabulary based on the Hidden Markov Models (HMMs): discrete with wk-means and continuous. In the suggested approach, each word of the lexicon is modelled by a discrete or continuous HMM. After a series of pre-processing, the word image is segmented from right to left in succession frames of fixed or variable size in order to generate a sequence vector of statistical and structural parameters which will be submitted to two classifiers to identify the word. To illustrate the efficiency of the proposed systems, significant experiments are carried out on IFN/ENIT benchmark database.

References

[1] Abdi M. and Khemakhem M., Off-Line Text Independent Arabic Writer Identification Using Contour Based Features, International Journal of Signal and Image Processing, vol. 1, no. 1, pp. 4-11, 2010.

[2] Al Badr B. and Mahmoud S., Survey and Bibliography of Arabic Optical Text Recognition, Signal Processing, vol. 41, no. 1, pp. 49-77, 1995.

[3] Al-Ma adeed S., Recognition of off-Ligne Handwritten Arabic Words using Neural Network, in proceeding of GMAI 06 International Conference on Geometric Modeling and Imaging, London, pp. 141-114, 2006.

[4] Almuallim H. and Yamaguchi S., A Method of Recognition of Arabic Cursive Handwriting, 688 The International Arab Journal of Information Technology, Volume 14, No. 5, September 2017 IEEE Transactions, vol. 9, no. 5, pp.715-722, 1987.

[5] Alsallah B. and Safadi H., An Arabic Online Handwriting Recognition System, in Proceeding of ICTTA 06 2nd IEEE International conference on Information ET Communication Technologies: from Theory to Applications, Damascus, pp. 1844-1849, 2006.

[6] Ameur A., Romeo-Pakker K., Miled H., and Cheriet M., Approche Globale pour la Reconnaissance de Mots Manuscrits Arabes, Actes CNED 94, 3 me Colloque National sur l Ecrit et le Document, 1994.

[7] Amin A., Off-Line Arabic Character Recognition: the State of the Art, Pattern Recognition, vol. 31, no. 5, pp.517 530, 1998.

[8] Amin A. Kaced A., Haton J., and Mohr R., Handwritten Arabic Character Recognition by the IRAC System, in Proceedings of ICPR 80, 5th International Conference on Pattern Recognition, Florida, pp. 729-731, 1980.

[9] Azizi N., Farah N., and Sellami M., Off-line Handwritten Word Recognition using Ensemble of Classifier Selection and Features Fusion, Journal of Theoretical and Applied Information Technology JATIT, vol. 14. 2, pp. 141-150, 2010.

[10] Benouareth A., Ennaji A., and Sellami M., Arabic Handwritten Word Recognition using HMMs with Explicit State Duration, EURASIP Journal on Advances in Signal Processing, vol. 2008.

[11] Biadsy F. El-Sana S. and Habash N., Online Arabic Handwriting Recognition using Hidden Markov Models, in Proceeding of IWFHR 06, 10th International Work shop on Frontiers in Handwriting Recognition, La Baule, pp. 85-90, 2006.

[12] Blumenstein M. and Verma B., A Segmentation Algorithm used in Conjunction with Artificial Neural Networks for the Recognition of Real- World Postal Addresses, in proceeding of ICCIMA, Gold Coast, pp. 1-9, 1997.

[13] Boobord F., Othman Z., and Abu Bakar A., A WK-means Approach for Clustering, The International Arab Journal of Information Technology, vol. 12, no. 5, pp. 489-493, 2015.

[14] Bulacu M., Schomaker L., and Brink A., Text- Independent Writer Identification and Verification on Off-Line Arabic Handwriting, in proceeding of 9th ICDAR, Parana, pp. 769-773, 2007.

[15] Chen J., Lopresti D., and Kavallieratou E., The Impact of Ruling Lines on Writer Identification, in proceeding of the 12th International Conference on Frontiers in Handwriting Recognition, Kolkata, pp.439-444, 2010.

[16] Chen M., Kundu A., and Srihari S., Variable Duration Hidden Markov Model and Morphological Segmentation for Handwritten Word Recognition, IEEE Transactions on Image Processing, vol. 4, no. 12, pp. 1675-1688, 1995.

[17] Djeddi C. and Souici-Meslati L., Artificial Immune Recognition System for Arabic Writer Identification, in proceeding of 4th International Symposium on Innovation in Information and Communication Technology, Rome, pp.159-165, 2011.

[18] El-Hadj R., Reconnaissance Hors Ligne de Textes Manuscrits Cursifs Par L utilisation de Syst mes Hybrides et de Techniques D apprentissage Automatique, Th se de Doctorat, 2007.

[19] El-Hadj R., Likeforman-Seulem L., and Mokbel C., Arabic Handwriting Recognition Using Baseline Dependant Features and Hidden Markov Models, in Proceeding of ICDAR 05 International Conference on Document Analysis and Recognition, Seoul, pp. 893-897, 2005.

[20] El-Hadj R., Mokbel C., and Likeforman-Seulem L., Reconnaissance de l criture arabe cursive: combinaison de classifieurs MMCs fen tres orient es, Actes CIFED 06, 2006.

[21] El-Yacoubi M., Gilloux M., Sabourin R., and Suen C., An HMM-based Approach for off- Line Unconstrained Handwritten Word Modeling and Recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 21, no. 8, pp.752-760, 1999.

[22] Farah N. Ennaji A. Kadir T. and Sellami M., Benefit of Multiclassifier Systems for Arabic Handwritten Words Recognition, in proceeding of ICDAR 05 8th International Conference on Document Analysis and recognition, Seoul, pp. 222-226, 2005.

[23] Farah N., Souici L., and Sellami M., Classifiers Combination and Syntax Analysis for Arabic Literal Amount Recognition, Engineering Applications of Artificial Intelligence, vol. 19, no. 1, pp. 9-39, 2006.

[24] Fujimoto Y. and Murata N., A modified EM Algorithm for Mixture Models based on Bregman Divergence, Springer, 2007.

[25] Garian U. and Paquet T., Off-Line Multi-Script Writer Identification Using AR Coefficients, in proceeding of International Conference on Document Analysis and Recognition, Spain, pp. 991-995, 2009.

[26] Gazzah S. and Ben Amara N., Arabic Handwriting Texture Analysis for Writer Identification Using the DWT-Lifting Scheme, in proceeding of 9th International Conference on Document Analysis and Recognition, Parana, pp.1133-1137, 2007.

[27] Kammon W. and Ennaji A., Reconnaissance de textes arabes vocabulaire ouvert. Laboratoire Features Modelling in Discrete and Continuous Hidden Markov Models... 689 Perception, Syst me Information (PSI) FRE- CNRS 2645, 2001.

[28] Khorsheed M., Off-Line Arabic Character Recognition a Review, Pattern Anal, vol. 5, no. 1, pp. 31-45, 2002.

[29] Khorsheed M., Recognising Handwritten Arabic Manuscripts using a Single Hidden Markov Model, Pattern Recognition Letters, vol. 24, no. 14, pp. 2235-2242, 2003.

[30] Koerich A., Sabourin R., and Suen C., Recognition and Verification of Unconstrained Handwritten Words, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 27, no. 10, pp. 1509-1522, 2005.

[31] Mahmoud S., Arabic Character Recognition Using Fourier Descriptors and Character Contour Encoding, Pattern Recognition, vol. 27, no. 6, pp. 815-824, 1994.

[32] Margner V., El-Abed H., and Pechwitz M., Off- Line Handwritten Word Recognition Using HMM- a Character Approach Without Explicit Segmentation, Actes CIFED 06, 2006.

[33] Margner V., Pechwitz M., and El-Abed H., ICDAR 2005 Arabic Handwriting Recognition Competition, In Proceedings of the International Conference on Document Analysis and Recognition, Seoul, pp. 70-74, 2005.

[34] Mezghani N., Densit s de Probabilit D entropie Maximale et M moires Associatives Pour la Reconnaissance en Ligne de Caract res Arabes, Th se de PHD, Institut National de la Recherche Scientifique, 2005.

[35] Mezghani N., Mitiche A., and Cheriet M., A New Representation of Shape and its use for High Performance in Online Arabic Character Recognition by an Associative Memory, International Journal on Document Analysis and recognition, vol. 7, no. 4, pp. 201-210, 2005.

[36] Mezghani N., Mitiche A., and Cheriet M., Estimation de Densit s de Probabilit par Maximum D entropie et Reconnaissance Bayesienne de Caract res Arabes en Ligne, RFIA 06, 2006.

[37] Olivier C., Miled H., Remeo K., and Lecourtier Y., Segmentation and Coding of Arabic Handwritten Words, in Proceedings of 13th International Conference on Pattern Recognition, Vienne, pp. 264-268, 1996.

[38] Pavlidis T., Algorithms for Graphic and Image Processing. Rockville, MD: Computer science press, pp.195-200, 1982.

[39] Pechwitz M. and Maergner V., HMM Based Approach for Handwritten Arabic Word Recognition Using the IFN/ENIT- Database, in Proceedings of the 7th International Conference on Document Analysis and Recognition, Edinburgh, pp.890-894, 2003.

[40] Rabiner L., A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, IEEE, vol. 77, no. 2, pp. 257-286, 1989.

[41] Rahman A. and Fairhurst M., Multiple Classifier Decision Combination Strategies for Character Recognition, International Journal on Document Analysis and Recognition, vol. 5, no. 4, pp. 166-194, 2003.

[42] Saon G., Mod les Markoviens uni- Bidimensionnels Pour la Reconnaissance de L criture Manuscrite Hors-Ligne, Th se de doctorat, Universit Henri Poincar Nancy 1, 1998.

[43] Sari T. and Sellami M., Cursive Arabic Script Segmentation and Recognition System, International Journal of Computers and Applications, vol. 27, no.3, pp. 161-168 2005.

[44] Slimane F., Kanoun S., Hennebert J., Alimi A., and Ingold R., Mod les de Markov Cach s et Mod le de Longueur pour la Reconnaissance de l Ecriture Arabe Basse R solution, MajecSTIC, 2009.

[45] Souici L., Aoun A., and Sellami M., Versune Architecture Modulaire de Reconnaissance de Montants de Ch ques Arabes, in Proceedings of de la Conf rence Internationale en Informatique, Annaba, pp.260-270, 1999.

[46] Vinciarelli A., Bengio S., and Bunke H., Off- Line Recognition of Unconstrained Handwritten Texts Using {HMM}s and Statistical Language Models, IEEE Transactions on PAMI, vol. 26, no. 6, pp. 709-720, 2004.

[47] Zermi N., Ramdani M., and Bedda M., Arabic Handwriting Word Recognition based on Hybride HMM/ANN Approach, International Journal of Soft Computing, vol. 2, no. 1, pp. 5- 10, 2007.

[48] Zouari H., Heutte L., and Lecourtier Y., Controlling the Diversity in Classifier Ensembles trough a Measure of Agreement, Pattern Recognition, vol. 38, no. 1, pp. 2195- 2199, 2005. 690 The International Arab Journal of Information Technology, Volume 14, No. 5, September 2017 Amine Benzenache received his Engineer degree in Electronics from University of 08Mai 1945, Guelma, Algeria. in 2004 and the Magister degree in Intelligence artificial University of Guelma in 2007. Currently, he is a researcher in the laboratory LabSTIC, University of 8 Mai 1945 of Guelma and member in GADM team at LabSTIC laboratory, Guelma, Algeria. Her current research interests include Handwriting recognition, HMM, pattern recognition and document processing. Hamid Seridi received his Bachelor s degree with honours in 1981, from the University of Annaba, Algeria, and the Master s degree from the Polytechnic Institute of New-York, USA in 1984, both in Electrical Engineering. He received his PhD in Computer Science with distinction in 2001 from the University of Reims, France. He was Vice Dean of the Post-Graduation, Scientific Research and External Relations in the University of Guelma. Currently he is Professor and Director of Laboratory of Science and Information Technologies and Communication LabSTIC . He is also Chairman of the Scientific Council of the Faculty of Mathematics and Computing and Material Sciences. He is an expert member at the national committee for evaluation and accreditation national projects research. His research interests include approximate knowledge management, pattern recognition and artificial intelligence, data mining, video mining, machine learning and cryptography. Herman Akdag received his PhD and HDR degree at Paris 6 University in 1980 and 1992, respectively. Assistant Professor since 1980, he obtained a Full Professor position at Reims University, France in 1995. He is was a Senior Researcher at LIP6, CNRS, Paris and the head of the research group MODECO in University of Reims. Currently, he is a Full Professor at the University of Paris 8 and member at LIASD, France. His research interests include Fuzzy Set Theory and Machine Learning approaches to decision-making, image classification and image retrieval. He also works on approximate reasoning, fuzzy abduction, data mining, and user modelling.