{"references": ["R. Elanwar, M. Rashwan, and S. Mashali, \"OHASD: The first online Arabic sentence database handwritten on tablet PC\", International\nConference on Signal and Image Processing ICSIP 2010, Singapore,\nProceedings of World Academy of Science, Engineering and\nTechnology (WASET), vol. 72, pp.710-715, 2010.", "R. Plamondon, S. Srihari, \"Online and Off-Line Handwriting Recognition, A Comprehensive Survey\", IEEE Transactions on Pattern\nAnalysis and Machine Intelligence, vol. 22, No.1, pp. 63-84, 2000.", "H. Bunke, \"Recognition of Cursive Roman Handwriting - Past, Present\nand Future\", Proceedings of the 7th International Conference on\nDocument Analysis and Recognition, ICDAR'03, vol. 1, pp. 448-455,2003.", "E. Kavallieratou, E. Stamatatos, N. Fakotakis, G. Kokkinakis, \"Handwritten Character Segmentation Using Transformation-Based\nLearning\", Proceedings of the 15th International Conference on Pattern Recognition ICPR, 2000, pp.634-637.", "C. De Stefano, M. Garruto, A. Marcelli, \"A Multiresolution Approach to On-line Handwriting Segmentation and Feature Extraction\", Proceedings of the 17th International Conference on Pattern Recognition,\nICPR-04, vol. 2, pp. 614-617, 2004.", "C. De Stefano, A. Marcelli, \"From Ligatures to Characters: A Shapebased\nAlgorithm for Handwriting Segmentation\", Proceedings of the 8th\nInternational Workshop on Frontiers in Handwriting Recognition (IWFHR-02), pp. 473-478, 2002.", "S. Abdulla, A. Al-Nassiri, R. Abdul Salam, \"Offline Arabic Handwritten\nWord Segmentation using rotational invariant segments features\",\nInternational Arab Journal of Information Technology, vol. 5, no. 2, pp. 200-208, 2008.", "M. Kherallah, L. Haddad, A. Alimi, \"A new Approach for Online Arabic\nHandwriting Recognition\", Proceedings of the Second International Conference on Arabic Language Resources and Tools, pp.22-23, 2009.", "F. Kurniawan, M. Rahim, N. Sholihah, A. Rakhmadi, D. Mohamad, \"Characters Segmentation of Cursive Handwritten Words based on\nContour Analysis and Neural Network Validation\", ITB J. ICT, vol. 5, no. 1, pp. 1-16, 2011.\n[10] A. Rehman Khan, D. Muhammad, \"A Simple Segmentation Approach\nfor Unconstrained Cursive Handwritten Words in Conjunction with the\nNeural Network\", International Journal of Image Processing, vol 2, no.\n3, pp. 29-35, 2008.\n[11] P. Cavalin, A. de Souza Britto, F. Bortolozzi, R. Sabourin, L. Oliveira,\n\"An Implicit Segmentation-based Method for Recognition of Handwritten Strings of Characters\", ACM Symposium on Applied\nComputing - SAC , pp. 836-840, 2006.\n[12] I. Guyon, L. Schomaker, R. Plamondon, M. Liberman, S. Janet, \"Unipen\nProject of On-Line Data Exchange and Recognizer Benchmarks\",\nProceedings of 12th International Conference on Pattern Recognition,\npp. 29-33, 1994.\n[13] M. Liwicki, H. Bunke, \"IAM-OnDB - an online English sentence\ndatabase acquired from handwritten text on a whiteboard\", In the\nProceedings of 8th International Conference on Document Analysis and\nRecognition, vol. 2, pp. 956-961, 2005.\n[14] H. El-Abed, M. Kherallah, V. M\u251c\u00f1rgner, A. Alimi, \"On-line Arabic\nhandwriting recognition competition - ADAB database and participating\nsystems\", International Journal on Document Analysis and Recognition,\n2010.\n[15] J. Hull, \"A database for handwritten text recognition research\", IEEE\nTransactions on Pattern Analysis and Machine Intelligence, vol. 16, no.\n5, pp. 550\u2013554, 1994.\n[16] R. Wilkinson, J. Geist, S. Janet, In the first census optical character\nrecognition systems Conference #NISTIR 4912, The U.S. Bureau of\nCensus and the National Institute of Standards and Technology,\nGaithersburg, MD, 1992.\n[17] M. Pechwitz, S. Maddouri, V. Maergner, N. Ellouze, H. Amiri,\n\"IFN/ENIT: Database of Handwritten Arabic Words\", in Proceedings of\nthe CIFED 2002, Tunisia, pp. 129-136, 2002.\n[18] http://www.iam.unibe.ch/\u02dcfki/iamondb/\n[19] S. Abdelazeem, H. Eraqi, \"On-line Arabic Handwritten Personal Names\nRecognition System based on HMM\", Proceedings of the 11th\ninternational conference on document analysis and recognition\nICDAR2011, Beijing, China, pp. 1304-1308, 2011."]}

In this paper we propose a segmentation system for unconstrained Arabic online handwriting. An essential problem addressed by analytical-based word recognition system. The system is composed of two-stages the first is a newly special designed hidden Markov model (HMM) and the second is a rules based stage. In our system, handwritten words are broken up into characters by simultaneous segmentation-recognition using HMMs of unique design trained using online features most of which are novel. The HMM output characters boundaries represent the proposed segmentation points (PSP) which are then validated by rules-based post stage without any contextual information help to solve different segmentation errors. The HMM has been designed and tested using a self collected dataset (OHASD) [1]. Most errors cases are cured and remarkable segmentation enhancement is achieved. Very promising word and character segmentation rates are obtained regarding the unconstrained Arabic handwriting difficulty and not using context help.