Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Hybrid Feature Vector for the Recognition of Arabic Handwritten Characters Using Feed-Forward Neural Network

  • Research Article - Computer Engineering and Computer Science
  • Published:
Arabian Journal for Science and Engineering Aims and scope Submit manuscript

    We’re sorry, something doesn't seem to be working properly.

    Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

Abstract

Character recognition is one of the most successful applications of artificial neural network methods. However, most of the work has been dedicated to the recognition of Latin handwritten characters, and only few studies have been devoted to the recognition of Arabic handwritten characters. This paper presents an off-line recognition system for Arabic handwritten characters. In this context, we use 66 statistical, structural, and regional characteristics extracted using five methods. These characteristics are treated by a feed-forward neural network with a hidden layer. To this end, we use our database for Arabic handwritten characters and ligatures (DBAHCL) in the learning, test and validation phases. The accuracy generated by our system is about 98.27%.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Guillaud, H.: Notre cerveau à l’heure des nouvelles lectures, http://internetactu.blog.lemonde.fr/2013/01/11/notre-cerveau-a-lheure-des-nouvelles-lectures/. Accessed 11 January (2013)

  2. Dehaene, S.: Les neurones de la lecture, A Book. Editions Odile Jacob, Paris (2007)

    Google Scholar 

  3. Menasri, F.: Contributions à la reconnaissance de l’écriture arabe manuscrite, Ph.D. thesis, Paris Descartes University (2008)

  4. Lorigo, L.M.; Govindaraju, V.: Offline Arabic handwriting recognition: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 28(5), 712–724 (2006)

    Article  Google Scholar 

  5. Alaei, A.; Pal, U.; Nagabhushan, P.: Dataset and ground truth for handwritten text in four different scripts. Int. J. Pattern Recognit. Artif. Intell. 26(04), 1253001 (2012)

    Article  MathSciNet  Google Scholar 

  6. Chergui, L.: Combinaison de classifieurs pour la reconnaissance de mots arabes manuscrits, Ph.D. Thesis, Mentouri Constantine University (2012)

  7. Lamghari, N.; Charaf, M.E.H.; Raghay, S.: A feature extraction method for handwritten arabic characters. In: Proceeding of Computer Science, Optimization and Systems Modelization (CSOSM’15), Kenitra, Morocco (2015)

  8. Lamghari, N.; Charaf, M.E.H.; Raghay, S.: Reconnaissance des caractères manuscrits arabes: une méthode de test de similarité. In: International Francophone Conference AAFD & SFC (2016)

  9. Märgner, V.; Haikal, E.: Guide to OCR for Arabic Scripts. SpringerLink: Bücher, New York (2012). https://doi.org/10.1007/978-1-4471-4072-6

    Google Scholar 

  10. Cheriet, M.; Kharma, N.; Liu, C.L.; Suen, C.Y.: Character Recognition Systems: A Guide for Students and Practioners. Wiley, Hoboken (2007)

    Book  Google Scholar 

  11. Amor, N.B.; Amara, N.E.B.: Combining a hybrid approach for features selection and hidden Markov models in multifont arabic characters recognition. In: IEEE Second International Conference on Document Image Analysis for Libraries (DIAL’06) 07695-2531-8/06, (2006)

  12. Bouchon-Meunier, B.; Marsala, C. (eds.): Logique Floue. Principes, Aide à la Décision. Hermès-Lavoisier, Paris (2003)

    Google Scholar 

  13. Benouareth, A.; Ennaji, A.; Sellami, M.: HMMs with explicit state duration applied to handwritten Arabic word recognition. In: International Conference on Pattern Recognition, IEEE (ICPR’06) 0-7695-2521-0/06 (2006)

  14. Elbaati, A.; Boubaker, H.; Kherallah, M.; Alimi, A.M.: Arabic handwriting recognition using restored stroke chronology. In: 10th International Conference on Document Analysis and Recognition (2009)

  15. Abed, M.A.; Abed, H.A.A.L.; Al-Deen, Z.B.; Ismail, A.N.: Fuzzy logic approach to recognition of isolated Arabic characters (2010)

  16. Zawaideh, F. H.: Arabic hand written character recognition using modified multi-neural network. J. Emerg. Trends Comput. Inf. Sci., 3:1021–1026, ISSN 2079–8407 (2012).

  17. Al Hamad, H.A.: Use an efficient neural network to improve the Arabic handwriting recognition. In: International Conference on Systems, Control, Signal Processing and Informatics (2013)

  18. Lawgali, A.: Handwritten digit recognition based on DWT and DCT. Int. J. Database Theory Appl. 8(5), 215–222 (2015)

    Article  Google Scholar 

  19. Elanwar, R.I.M.; Rashwan, M.A.A.; Mashali, S.: A multiple classifiers system for solving the character recognition problem in Arabic alphabet. In: Conference Paper (2006)

  20. Abandah, G.; Anssari, N.: Novel moment features extraction for recognizing handwritten Arabic letters. J. Comput. Sci. 5(3), 226 (2009)

    Article  Google Scholar 

  21. Lamghari, N.; Charaf, M.E.H.; Raghay, S.: Template matching for recognition of handwritten Arabic characters using structural characteristics and Freeman code. Int. J. Comput. Sci. Inf. Secur. 14(12), 31 (2016)

    Google Scholar 

  22. Hu, M.K.: Visual pattern recognition by moment invariant. IRE Trans. Inf. Theory 8, 179–187 (1962)

    MATH  Google Scholar 

  23. Ramteke, R.J.; Borkar, P.D.; Mehrotra, S.C.: Recognition of isolated handwritten numerals: an invariant moment approach. In: International Conference on Cognition and Recognition (ICCR 2005), Mysore, (Karnataka), India on 22nd–23rd Dec. (2005)

  24. Ming-Kuei, H.: Visual pattern recognition by moment invariants. IRE Trans. Inf. Theory 8, 179–187 (1962)

    Article  Google Scholar 

  25. https://www.mathworks.com/help/images/ref/regionprops.html

  26. Mars, A.; Antoniadis, G.: Arabic online handwriting recognition using neural network. Int. J. Artif. Intell. Appl. (IJAIA), 7(5), 51–59 (2016)

    Article  Google Scholar 

  27. Zhang, G.P.: Neural networks for classification: a survey. IEEE Trans. Syst. Man Cybern. Part C 30(4), 641–662 (2000)

    Article  Google Scholar 

  28. Sheela, K.G.; Deepa, S.N.: Review on Methods to Fix Number of Hidden Neurons in Neural Networks. Hindawi Publishing Corporation Mathematical Problems in Engineering, Cairo (2013). https://doi.org/10.1155/2013/425740

    Article  Google Scholar 

  29. Rady, H.: Reyni’s entropy and mean square error for improving the convergence of multilayer backprobagation neural networks: a comparative study. Int. J. Electr. Comput. Sci. IJECS-IJENS, 11(05) 68–79 (2011)

  30. Lamghari, N.; Raghay, S.: DBAHCL: Database for Arabic handwritten characters and ligatures. Int. J. Multimed Inf. Retr. https://doi.org/10.1007/s13735-017-0127-x

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. FSTG, LAMAI / Cadi Ayyad University, Marrakesh, Morocco

    N. Lamghari & S. Raghay

  2. Faculty of sciences, ISO-LAB/Ibn Tofail University, Kenitra, Morocco

    M. E. H. Charaf

Authors
  1. N. Lamghari
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. E. H. Charaf
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. S. Raghay
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to N. Lamghari.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lamghari, N., Charaf, M.E.H. & Raghay, S. Hybrid Feature Vector for the Recognition of Arabic Handwritten Characters Using Feed-Forward Neural Network. Arab J Sci Eng 43, 7031–7039 (2018). https://doi.org/10.1007/s13369-017-2969-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13369-017-2969-1

Keywords

Search

Navigation