Skip to main content
Log in

Urdu Nasta’liq text recognition system based on multi-dimensional recurrent neural network and statistical features

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

Abstract

Character recognition for cursive script like Arabic, handwritten English and French is a challenging task which becomes more complicated for Urdu Nasta’liq text due to complexity of this script over Arabic. Recurrent neural network (RNN) has proved excellent performance for English, French as well as cursive Arabic script due to sequence learning property. Most of the recent approaches perform segmentation-based character recognition, whereas, due to the complexity of the Nasta’liq script, segmentation error is quite high as compared to Arabic Naskh script. RNN has provided promising results in such scenarios. In this paper, we achieved high accuracy for Urdu Nasta’liq using statistical features and multi-dimensional long short-term memory. We present a robust feature extraction approach that extracts feature based on right-to-left sliding window. Results showed that selected features significantly reduce the label error. For evaluation purposes, we have used Urdu printed text images dataset and compared the proposed approach with the recent work. The system provided 94.97 % recognition accuracy for unconstrained printed Nasta’liq text lines and outperforms the state-of-the-art results.

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

Access this article

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

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

Similar content being viewed by others

References

  1. Naz S, Razzak MI, Hayat K, Anwar MW, Khan SZ (2014) Challenges in baseline detection of arabic script based languages. Intell Syst Sci Inf 542:181–196

    Article  Google Scholar 

  2. Sabbour N, Shafait F, Sabbour N, Shafait F (2013) A segmentation-free approach to Arabic and Urdu OCR. In: Proceedings of the SPIE international society for optics and photonics, vol 86580, p 86580 N

  3. Graves A (2013) RNNLIB: a recurrent neural network library for sequence learning problems. http://sourceforge.net/projects/rnnl/

  4. Ul-Hasan A, Ahmed SB, Rashid F, Shafait F, Breuel TM (2013) Offline printed Urdu Nastaleeq script recognition with bidirectional LSTM networks. In: 12th International conference on document analysis and recognition (ICDAR’13), pp. 1061–1065

  5. McCulloch WPWS (1990) A logical calculus of the ideas immanent in nervous activity. Bull Math Biol 52(1–2):99–115

    Article  Google Scholar 

  6. Rosenblatt F (1961) Principles of neurodynamics: perceptrons theory brain mechanism. No. VG-1196-G-8. Cornell Aeronautical Lab Inc.

  7. Jaeger H (2002) Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the ‘echo state network’ approach. GMD Rep 159, Ger Natl Res Cent Inf Technol, p 48

  8. Hochreiter J, Schmidhuber S (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  9. Schmidhuber J, Gers FA (2001) LSTM recurrent networks learn simple context free and context sensitive languages. IEEE Trans Neural Netw 12(6):1333–1340

    Article  Google Scholar 

  10. Graves A (2012) Offline arabic handwriting recognition with multidimensional recurrent neural networks. Springer, London

    Book  Google Scholar 

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

    Article  Google Scholar 

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

    Article  Google Scholar 

  13. Graves A, Fernández S, Schmidhuber J (2007) Multidimensional recurrent neural networks. In: Proceedings of the international conference on artificial neural networks

  14. Naz S, Umar AI, Shirazi SH, Ahmed SB, Siddiqi I, Razzak MI (2015) Segmentation techniques for recognition of Arabic-like scripts: a comprehensive survey. Educ Inf Technol 20(2). doi:10.1007/s10639-015-9377-5

  15. Naz S, Hayat K, Razzak MI, Anwar MW, Madani SA, Khan SU (2013) The optical character recognition of Urdu-like cursive scripts. Pattern Recognit 47(3):1229–1248

    Article  Google Scholar 

  16. Nishide S, Okuno HG, Ogata T, Tani J (2011) Handwriting prediction based character recognition using recurrent neural network. In: IEEE international conference on systems, man, and cybernetics (SMC), pp 2549–2554

  17. Graves A, Liwicki M, Fernández S, Bertolami R, Bunke H, Schmidhuber J (2009) A novel connectionist system for unconstrained handwriting recognition. IEEE Trans Pattern Anal Mach Intell 31:855–868

    Article  Google Scholar 

  18. Graves A, Schmidhuber J (2009) Offline handwriting recognition with multidimensional recurrent neural networks. International conference on neural information processing systems, pp 545–552

  19. Liwicki M, Graves A, Bunke H, Schmidhuber J (2007) A novel approach to on-line handwriting recognition based on bidirectional long short-term memory networks. Proc 9th Int Conf Doc Anal Recognit 1:367–371

    Google Scholar 

  20. Graves A, Mohamed A, Hinton G (2013) Speech recognition with deep recurrent neural networks. Icassp 3:6645–6649

    Google Scholar 

  21. Ahmed SB, Naz S, Swati S, Razzak MI, Khan AA, Umar AI (2015) Ucom offline dataset: a Urdu handwritten dataset generation.  Int Arab J Inf Technol 12(5)

  22. Rath TM, Manmatha R (2003) Features for word spotting in historical manuscripts. In: Proceedings of the seventh international conference on document analysis recognition, 2003

  23. Al-Hajj Mohamad R, Likforman-Sulem L, Mokbel C (2009) Combining slanted-frame classifiers for improved HMM-based Arabic handwriting recognition. IEEE Trans Pattern Anal Mach Intell 31(7):1165–1177

    Article  Google Scholar 

  24. Khorsheed MS, Al-Omari HK (2014) System and methods for arabic text recognition based on effective arabic text feature extraction. IS Patent No US 20140219562 A1

  25. Khorsheed MS (2007) Offline recognition of omnifont Arabic text using the HMM ToolKit (HTK). Pattern Recognit Lett 28(12):1563–1571

    Article  Google Scholar 

  26. Naeimizaghiani M, Abdullah SNHS, Bataineh B, PirahanSiah F (eds) (2011) Character recognition based on global feature extraction. In: International conference on electrical engineering and informatics (ICEEI), pp 1–4

  27. Singla L, Singh S (2014) Offline handwritten devanagari numerals recognition using GLCM features and neural networks. Int J Eng Res Technol 3(6):25

    Article  Google Scholar 

  28. Bharathi VC, Geetha MK (2013) Segregated handwritten character recognition using GLCM features. Int J Comput Appl 84(2):1–7

    Google Scholar 

  29. Ahmad Z, Orakzai JK, Shamsher I (2009) Urdu compound character recognition using feed forward neural networks. In: Proceedings of the 2nd international conference on computer science and information technology (ICCSIT’09), pp 457–462

  30. Morillot O, Oprean C, Likforman-sulem L, Mokbel C, Chammas E, Grosicki E, Paristech IMT, Ltci C (2013) The UOB-telecom Paristech Arabic handwriting recognition and translation systems for the openhart 2013 competition. NIST-openhart Workshop, Washington

  31. Chherawala Y, Roy PP, Cheriet M (2013) Feature design for offline Arabic handwriting recognition: handcrafted vs automated. In: Proceedings of the 12th international conference on document analysis and recognition (ICDAR)

  32. Marti UV, Bunke H (2000) Using a statistical language model to improve the performance of an hmm based cursive handwriting recognition system. Int J Pattern Recognit Artif Intell 15(01):6–90

    Google Scholar 

  33. Azeem SA, Ahmed H (2013) Effective technique for the recognition of offline Arabic handwritten words using hidden Markov models. Int J Doc Anal Recognit 16(4):399–412

    Article  Google Scholar 

  34. Morillot O, Likforman-Sulem L, Grosicki E (2013) New baseline correction algorithm for text-line recognition with bidirectional recurrent neural networks. J Electron Imaging 22(2):023028

    Article  Google Scholar 

  35. Naz S, Hayat K, Razzak MI, Anwar MW, Akbar H (2013) Arabic script based character segmentation: a review. In: World congress on computer and information technology (WCCIT’13), pp 1–6

  36. Ul-Hasan A, Bin Ahmed S, Rashid F, Shafait F, Breuel TM (2013) Offline printed urdu nastaleeq script recognition with bidirectional LSTM networks. In: Proceedings of the international conference on document analysis recognition, ICDAR, pp 1061–1065

  37. Javed ST, Hussain S, Maqbool A, Asloob S, Jamil S, Moin H (2010) Segmentation free Nastalique Urdu OCR. Word Acad Sci Eng Technol 46:456–461

    Google Scholar 

  38. Akram QUA, Hussain S, Niazi A, Anjum U, Irfan F (2014) Adapting tesseract for complex scripts: an example for Urdu Nastalique. In: Proceedings of the 11th IAPR international workshop on document analysis systems, pp 191–195

  39. Javed ST, Hussain S (2013) Segmentation based Urdu Nastalique OCR, Lecture notes in computer science, vol 8259, pp 41–49

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Muhammad I. Razzak.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Naz, S., Umar, A.I., Ahmad, R. et al. Urdu Nasta’liq text recognition system based on multi-dimensional recurrent neural network and statistical features. Neural Comput & Applic 28, 219–231 (2017). https://doi.org/10.1007/s00521-015-2051-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-015-2051-4

Keywords

Navigation