[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Evaluation of cursive and non-cursive scripts using recurrent neural networks

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Character recognition has been widely used since its inception in applications involved processing of scanned or camera-captured documents. There exist multiple scripts in which the languages are written. The scripts could broadly be divided into cursive and non-cursive scripts. The recurrent neural networks have been proved to obtain state-of-the-art results for optical character recognition. We present a thorough investigation of the performance of recurrent neural network (RNN) for cursive and non-cursive scripts. We employ bidirectional long short-term memory (BLSTM) networks, which is a variant of the standard RNN. The output layer of the architecture used to carry out our investigation is a special layer called connectionist temporal classification (CTC) which does the sequence alignment. The CTC layer takes as an input the activations of LSTM and aligns the target labels with the inputs. The results were obtained at the character level for both cursive Urdu and non-cursive English scripts are significant and suggest that the BLSTM technique is potentially more useful than the existing OCR algorithms.

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
£29.99 /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 includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Wang Y, Ding X, Liu C (2011) MQDF discriminative learning based offline handwritten chinese character recognition. In: ICDAR, IEEE, pp 1100–1104

  2. Tonouchi Y (2010) Path evaluation and character classifier training on integrated segmentation and recognition of online handwritten Japanese character string. In: ICFHR, IEEE Computer Society, pp 513–517

  3. Razzak MI, Hussain SA (2010) Locally baseline detection for online Arabic script based languages character recognition. International Journal of the Physical Sciences 5:955–959

    Google Scholar 

  4. Biadsy F, El-Sana J, Habash N (2006) Online Arabic handwriting recognition using hidden markov models in computer vision and pattern recognition, http://hal.archives-ouvertes.fr/docs/00/10/83/06/PDF/cr102362277910.pdf

  5. Rashid SF, Shafait F, Breuel TM (2012) Scanning neural network for text line recognition. In: Blumenstein M, Pal U, Uchida S (eds) Document analysis systems. IEEE, New Jersey, pp 105–109

    Google Scholar 

  6. Taghva K, Nartker T, Borsack J, Condit A (2000) UNLV-ISRI document collection for research in OCR and information retrieval. SPIE—The International Society for Optical Engineering, pp 157–164

  7. Azmi AN, Nasien D, Shamsuddin SM (2013) A review on handwritten character and numeral recognition for Roman, Arabic, Chinese and Indian scripts. CoRR abs/1308.4902

  8. Camastra F (2008) A SVM Greek character recognizer. IJIDSS 1:290–299

    Article  Google Scholar 

  9. Syal S, Sood E, Sharma S, Randhawa EN (2013) Segmented character recognition using neural networks. Int J Eng Res Appl (IJERA) 1:1731–1735

    Google Scholar 

  10. Camastra F (2007) A SVM-based cursive character recognizer. Pattern Recogn 40:3721–3727

    Article  MATH  Google Scholar 

  11. Nagata M (1998) Japanese OCR error correction using character shape similarity and statistical language model. In: Boitet C, Whitelock P (eds) ACL/COLING. Morgan Kaufmann Publishers/ACL, San Francisco, pp 922–928

    Google Scholar 

  12. Pathan IK, Ali AB, Ramteke RJ (2012) Recognition of offline handwritten isolated Urdu character. Advances in Computational Research 4:117–121

    Google Scholar 

  13. Graves A (2012) Supervised sequence labelling with recurrent neural networks, Studies in computational intelligence, vol 385. Springer, Heidelberg, pp 1–131

    MATH  Google Scholar 

  14. Schuster M, Paliwal KK (1997) Bidirectional recurrent neural networks. IEEE Trans Signal Process 45:2673–2681

    Article  Google Scholar 

  15. Graves A, Schmidhuber J (2005) Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw 18(5–6):602–610

    Article  Google Scholar 

  16. Danilo P, Mandic JA Chambers (2001) Recurrent neural network for prediction. Wiley, New York

    MATH  Google Scholar 

  17. Hochreiter S, Schmidhuber J (1997) Long short term memory. Neural Comput 9:1735–1780

    Article  Google Scholar 

  18. Gers FA, Schmidhuber E (2001) LSTM recurrent networks learn simple context-free and context-sensitive languages. IEEE-EC 12:1333–1340

    Google Scholar 

  19. Fernández S, Graves A, Schmidhuber J (2007) Sequence labelling in structured domains with hierarchical recurrent neural networks. IJCAI, Hyderabad, India, pp 774–779

    Google Scholar 

  20. Ahmed SB, Naz S, Salahuddin (2015) UCOM offline dataset—a Urdu handwritten dataset generation. Int Arab J Inf Technol (IAJIT) (still to be published)

  21. Graves A, Fernández S, Liwicki M, Bunke H, Schmidhuber J (2007) Unconstrained online handwriting recognition with recurrent neural networks. NIPS, Vancouver, Canada

    Google Scholar 

  22. Smith R (2007) An overview of the tesseract OCR engine. In: ICDAR, pp 629–633

  23. Breuel TM (2008) The OCRopus open source OCR system. In: Yanikoglu BA, Berkner K (eds) DRR. SPIE, volume 6815 of SPIE proceedings, p 68150. doi:10.1117/12.783598

  24. Naz S, Hayat K, Razzak MI, Anwar MW, Akbar H (2013) Challenges in baseline detection of cursive script languages. In: Science and information conference (SAI), pp 551–556

  25. Naz S, Hayat K, Razzak MI, Anwar MW, Akbar H (2013) Arabic script based language character recognition: Nasta’liq vs Naskh analysis. In: Proceeding of IEEE World Congress on in Computer and Information Technology (WCCIT), pp 1–7

  26. http://kics.edu.pk. Accessed 27 May 2014

  27. http://crulp.org. Accessed 13 June 2014

  28. http://jang.com.pk. Accessed 02 May 2013

  29. Ul-Hasan A, Bin Ahmed S, Rashid SF, Shafait F, Breuel TM (2013) Offline printed Urdu Nastaleeq script recognition with bidirectional LSTM networks. In: Proceedings IEEE “2013”, International Conference on Document Analysis and Recognition (ICDAR)

  30. Ahmed SB, Naz S, Salahuddin, Razzak MI, Umar AI (2015) Handwritten Urdu character recognition using recurrent neural networks. Neural Comput Appl (NCA) (under reviewed)

  31. AlKhateeb JH (2011) Word-based handwritten Arabic scripts recognition using dynamic Bayesian network, 2011. In: The 5th international conference on information technology, Faculty of Science and Information Technology, AlZaytoonah University of Jordan Ammnan Jordan

  32. Sabbour N 1, Shafait F (2013) A segmentation free approach to Arabic and Urdu OCR. In 20th Document recognition and retrieval conference, 2013, Department of Computer Science, German University in Cairo (GUC), Cairo; German Research Center for Artificial Intelligence (DFKI), Kaiserslautern

Download references

Author information

Authors and Affiliations

  1. King Saud Bin Abdulaziz University for Health Sciences, Riyadh, Saudi Arabia

    Saad Bin Ahmed & Muhammad Imran Razzak

  2. Department of Information Technology, Hazara University, Mansehra, Pakistan

    Saeeda Naz

  3. Higher Education Department, KPK, Abbottabad, Pakistan

    Saeeda Naz

  4. University of Technology, Kaiserslautern, Germany

    Shiekh Faisal Rashid, Muhammad Zeeshan Afzal & Thomas M. Breuel

Authors
  1. Saad Bin Ahmed
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Saeeda Naz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Muhammad Imran Razzak
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shiekh Faisal Rashid
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Muhammad Zeeshan Afzal
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Thomas M. Breuel
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Muhammad Imran Razzak.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ahmed, S.B., Naz, S., Razzak, M.I. et al. Evaluation of cursive and non-cursive scripts using recurrent neural networks. Neural Comput & Applic 27, 603–613 (2016). https://doi.org/10.1007/s00521-015-1881-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-015-1881-4

Keywords

Search

Navigation