Skip to main content
SpringerLink
Log in

A Spell Correction Model for OCR Errors for Arabic Text

  • Conference paper
  • First Online:
Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016 (AISI 2016)

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 533))

  • 2531 Accesses

Abstract

This paper presents a new correction model for Arabic OCR errors. The proposed model is mainly based on the character segmentation and the character alignment on a single character or multi-characters. Results show that the multi-character model is better than the single character model in that it is trained on 502,167 words and can find the correct word within the top 10 proposed corrections for 94 % of the words. This model considers the effect of increasing the size of training set that perfectly leads to better results; the correction rate will approach 53 % upon using 6000 words, 80 % upon using 64,225 words, and 94 % upon using 502,167 words.

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

Notes

  1. 1.

    Available at: https://sourceforge.net/projects/arabic-wordlist/.

References

  1. Nazif, A.: A System for the Recognition of the Printed Arabic Characters. M.Sc. Thesis. Cairo University, Faculty of Engineering, Egypt (1975)

    Google Scholar 

  2. Habash, N., Roth, R.M.: Using deep morphology to improve automatic error detection in arabic handwriting recognition. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, Human Language Technologies, vol. 1, pp. 875–884 (2011)

    Google Scholar 

  3. Mahdi, A.: Spell Checking and Correction for Arabic Text Recognition. M.Sc. Thesis. King Fahd University of Petroleum And Minerals, Saudi Arabia (2012)

    Google Scholar 

  4. Kukich, K.: Techniques for automatically correcting words in text. ACM Comput. Surv. 24, 377–439 (1992)

    Article  Google Scholar 

  5. Muhammad, M., ElGhazaly, T.: Handling OCR-degraded arabic text: a comprehensive survey. In: Proceedings of the 48th annual ISSR conference, Institute of Statistical Studies and Research, Cairo University, Egypt (2013)

    Google Scholar 

  6. Magdy, W., Darwish, K.: Omni font OCR error correction with effect on retrieval. In: Intelligent Systems Design and Applications (ISDA), pp. 415–420 (2010)

    Google Scholar 

  7. Magdy, W., Darwish, K.: Arabic OCR error correction using character segment correction, language modeling, and shallow morphology. In: Proceedings of 2006 Conference on Empirical Methods in Natural Language Processing (EMNLP 2006), Sydney, Australia, pp. 408–414 (2006)

    Google Scholar 

  8. Kanungo, T., Marton, G.A., Bulbul, O.: OmniPage vs. Sakhr: paired model evaluation of two arabic OCR products. In: Proceedings of SPIE Conference on Document Recognition and Retrieval (1999)

    Google Scholar 

  9. Ezzat, M., ElGhazaly, T., Gheith, M.: An enhanced arabic OCR degraded text retrieval model. In: Castro, F., Gelbukh, A., González, M. (eds.) MICAI 2013. LNCS (LNAI), vol. 8265, pp. 380–393. Springer, Heidelberg (2013). doi:10.1007/978-3-642-45114-0_31

    Chapter  Google Scholar 

  10. Church, K., Gale, W.: Probability scoring for spelling correction. Stat. Comput. 1, 93–103 (1991)

    Article  Google Scholar 

  11. Brill, E., Moore, R.: An improved error model for noisy channel spelling correction. In: Proceedings of the 38th Annual Meeting of Association for Computational Linguistics, pp. 286–293 (2000)

    Google Scholar 

  12. Attia, M., Pavel, P., Younes, S., Shaalan, K., Josef, v., G.: Improved spelling error detection and correction for arabic. In: COLING 2012, Mumbai, India (2012)

    Google Scholar 

  13. Olshausen, B.A.: Bayesian Probability Theory. The Redwood Center for Theoretical Neuroscience, Helen Wills Neuroscience Institute at the University of California at Berkeley, Berkeley, CA (2004)

    Google Scholar 

  14. Elghazaly, T.: Improving OCR-degraded arabic text retrieval through an enhanced orthographic query expansion model. In: Tan, Y., Shi, Y., Buarque, F., Gelbukh, A., Das, S., Engelbrecht, A. (eds.) ICSI 2015. LNCS, vol. 9141, pp. 117–124. Springer, Heidelberg (2015). doi:10.1007/978-3-319-20472-7_13

    Chapter  Google Scholar 

  15. Levenshtein, V.: Binary codes capable of correcting deletions, insertions, and reversals. Sov. Phys. Dokl. 10, 707 (1966)

    MathSciNet  MATH  Google Scholar 

  16. Mohit, B., Rozovskaya, A., Habash, N., Zaghouani, W., Obeid, O.: The first QALB shared task on automatic text correction for arabic. In: Proceedings of EMNLP 2014 Workshop on Arabic Natural Language (2014)

    Google Scholar 

  17. Muaidi, H., Al-Tarawneh, R.: Towards arabic spell-checker based on N-grams scores. Int. J. Comput. Appl. 53(3), 12–16 (2012)

    Google Scholar 

  18. Ng, H.T., Wu, S.M., Wu, Y.,: Hadiwinoto, C., Tetreault, J.: The CoNLL-2013 shared task on grammatical error correction. In: Proceedings of CoNLL-2013 Shared Task (2013)

    Google Scholar 

  19. Rozovskaya, A., Habash, N., Eskander, R., Farra, N., Salloum, W.: The columbia system in the QALB-2014 shared task on arabic error correction. In: Proceedings of EMNLP 2014 Workshop on Arabic Natural Language (2014)

    Google Scholar 

  20. Zobel, J., Box, G., Dart, P.: Phonetic string matching: lessons from information retrieval. In: Proceedings of SIGIR-96, the 19th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (1996)

    Google Scholar 

  21. Riseman, E., Hanson, A.: A contextual post processing system for error correction using binary n-grams. IEEE Trans. Comput. 23(5), 480–493 (1974)

    Article  Google Scholar 

  22. Islam, A., Inkpen, D.: Real-word spelling correction using google web IT 3-grams. In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, 3(August), pp. 1241–1249 (2009)

    Google Scholar 

  23. Kemighan, M., Church, K., Gale, W.: A spelling correction program based on a noisy channel model. In: Proceedings of the 13th conference on Computational linguistics, vol. 2, pp. 205–210 (1990)

    Google Scholar 

  24. Yannakoudakis, E., Fawthro, D.: The rules of spelling errors. Inf. Process. Manage. 19(2), 87–99 (1983)

    Article  Google Scholar 

  25. Shaalan, K., Allam, A., Gohah, A.: Towards automatic spell checking for arabic. In: Proceedings of the Conference on Language Engineering (ELSE), pp. 240–247 (2003)

    Google Scholar 

  26. Alkanhal, M.I., Al-Badrashiny, M.A., Alghamdi, M.M., Al-Qabbany, A.O.: Automatic stochastic arabic spelling correction with emphasis on space insertions and deletions. In: Proceeding of IEEE Transactions on Audio, Speech, and Language Processing, vol. 20, no. 7 (2012)

    Google Scholar 

  27. Haddad, B., Mustafa, Y.: Detection and correction of non-words in arabic: a hybrid approach. Int. J. Comput. Process. Orient. Lang. 20(4), 237–257 (2007)

    Article  Google Scholar 

  28. Hassan, Y., Aly, M., Atiya, A.: Arabic spelling correction using supervised learning. In: Proceedings of EMNLP 2014 Workshop on Arabic Natural Language (2014)

    Google Scholar 

  29. Kanungo, T., Marton, G.A., Bulbul, O.: OmniPage vs. Sakhr: paired model evaluation of two arabic OCR products. In: International Society for Optics and Photonics, pp. 109–120 (1999)

    Google Scholar 

Download references

Acknowledgements

The authors are grateful to the referees for their careful reading, insightful comments and helpful suggestions which have led to improvement in the paper.

Author information

Authors and Affiliations

  1. Computer Sciences Department, Institute of Statistical Studies and Research, Cairo University, Giza, Egypt

    Mariam Muhammad, Tarek ELGhazaly, Mostafa Ezzat & Mervat Gheith

Authors
  1. Mariam Muhammad
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tarek ELGhazaly
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mostafa Ezzat
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Mervat Gheith
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mariam Muhammad .

Editor information

Editors and Affiliations

  1. Faculty of Computers & Information, Cairo University, Giza, Egypt

    Aboul Ella Hassanien

  2. Dubai International Academic City, The British University, Dubai, United Arab Emirates

    Khaled Shaalan

  3. CS Dept. Faculty of Computers and Inform, Suez Canal University CS Dept. Faculty of Computers and Inform, Ismailia, Egypt

    Tarek Gaber

  4. Ahmed Orabi Square , Menouf, Egypt

    Ahmad Taher Azar

  5. Faculty of Computer & Information Scienc, Ain Shams University Faculty of Computer & Information Scienc, Cairo, Egypt

    M. F. Tolba

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing AG

About this paper

Cite this paper

Muhammad, M., ELGhazaly, T., Ezzat, M., Gheith, M. (2017). A Spell Correction Model for OCR Errors for Arabic Text. In: Hassanien, A., Shaalan, K., Gaber, T., Azar, A., Tolba, M. (eds) Proceedings of the International Conference on Advanced Intelligent Systems and Informatics 2016. AISI 2016. Advances in Intelligent Systems and Computing, vol 533. Springer, Cham. https://doi.org/10.1007/978-3-319-48308-5_13

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-48308-5_13

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-48307-8

  • Online ISBN: 978-3-319-48308-5

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation