Advertisement

Neural Computing and Applications

, Volume 31, Issue 4, pp 1143–1151 | Cite as

Handwritten Urdu character recognition using one-dimensional BLSTM classifier

  • Saad Bin Ahmed
  • Saeeda Naz
  • Salahuddin Swati
  • Muhammad Imran RazzakEmail author
Original Article

Abstract

The recognition of cursive script is regarded as a subtle task in optical character recognition due to its varied representation. Every cursive script has different nature and associated challenges. As Urdu is one of cursive language that is derived from Arabic script, that is why it nearly shares the similar challenges and complexities but with more intensity. We can categorize Urdu and Arabic language on basis of its script they use. Urdu is mostly written in Nasta’liq style, whereas Arabic follows Naskh style of writing. This paper presents new and comprehensive Urdu handwritten offline database name Urdu-Nasta’liq handwritten dataset (UNHD). Currently, there is no standard and comprehensive Urdu handwritten dataset available publicly for researchers. The acquired dataset covers commonly used ligatures that were written by 500 writers with their natural handwriting on A4 size paper. UNHD is publically available and can be download form https://sites.google.com/site/researchonurdulanguage1/databases. We performed experiments using recurrent neural networks and reported a significant accuracy for handwritten Urdu character recognition.

Keywords

Recurrent neural networks Optical character recognition Cursive offline handwriting 

Notes

Compliance with ethical standards

Conflict of interest

Authors have no conflict of interest to declare.

References

  1. 1.
    Biadsy F, El-Sana J, Habash NY (2006) Online Arabic handwriting recognition using hidden Markov models. In: Proceedings of the 10th international workshop on frontiers of handwriting and recognitionGoogle Scholar
  2. 2.
    Breuel TM (2008) The OCRopus open source OCR system. In: Yanikoglu BA, Berkner K (eds) Document Recognition and Retrieval XV, vol 6815. SPIE, San Jose, CA, p 68150. doi: 10.1117/12.783598
  3. 3.
    Deng L (2012) The MNIST database of handwritten digit images for machine learning. IEEE Signal Process Mag 29(6):141–147CrossRefGoogle Scholar
  4. 4.
    Essoukri N, Amara B, Mazhoud O, Bouzrara N, Ellouze N (2005) ARABASE: a relational database for Arabic OCR systems. Int Arab J Inf Technol 2(4):259–266Google Scholar
  5. 5.
    Graves A (2012) Supervised sequence labeling with recurrent neural networks, vol 385. Springer Studies in Computational IntelligenceGoogle Scholar
  6. 6.
    Gosselin B (1996) Multilayer perceptrons combination applied to handwritten character recognition. Neural Process Lett 3(1):3CrossRefGoogle Scholar
  7. 7.
    Razzak MI, Hussain SA (2010) Locally baseline detection for online Arabic script based languages character recognition. Int J Phys Sci 5:955Google Scholar
  8. 8.
    Sabbour N, Shafait F (2013) A segmentation free approach to Arabic and Urdu OCR. In: DRR, ser. SPIE Proceedings 8658Google Scholar
  9. 9.
    Marti U-V, Horst Bunke H (2004) The IAM-database: an English sentence database for offline handwriting recognition. IJDAR 5(1):39CrossRefzbMATHGoogle Scholar
  10. 10.
    Taghva K, Nartker T, Borsack J, Condit A (1999) UNLV-ISRI document collection for research in OCR and information retrieval. In: International society for optics and photonics in electronic imagingGoogle Scholar
  11. 11.
    Javed ST, Hussain S (2013) Segmentation based Urdu Nastalique OCR. Springer 8259:41Google Scholar
  12. 12.
    Naz S, Hayat K, Razzak MI, Anwar MW, Madani SA, Khan SU (2014) The optical character recognition of Urdu-like cursive scripts. Pattern Recognit 47(3):12291248CrossRefGoogle Scholar
  13. 13.
    Naz S, Hayat K, Razzak MI, Anwar MW, Khan SK (2014) Challenges in baseline detection of Arabic script based languages. Springer International Publishing in Intelligent Systems for Science and Information, p 181Google Scholar
  14. 14.
    Parvez MT, Mahmoud SA (2013) Offline Arabic handwritten text recognition: a survey. ACM Comput Surveys (CSUR) 45(2):23CrossRefzbMATHGoogle Scholar
  15. 15.
    Smith R (2007) An overview of the tesseract OCR engine. In: ICDAR 629Google Scholar
  16. 16.
    Lorigo LM, Govindaraju V (2006) Offline Arabic handwriting recognition: a survey. IEEE Trans Pattern Anal Mach Intell 28(5):712CrossRefGoogle Scholar
  17. 17.
    Marti U-V, Bunke H (2002) Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition system. World Scientific Publishing Co., River Edge, p 65Google Scholar
  18. 18.
    Seiler R, Schenkel M (1996) Off-line cursive handwriting recognition compared with on-line recognition. In: ICPR, p 505Google Scholar
  19. 19.
    Sagheer MW, He CL, Nobile N, Suen CY (2009) A new large Urdu database for off line handwriting recognition. In: Image analysis and processing ICIAP. Springer, Berlin, p 538Google Scholar
  20. 20.
    Ul-Hasan A, Bukhari SS, Rashid SF, Shafait F, Breuel TM (2012) Semi-automated OCR database generation for Nabataean scripts. In: ICPR 1667Google Scholar
  21. 21.
    Ahmed SB, Naz S, Razzak MI, Rashid SF, Afzal MZ, Breuel TM (2015) Evaluation of cursive and non-cursive scripts using recurrent neural networks. Neural Comput Appl 27(3):603–613Google Scholar
  22. 22.
    Al-Maadeed S, Elliman D, Higgins C (2002) A data base for Arabic handwritten text recognition research. In: Proceedings of the 8th international workshop on frontiers in handwriting recognition, p 485Google Scholar
  23. 23.
    Al-Ohali Y, Cheriet M, Suen C (2003) Databases for recognition of handwritten Arabic cheques. Pattern Recognit 36(1):111CrossRefzbMATHGoogle Scholar
  24. 24.
    Wang Y, Ding X, Liu C (2011) MQDF discriminative learning based offline handwritten Chinese character recognition. In: ICDAR. IEEE 1100Google Scholar
  25. 25.
    Graves A, Bunke H, Fernandez S, Liwicki M, Schmidhuber J (2008) Unconstrained online handwriting recognition with recurrent neural networks. In: Advances in neural information processing systems, p 577Google Scholar
  26. 26.
    Gers FA, Schmidhuber E (2001) LSTM recurrent networks learn simple context-free and context-sensitive languages. IEEE Trans Neural Netw 12(6):1333CrossRefGoogle Scholar
  27. 27.
    Hochreiter S, Schmidhuber J (1997) Long short term memory. Neural Comput 9(8):1735CrossRefGoogle Scholar
  28. 28.
    Graves A (2008) Supervised sequence labeling with recurrent neural networks. PhD thesis, 1-117, Technical University MunichGoogle Scholar
  29. 29.
    Mrgner V, El-Abed H (2008) Databases and competitions: strategies to improve Arabic recognition systems. In: Proceedings of the conference on Arabic and Chinese handwriting recognition, Springer, Berlin, p 82Google Scholar
  30. 30.
    Srihari S, Srinivasan, H, Babu, P, Bhole C (2005) Handwritten Arabic word spotting using the cedarabic document analysis system. In: Proceedings of the symposium on document image UNHDerstanding technology (SDIUT-05), p 123Google Scholar
  31. 31.
    Al-Ohali Y, Cheriet M, Suen C (2003) Databases for recognition of handwritten Arabic cheques. Pattern Recognit 36(1):111–121CrossRefzbMATHGoogle Scholar
  32. 32.
    Schlosser S (1995) Erim Arabic Database. Document Processing Research Program, Information and Materials Applications Laboratory, Environmental Research Institute of MichiganGoogle Scholar
  33. 33.
    Slimane F, Ingold R, Kanoun S, Alimi A, Hennebert J (2009) Database and evaluation protocols for Arabic printed text recognition. Technical Report 296-09-01. Department of Informatics, University of FribourgGoogle Scholar
  34. 34.
    Mozaffari S, El-Abed H, Maergner V, Faez K, Amirshahi A (2008) A database of Farsi handwritten city names. IfN/Farsi-Database, p 24Google Scholar
  35. 35.
    Ziaratban M, Faez K, Bagheri F (2009) FHT: an unconstraint Farsi handwritten text database. In: Proceedings of the 10th international conference on document analysis and recognition, Catalonia, Spain, p 281Google Scholar
  36. 36.
  37. 37.
    Ul-Hasan A, Bukhari SS, Rashid SF, Shafait F, Breuel TM (2012) Semi-automated OCR database generation for Nabataean scripts. In: ICPR, p 1667Google Scholar

Copyright information

© The Natural Computing Applications Forum 2017

Authors and Affiliations

  • Saad Bin Ahmed
    • 1
  • Saeeda Naz
    • 2
    • 3
  • Salahuddin Swati
    • 4
  • Muhammad Imran Razzak
    • 1
    Email author
  1. 1.King Saud Bin Abdul Aziz University for Health SciencesRiyadhSaudi Arabia
  2. 2.Department of Information TechnologyHazara UniversityMansehraPakistan
  3. 3.Higher Education DepartmentGovt. Girls Postgraduate College No. 1MansehraPakistan
  4. 4.COMSATS Institute of Information TechnologyAbbottabadPakistan

Personalised recommendations