Research Article

Recognition of Multifont Isolated Arabic Characters by B´ezier Curves

by  A. Mazroui, A. Kerkour Elmiad
journal cover
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 100 - Issue 6
Published: August 2014
Authors: A. Mazroui, A. Kerkour Elmiad
10.5120/17526-8101
PDF

A. Mazroui, A. Kerkour Elmiad . Recognition of Multifont Isolated Arabic Characters by B´ezier Curves. International Journal of Computer Applications. 100, 6 (August 2014), 1-7. DOI=10.5120/17526-8101

                        @article{ 10.5120/17526-8101,
                        author  = { A. Mazroui,A. Kerkour Elmiad },
                        title   = { Recognition of Multifont Isolated Arabic Characters by B´ezier Curves },
                        journal = { International Journal of Computer Applications },
                        year    = { 2014 },
                        volume  = { 100 },
                        number  = { 6 },
                        pages   = { 1-7 },
                        doi     = { 10.5120/17526-8101 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2014
                        %A A. Mazroui
                        %A A. Kerkour Elmiad
                        %T Recognition of Multifont Isolated Arabic Characters by B´ezier Curves%T 
                        %J International Journal of Computer Applications
                        %V 100
                        %N 6
                        %P 1-7
                        %R 10.5120/17526-8101
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

The recognition of Arabic characters is still a major challenge to overcome. In this paper, we propose a new approach in the field of recognition of multifont isolated Arabic characters. It is based on the semi-cursive nature of Arabic characters and consists in assimilating them to a small number of checkpoints equipped with their derivatives. The choice of this approach is motivated by the interesting properties of B´ezier curves that allow drawing parametric curves from a limited number of dots equipped with their tangents. The results achieved are very interesting and relate to character recognition derived from a large number of fonts (23 fonts).

References
  • A. M. AL-Shatnawi, S. AL-Salaimeh, F. H. AL-Zawaideh, and O. Khairuddin. Offline arabic text recognition-an overview. World of Computer Science and Information Technology Journal (WCSIT), 5(1):184–192, 2011.
  • J. H. AlKhateeb, J. Ren, J. Jiang, and H. Al-Muhtaseb. Offline handwritten arabic cursive text recognition using hidden markov models and re-ranking. Pattern Recognition Letters, (32):1081–1088, 2011.
  • D. Arrivault. Apport des Graphes dans la Reconnaissance Non-Contrainte de Caractres Manuscrits Anciens. PhD thesis, Universit de Poitiers, 2006.
  • S. Bahgat, S. Ghomiemy, S. Aljahdali, and M. Alotaibi. A proposed hybrid technique for recognizing arabic characters. International Journal of Advanced Research in Artificial Intelligence, 4(1):35–43, 2012.
  • N. Ben Amor and N. Essoukri. Multifont arabic character recognition using hough transform and hmm/ann. Journal of Multimedia, 2(1):50–54, 2012.
  • T. S. Elsheich and R. M. Guindi. Automatic recognition of isolated arabic characters. Signal Processing, 14(2):177–184, 1980.
  • G. Farin and P Massart. Curves and Surfaces for Computer Aided Geometric Design, volume 3368/2005. Academic Press - San Diego, 1983.
  • A. Hassin, X. Tang, J. Liu, and W. Zhao. Printed arabic character recognition using hmm. J. Comput. Sci. Technol, 19(4):538–543, 1980.
  • A. A. -M. Husni, A. M. Sabri, and S. Q. Rami. Recognition of off-line printed arabic text using hidden markov models. Signal Processin, 12(88):2902–2912, 2008.
  • H. Izakian, S. A. Monadjemi, B. Tork Ladani, and K. Zamanifar. Multi-font farsi/arabic isolated character recognition using chain codes. World Academy of Science, Engineering and Technology, 43:67–70, 2008.
  • A. Kacem, A. Belad, and M. Ben Ahmed. Automatic extraction of printed mathematical formulas using fuzzy logic and propagation of context. International Journal on Document Analysis and Recognition, 2(4):97–108, 2001.
  • L. M. Lorigo and V. Govindaraju. Offline arabic handwriting recognition: A survey. IEEE Trans. Pattern Anal. Machine Intell, 28:712–724, 2006.
  • A. Mesleh, A. Sharadqh, A. Al-Azzeh, J. Abu-Zaher, M. Al- Zabin, N. Jaber, Odeh, and T. Hasn. Offline arabic handwriting recognition: A survey. Contemporary Engineering Sciences, 11(5):521–529, 2012.
  • N. Mezghani, A. Mitiche, and A. Cheriet. Bayes classification of online arabic characters by gibbs modeling of class conditional densities. IEEE Transactions on Pattern Analysis and Machine Intelligence, 30(7):1121–1131, 2008.
  • M. Oujaoura, R. El Ayachi, M. Fakir, Bouikhalene B. , and B. Minaoui. Zernike moments and neural networks for recognition of isolated arabic characters. International Journal of Computer Engineering Science, 3(2):17–25, 2012.
  • I. K. Pathan, A. A. Ali, and R. J. Ramteke. Recognition of offline handwritten isolated urdu character. Advances in Computational Research- Intl. Journal, 1(4):117–121, 2012.
  • R. Prasad, A. Bhardwaj, K. Subramanian, H. Cao, and P. Natarajan. Stochastic segment model adaptation for offline handwriting recognition. In In: Proc. Internet. Conf. Pattern Recognition, pages 1993–1996, 2010.
  • I. Zavorin, E. Borovikov, E. Davis, and A. Borovikov. Combining different classification approaches to improve off-line arabic handwritten word recognition. In Proc. of SPIE 6815 (681504), 2008.
  • Y. Y. Zhang and P. S. P. Wang. A new parallel thinning methodology. International Journal of Pattern Recognition and Artificial Intelligence, (8):999–1011, 1994.
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

Recognition Multifont

Powered by PhDFocusTM