Unconstrained Arabic Online Handwritten Words Segmentation using New HMM State Design

Authors: Randa Ibrahim Elanwar, Mohsen Rashwan, Samia Mashali

Abstract:

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.

Keywords: Arabic, Hidden Markov Models, online handwriting, word segmentation

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1084702

References:

[1] R. Elanwar, M. Rashwan, and S. Mashali, "OHASD: The first online Arabic sentence database handwritten on tablet PC", International Conference on Signal and Image Processing ICSIP 2010, Singapore, Proceedings of World Academy of Science, Engineering and Technology (WASET), vol. 72, pp.710-715, 2010.
[2] R. Plamondon, S. Srihari, "Online and Off-Line Handwriting Recognition, A Comprehensive Survey", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, No.1, pp. 63-84, 2000.
[3] H. Bunke, "Recognition of Cursive Roman Handwriting - Past, Present and Future", Proceedings of the 7th International Conference on Document Analysis and Recognition, ICDAR'03, vol. 1, pp. 448-455,2003.
[4] E. Kavallieratou, E. Stamatatos, N. Fakotakis, G. Kokkinakis, "Handwritten Character Segmentation Using Transformation-Based Learning", Proceedings of the 15th International Conference on Pattern Recognition ICPR, 2000, pp.634-637.
[5] 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, ICPR-04, vol. 2, pp. 614-617, 2004.
[6] C. De Stefano, A. Marcelli, "From Ligatures to Characters: A Shapebased Algorithm for Handwriting Segmentation", Proceedings of the 8th International Workshop on Frontiers in Handwriting Recognition (IWFHR-02), pp. 473-478, 2002.
[7] S. Abdulla, A. Al-Nassiri, R. Abdul Salam, "Offline Arabic Handwritten Word Segmentation using rotational invariant segments features", International Arab Journal of Information Technology, vol. 5, no. 2, pp. 200-208, 2008.
[8] M. Kherallah, L. Haddad, A. Alimi, "A new Approach for Online Arabic Handwriting Recognition", Proceedings of the Second International Conference on Arabic Language Resources and Tools, pp.22-23, 2009.
[9] F. Kurniawan, M. Rahim, N. Sholihah, A. Rakhmadi, D. Mohamad, "Characters Segmentation of Cursive Handwritten Words based on Contour Analysis and Neural Network Validation", ITB J. ICT, vol. 5, no. 1, pp. 1-16, 2011.
[10] A. Rehman Khan, D. Muhammad, "A Simple Segmentation Approach for Unconstrained Cursive Handwritten Words in Conjunction with the Neural Network", International Journal of Image Processing, vol 2, no. 3, pp. 29-35, 2008.
[11] P. Cavalin, A. de Souza Britto, F. Bortolozzi, R. Sabourin, L. Oliveira, "An Implicit Segmentation-based Method for Recognition of Handwritten Strings of Characters", ACM Symposium on Applied Computing - SAC , pp. 836-840, 2006.
[12] I. Guyon, L. Schomaker, R. Plamondon, M. Liberman, S. Janet, "Unipen Project of On-Line Data Exchange and Recognizer Benchmarks", Proceedings of 12th International Conference on Pattern Recognition, pp. 29-33, 1994.
[13] M. Liwicki, H. Bunke, "IAM-OnDB - an online English sentence database acquired from handwritten text on a whiteboard", In the Proceedings of 8th International Conference on Document Analysis and Recognition, vol. 2, pp. 956-961, 2005.
[14] H. El-Abed, M. Kherallah, V. Märgner, A. Alimi, "On-line Arabic handwriting recognition competition - ADAB database and participating systems", International Journal on Document Analysis and Recognition, 2010.
[15] J. Hull, "A database for handwritten text recognition research", IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16, no. 5, pp. 550–554, 1994.
[16] R. Wilkinson, J. Geist, S. Janet, In the first census optical character recognition systems Conference #NISTIR 4912, The U.S. Bureau of Census and the National Institute of Standards and Technology, Gaithersburg, MD, 1992.
[17] M. Pechwitz, S. Maddouri, V. Maergner, N. Ellouze, H. Amiri, "IFN/ENIT: Database of Handwritten Arabic Words", in Proceedings of the CIFED 2002, Tunisia, pp. 129-136, 2002.
[18] http://www.iam.unibe.ch/˜fki/iamondb/
[19] S. Abdelazeem, H. Eraqi, "On-line Arabic Handwritten Personal Names Recognition System based on HMM", Proceedings of the 11th international conference on document analysis and recognition ICDAR2011, Beijing, China, pp. 1304-1308, 2011.