Skip to main content
SpringerLink
Log in

Improving the DBLSTM for on-line Arabic handwriting recognition

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Various applications involved in the computer recognition of pen-input handwritten words, such as the online form filling, text editing, note taking, and so on. Therefore, a great deal of research work tries to improve the recognition rate of those online words recognition systems resulting in several effective methods. Relevant results related to Latin and Chinese scripts have been achieved. However, the Arabic script has been neglected so far, which stimulated us to propose a new online Arabic handwriting recognition system based on DBLSTM that relies on three techniques that were applied in order to enhance its performance. First, the dropout was applied, in different positions, to prevent overfitting. Then, ReLU and Maxout units were added, in different ways, to overcome the vanishing gradient problem. These proposed systems were tested on a large database ADAB to prove its performance against difficult conditions such as the variety of writers, the large vocabulary and the diversity of style. According to the experimental results and compared to the baseline system, the best tested architecture gives a reduction of 10.99% in label error rate.

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

Access this article

Log in via an institution

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
Fig. 12

Similar content being viewed by others

References

  1. Abdelazeem S, Eraqi HM (2011) On-line Arabic handwritten personal names recognition system based on HMM. In International Conference on Document Analysis and Recognition (ICDAR), pp. 1304–1308

  2. Abdou S, Fahmy A, Hosney I, Mostafa I (2009) Artificial Tutor For Arabic Handwriting Training. In Proceedings of the Second International Conference on Arabic Language Resources and Tools, pp. 24–30

  3. Ahmed SB, Naz S, Swati S, Razzak MI (2017) ‘Handwritten Urdu character recognition using one-dimensional BLSTM classifier’. Neural Comput & Applic, p. 1–9

  4. Boubaker H, Elbaati A, Tagougui N, El Abed H, Kherallah M, Alimi AM (2012) ‘Online Arabic databases and applications’, in ‘Guide to OCR for Arabic Scripts’, pp. 541–557

  5. Cai M, Liu J (2016) Maxout neurons for deep convolutional and LSTM neural networks in speech recognition. Speech Comm 77:53–64

    Article  Google Scholar 

  6. Cheng G, Peddinti V, Povey D, Manohar V, Khudanpur S, Yan Y (2017) ‘An exploration of dropout with LSTMs’ In : Proc. Interspeech

  7. Dahl GE, Sainath TN, Hinton GE (2013) ‘Improving deep neural networks for LVCSR using rectified linear units and dropout’. In International Conference on Acoustics, Speech and Signal Processing, pp.8609–8613

  8. Dahl GE, Sainath TN, Hinton GE (2013) ‘Improving deep neural networks for LVCSR using rectified linear units and dropout’, in IEEE International Conference on ‘Acoustics, Speech and Signal Processing, pp. 8609–8613

  9. El Abed H, Kherallah M, Märgner V, Alimi AM (2011) On-line arabic handwriting recognition competition. IJDAR 14(1):15–23

    Article  Google Scholar 

  10. Frinken V, Uchida S (2015) ‘Deep BLSTM neural networks for unconstrained continuous handwritten text recognition’, in 13th International Conference on ‘Document Analysis and Recognition, pp. 911–915

  11. Funahashi K, Nakamura Y (1993) Approximation of dynamical systems by continuous time recurrent neural networks. Neural Netw 6(6):801–806

    Article  Google Scholar 

  12. Fung I, Mak B (2018) ‘End-to-end low-ressource lip-reading with Maxout CNN and LSTM’. In International Conference on Acoustics, Speech and Signal Processing, pp. 2511–2515

  13. Glorot X, Bordes A, Bengio Y (2011) ‘Deep sparse rectifier neural networks’, in ‘Proceedings of the fourteenth international conference on artificial intelligence and statistics’, pp. 315–323

  14. Goodfellow IJ, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) ‘Maxout Networks’ arXiv preprint arXiv:1302.4389

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

  16. Graves A, Ch A, Fernández S, et al. (2006) ‘Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks’ In Proceedings of the 23rd international conference on Machine learning. p. 369–376

  17. Graves A, Liwicki M, Bunke H, et al. (2008) ‘Unconstrained on-line handwriting recognition with recurrent neural networks’, in ‘Adv Neural Inf Proces Syst’, pp. 577–584

  18. Graves A, Mohamed A, Hinton G (2013) ‘Speech recognition with deep recurrent neural networks’, in international conference on ‘Acoustics, speech and signal processing ,pp. 6645–6649

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

    Article  Google Scholar 

  20. Kermorvant C (2015) ‘Where to Apply Dropout in Recurrent Neural Networks for Handwriting Recognition’ in 13th International Conference on Document Analysis and Recognition, pp. 681–685

  21. Levenshtein VI (1966) Binary codes capable of correcting deletions, insertions, and reversals. In Soviet physics doklady Vol. 10, No. 8, pp. 707–710

  22. Li X, Wu X (2015) ‘Improving Long Short-Term Memory Networks using Maxout Units for Large Vocabulary Speech Recognition’in International Conference on Acoustics, Speech and Signal Processing, pp. 4600–4604

  23. Liwicki M, Bunke H (2005) ‘IAM-OnDB An on-line English sentence database acquired from handwritten text on a whiteboard’ In Eighth International Conference on Document Analysis and Recognition, p. 956–961

  24. Liwicki M, Graves A, Fernàndez S, et al. (2007) ‘A novel approach to on - line handwriting recognition based on bidirectional long short-term memory networks’, in ‘Proceedings of the 9th International Conference on Document Analysis and Recognition’

  25. Luo Y, Liu Y, Zhang Y, Wang B, Ye Z (2017) ‘Maxout neurons based deep bidirectional LSTM for acoustic modeling’, in IEEE International Conference on Robotics and Biomimetics (ROBIO), pp. 1599–1604

  26. Maalej R, Kherallah M (2016) ‘Improving MDLSTM for offline Arabic handwriting recognition using dropout at different positions’, in ‘ International Conference on Artificial Neural Networks’ pp. 431–438

  27. Maalej R, Tagougui N, Kherallah M (2016) ‘Online Arabic handwriting recognition with dropout applied in deep recurrent neural networks’, in 12th IAPR Workshop on ‘Document Analysis Systems , pp. 417–421

  28. Maalej R, Tagougui N, Kherallah M (2016) ‘Recognition of handwritten Arabic words with dropout applied in MDLSTM’, in ‘International Conference Image Analysis and Recognition’, pp. 746–752

  29. Nair V, Hinton GE (2010) ‘Rectified linear units improve restricted boltzmann machines’, in ‘Proceedings of the 27th international conference on machine learning (ICML-10)’, pp. 807–814

  30. Pham V, Bluche T, Kermorvant C, Louradour J (2014) ‘Dropout improves recurrent neural networks for handwriting recognition’, in 14th International Conference on ‘Frontiers in Handwriting Recognition, pp. 285–290

  31. Rajeswar S, Ray A, Chaudhury S (2015) ‘Text recognition using deep BLSTM networks’. In eighth international conference on: Advances in pattern recognition, p. 1–6

  32. Schuster, M., Paliwal, K.K.: ‘Bidirectional recurrent neural networks’ IEEE Trans Signal Process , Vol. 45, n 11, pp. 2673–2681 (1997).

  33. Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) ‘Dropout: A Simple Way to Prevent Neural Networks from Overfitting’ Vol. 15, n 1 , pp. 1929–1958

  34. Szegedy C, Liu W, Jia Y, et al. (2015) ‘Going deeper with convolutions’, in ‘Proceedings of the IEEE conference on computer vision and pattern recognition’, pp. 1–9

  35. Ul-Hasan A, Faisal Rashid S, Bin Ahmed S, Shafait F, Breuel TM (2013) ‘Offline Printed Urdu Nastaleeq Script Recognition with Bidirectional LSTM Networks’ In 12th International Conference on Document Analysis and Recognition, p. 1061–1065

Download references

Author information

Authors and Affiliations

  1. National School of Engineers of Sfax, University of Sfax, Sfax, Tunisia

    Rania Maalej

  2. Faculty of Sciences, University of Sfax, Sfax, Tunisia

    Monji Kherallah

Authors
  1. Rania Maalej
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Monji Kherallah
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rania Maalej.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Maalej, R., Kherallah, M. Improving the DBLSTM for on-line Arabic handwriting recognition. Multimed Tools Appl 79, 17969–17990 (2020). https://doi.org/10.1007/s11042-020-08740-w

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-020-08740-w

Keywords

Search

Navigation