Skip to main content
SpringerLink
Log in

Handwritten Arabic Character Recognition: Comparison of Conventional Machine Learning and Deep Learning Approaches

  • Conference paper
  • First Online:
Innovative Systems for Intelligent Health Informatics (IRICT 2020)

Part of the book series: Lecture Notes on Data Engineering and Communications Technologies ((LNDECT,volume 72))

  • 1085 Accesses

Abstract

Over the last decades, automatic handwriting recognition has received a lot of attention, as it is a crucial component for many applications in various fields. Research for this issue has focused on handwriting recognition in Latin languages and fewer studies have been dedicated to the Arabic language. In this paper, we propose and compare two approaches to classifying Arabic characters. The first is based on conventional machine learning using the SVM classifier by comparing different sets of features, most commonly used in the pattern recognition field. The second is based on deep learning by testing different CNN (convolutional neural networks) architectures, which brings a self-characterization of Arabic features. In this context, a new fast and simplified CNN architecture is proposed. We also test different transfer learning strategies on two versions of the OIHACDB dataset and the AIA9K dataset proposed in the literature. In the experimental section, we show that the proposed CNN model achieves accuracies of 94.7%, 98.3%, and 95.2% on the test set of the three databases OIHACDB-28, OIHACDB-40, and AIA9K respectively. Our experiments enrich the tests already carried out on these datasets and show good results in comparison with the literature.

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 169.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 219.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Chaouki, B., Adlen, K., Mohamed, B.: Investigation on deep learning for off-line handwritten Arabic character recognition. Cogn. Systems Research, 50, 180–195, August 2018

    Google Scholar 

  2. Rashid, S., Schambach, M., Rottland, J., Null, S.: Low resolution Arabic recognition with multidimensional recurrent neural networks. In: 4th Proceedings of the International Workshop on Multilingual OCR, New York, p. 6 (2013)

    Google Scholar 

  3. Ait Aider, M., Hammouche, K., Gaceb, D.: Recognition of handwritten characters based on wavelet transform and SVM classifier. Int. Arab J. Inf. Technol. 15(6), 1082–1087 (2018)

    Google Scholar 

  4. Baldominos, A., Saez, Y., Isasi, P.: A survey of handwritten character recognition with mnist and emnist. Appl. Sci. 9(15), 3169 (2019). https://doi.org/10.3390/app9153169

  5. Ramzan, M., Khan, H.U., Awan, S.M., Akhtar, W., Ilyas, M., Mahmood, A., Zamir, A.: A survey on using neural network based algorithms for handwritten digit recognition. Int. J. Adv. Comput. Sci. Appl. (IJACSA) 9(9), 519–528 (2018)

    Google Scholar 

  6. Dhillon, A., Verma, G.K.: Convolutional neural network: a review of models, methodologies and applications to object detection. Prog. Artif. Intell. 9, 85–112 (2020). https://doi.org/10.1007/s13748-019-00203-0

    Article  Google Scholar 

  7. El-Sawy, A., Loey, M., Hazem, E.: Arabic handwritten characters recognition using convolutional neural network. WSEAS Tran. Comput. Res. 5(1), 11–19 (2017)

    Google Scholar 

  8. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems (NIPS), vol. 1, pp. 1097–1105. Curran Associates Inc.57 Morehouse Lane, Red Hook; NY, United States, USA (2012)

    Google Scholar 

  9. Loffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: 32nd International Conference on International Conference on Machine Learning, France, vol. 37, pp. 448–456 (2015)

    Google Scholar 

  10. Younis, K.: Arabic handwritten character recognition based on deep convolutional neural networks. Jordanian J. Comput. Inf. Technol. (JJCIT) 3(3), 186–200 (2018)

    Article  Google Scholar 

  11. Kharma N., Ahmed M., Ward R.: A new comprehensive database of handwritten Arabic words, numbers, and signatures used for OCR testing. In: IEEE Canadian Conference 1999 on Electrical and Computer Engineering, Canada, vol. 2, pp. 766–768. IEEE (1999)

    Google Scholar 

  12. Saeed, M., Karim, F., Farhad, F., Majid, Z., Mohamad, G.: A comprehensive isolated Farsi/Arabic character database for handwritten OCR research. In: 10th International Workshop on Frontiers in Handwriting Recognition. Université de Rennes 1, La Baule (France), p. 5, October 2006

    Google Scholar 

  13. Somaya, A., Dave, E., Colin, H.: A data base for Arabic handwritten text recognition research. Int. Arab J. Inf. Technol. 1, 117–121 (2004)

    Google Scholar 

  14. Huda, A., Javad, S., Ching, Y., Suen, N.: A novel comprehensive database for arabic off-line handwriting recognition. In: Computer Science and Software Engineering Department, Concordia University, 1455 de Maisonneuve Blvd. West, Montreal, Quebec, Canada, p. 6 (2008)

    Google Scholar 

  15. Mario, P., Samia, S., Volker, M., E.llouze, N., Hamid, A.: Ifn/Enit - database of handwritten arabic words. In: Francophone International Conference on writing and Document, Tunis, pp. 1–8 (2002)

    Google Scholar 

  16. Sherif, A., Ezzat, E.: Arabic handwritten digit recognition. Doc. Anal. Recogn. 11(3), 127–141 (2008)

    Article  Google Scholar 

  17. Lawgali, A., Angelova, M., Bouridane, A.: HACDB: Handwritten Arabic characters database for automatic character recognition. In: EUVIP 2013: Proceedings of the 4th European Workshop on Visual Information Processing, pp. 255–259. IEEE, Piscataway, NJ (2013)

    Google Scholar 

  18. El-Sawy, A., Loey, M., El-bakry, H.: Arabic handwritten characters recognition using convolutional neural network. WSEAS Trans. Comput. Res. 5, 11–19 (2017)

    Google Scholar 

  19. Chaouki, B., Mohamed, B., Marc, S.: An artificial immune system for offline isolated handwritten Arabic character recognition. Evolving Systems, 9, 25–41 (2018). https://doi.org/10.1007/s12530-016-9169-1 (2016)

  20. Nibaran, Das., Ayatullah, F., Sudip, S., Syed, S.: Handwritten Arabic numeral recognition using a multi-layer perceptron. In: Proceedings National Conference on Recent Trends in Information Systems, pp. 200–203 (2006)

    Google Scholar 

  21. Torki, M., Hussein, M. E., Elsallamy, A., Fayyaz, M., Yaser, S.: Window-Based Descriptors for Arabic Handwritten Alphabet Recognition: A Comparative Study on a Novel Dataset. arXiv:1411.3519 (2014)

  22. Ashiquzzaman, A., Tushar, AK.: Handwritten Arabic numeral recognition using deep learning neural networks. In: IEEE International Conference on Imaging, Vision and Pattern Recognition (2017), Bangladesh, pp. 1–4. IEEE (2017)

    Google Scholar 

  23. Zhang, N., Ding, S., Zhang, J., Xue, Y.: An overview on restricted Boltzmann Machines. Neurocomputing, 275, 1186–1199 (2018)

    Google Scholar 

  24. Alani, A.: Arabic handwritten digit recognition based on restricted Boltzmann machine and convolutional neural networks. Information 8(4), 142 (2017)

    Article  Google Scholar 

  25. Latif, G., Alghazo, J., Alzubaidi, L., Naseer, MM., Alghazo, Y.: Deep convolutional neural network for recognition of unified multi-language handwritten numerals. In: 2nd IEEE International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR), London, pp. 90–95. IEEE (2018)

    Google Scholar 

  26. Ashiquzzaman, A., Tushar, AK., Rahman, A., Mohsin, F.: An efficient recognition method for handwritten Arabic numerals using CNN with data augmentation and dropout. In: Balas, V.E., Sharma, N., Chakrabarti, A., (eds) Data management, analytics and innovation, advances in intelligent systems and computing, pp. 299–30914. Springer, Singapore (2019)

    Google Scholar 

  27. Miled, H., Olivier, C., Cheriet, M., Romeo-Pakker, K.: Une Méthode Rapide de Reconnaissance de l’Écriture Arabe Manuscrite. 16th GRETSI colloquium, Grenoble, pp. 857–860 (1997)

    Google Scholar 

  28. Mars, A., Antoniadis G.: Arabic online handwriting recognition using neural network. Int. J. Artifi. Intell. Appl. (IJAIA), 7(5), September 2016

    Google Scholar 

  29. Maalej, R., Kherallah, M.: Convolutional Neural network and BLSTM for offline Arabic handwriting recognition. In: International Arab Conference on Information Technology (ACIT) 2018, Werdanye, Lebanon, pp. 1–6 (2018)

    Google Scholar 

  30. Alaasam, R., Kurar B., Kassis M., El-Sana J.: Experiment study on utilizing convolutional neural networks to recognize historical Arabic handwritten text. In: 1st International Workshop on Arabic script analysis and recognition (ASAR), Nancy, France, pp. 124–128. (2017)

    Google Scholar 

  31. Mudhsh, M.A., Almodfer, R.: Arabic handwritten alphanumeric character recognition us very deep neural network. Information 8(3), 105 (2017)

    Article  Google Scholar 

  32. Khayyat, M., Elrefaei, L.: A deep learning based prediction of arabic manuscripts handwriting style. Int. Arab J. Inf. Technol. 17(5), 1–10 (2020)

    Google Scholar 

  33. Sidheswar, R., Arun, K., Chandrabhanu, M.: Analysis of various image feature extraction methods against noisy image: SIFT, SURF and HOG. In: 2nd International Conference on Electrical, Computer and Communication Technologies (ICECCT), India, pp. 1–5 (2017)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Laboratory of Computer Science, Modeling, Optimization, and Electronic Systems (LIMOSE) FS, M’Hamed, Bouguerra University of Boumerdès, Boumerdès, Algeria

    Faouci Soumia & Gaceb Djamel

  2. Lab LIRIS, UMR CNRS 5205, University of Claude Bernard Lyon 1, 69622, Villeurbanne, France

    Mohammed Haddad

Authors
  1. Faouci Soumia
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Gaceb Djamel
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mohammed Haddad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Faouci Soumia .

Editor information

Editors and Affiliations

  1. College of Computer Science and Engineering, Taibah University, Medina, Saudi Arabia

    Faisal Saeed

  2. School of Computing, Information Systems Department, Universiti Utara Malaysia, Sintok, Malaysia

    Fathey Mohammed

  3. Sanaa’a Community College, Sana'a, Yemen

    Abdulaziz Al-Nahari

Rights and permissions

Reprints and permissions

Copyright information

© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Soumia, F., Djamel, G., Haddad, M. (2021). Handwritten Arabic Character Recognition: Comparison of Conventional Machine Learning and Deep Learning Approaches. In: Saeed, F., Mohammed, F., Al-Nahari, A. (eds) Innovative Systems for Intelligent Health Informatics. IRICT 2020. Lecture Notes on Data Engineering and Communications Technologies, vol 72. Springer, Cham. https://doi.org/10.1007/978-3-030-70713-2_100

Download citation

Publish with us

Policies and ethics

Search

Navigation