Advertisement

Multi-language online handwriting recognition based on beta-elliptic model and hybrid TDNN-SVM classifier

  • Ramzi Zouari
  • Houcine Boubaker
  • Monji Kherallah
Article
  • 38 Downloads

Abstract

Recently, several researches were carried on handwritten document analysis field thanks to the evolution of data capture technologies. For a given document, multiple components could be treated as text, signatures and graphics. In this study, we present a new framework for a Multilanguage online handwritten text analysis where both script identification and recognition are made. The proposed system proceeds by segmenting the script into continuous trajectories delimited between two successive pen-down and pen-up moments. These segments are clustered and trained using Time Delay Neural Network (TDNN) according to their beta-elliptic parameters. In script identification process, the segments belonging to the same script are gathered and brought to a Recurrent Neural Network with Long Short Term Memory (RNN-LSTM) in order to identify its language. For script recognition stage, the samples from the already selected language database are trained and tested using the fuzzy output description obtained by the TDNN coupled to a Support Vector Machines (SVM). The Experiments were made on a large multi-language database containing 45686 online handwriting words from Latin, Arabic and digit scripts and shows very promising results that exceed the recognition rate of 99%.

Keywords

Online handwriting Multi-language Beta-elliptic model Velocity beta impulse Pseudo-word RNN-LSTM TDNN Receptive field 

Notes

Acknowledgements

This work was supported by grants from the General Direction of Scientific Research and Technological Renovation (DGRST), Tunisia, under the ARUB program 01/UR/11/02.

References

  1. 1.
    Ahmed H, Azeem SA (2011) On-line Arabic handwriting recognition system based on HMM. In: International conference on document analysis and recognition (ICDAR). IEEE, pp 1324–1328Google Scholar
  2. 2.
    Alimi AM (2003) Beta neuro-fuzzy systems. Task Q 7(1):23–41Google Scholar
  3. 3.
    Alimolu F, Alpaydin E (2001) Combining multiple representations for pen-based handwritten digit recognition. Turkish J Electr Eng Comput Sci 9(1):1–12Google Scholar
  4. 4.
    Bhattacharya S, Maitra DS, Bhattacharya U, Parui SK (2016) An end-to-end system for Bangla online handwriting recognition. In: 15th international conference on frontiers in handwriting recognition (ICFHR). IEEE, pp 373–378Google Scholar
  5. 5.
    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. Springer, London, pp 541–557CrossRefGoogle Scholar
  6. 6.
    Boubaker H, Rezzoug N, Kherallah M, Gorce P, Alimi AM (2015) Spatiotemporal representation of 3D hand trajectory based on Beta-elliptic models. Comput Methods Biomech Biomed Eng J 18(15):1632–1647CrossRefGoogle Scholar
  7. 7.
    Bezine H, Alimi AM, Sherkat N (2004) Generation and analysis of handwriting script with the beta-elliptic model. In: Proceedings of the 9th international workshop on frontiers in handwriting recognition, pp 515–520Google Scholar
  8. 8.
    Burges CJ (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2(2):121–167CrossRefGoogle Scholar
  9. 9.
    Elleuch M, Zouari R, Kherallah M (2016) Feature extractor based deep method to enhance online arabic handwritten recognition system. In: 25th international conference on artificial neural networks, pp 136–144Google Scholar
  10. 10.
    Gargouri M, Kanoun S, Ogier JM (2013) Text-independent writer identification on online Arabic handwriting. In: 12th international conference on document analysis and recognition (ICDAR). IEEE, pp 428–432Google Scholar
  11. 11.
    Graves A, Liwicki M, Fernández S, Bunke H, Bertolami R, Schmidhuber J (2009) A novel connectionist system for unconstrained handwriting recognition. IEEE Trans Pattern Anal Mach Intell 31(5):855–868CrossRefGoogle Scholar
  12. 12.
    Ghosh R, Roy PP (2015) Study of two zone-based features for online Bengali and Devanagari character recognition. In: 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 401–405Google Scholar
  13. 13.
    Ghosh R, Roy PP (2016) Comparison of zone-features for online Bengali and Devanagari word recognition using HMM. In: 15th international conference on frontiers in handwriting recognition (ICFHR), IEEE, pp 435–440Google Scholar
  14. 14.
    Guyon I, Schomaker L, Plamondon R, Liberman M, Janet S (1994) UNIPEN project of on-line data exchange and recognizer benchmarks. In: Pattern recognition, vol 2, pp 29–33Google Scholar
  15. 15.
    Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780CrossRefGoogle Scholar
  16. 16.
    Hollerbach J (1981) An oscillation theory of handwriting. Biol Cybern 39(29, Issue 2):139–156CrossRefGoogle Scholar
  17. 17.
    Indhu TR, Vidya V, Bhadran VK (2015) Multilingual online handwriting recognition system: an android app. In: The fifth international conference on advances in computing and communications (ICACC), IEEE, pp 33–36Google Scholar
  18. 18.
    Keysers D, Deselaers T, Rowley HA, Wang LL, Carbune V (2017) Multi-language online handwriting recognition. IEEE Trans Pattern Anal Mach Intell 39(6):1180–1194CrossRefGoogle Scholar
  19. 19.
    Kherallah M, Njah S, Alimi AM, Derbel N (2002) Recognition of on-line handwritten digits by neural networks using circular and beta approaches. In: International conference on system: man and cybernetics, IEEE, pp 164–169Google Scholar
  20. 20.
    Kherallah M, Haddad L, Alimi AM, Mitiche A (2008) On-line handwritten digit recognition based on trajectory and velocity modeling. Pattern Recog Lett 29 (5):580–594CrossRefGoogle Scholar
  21. 21.
    Kherallah M, Bouri F, Alimi AM (2009) On-line Arabic handwriting recognition system based on visual encoding and genetic algorithm. Eng Appl Artif Intell 22 (1):153–170CrossRefGoogle Scholar
  22. 22.
    Kherallah M, Tagougui N, Alimi AM, El Abed H, Margner V (2011) Online Arabic handwriting recognition competition. In: International conference on document analysis and recognition (ICDAR). IEEE, pp 1454–1458Google Scholar
  23. 23.
    Khlif H, Prum S, Kessentini Y, Kanoun S, Ogier J (2016) Fusion of explicit segmentation based system and segmentation-free based system for on-line Arabic handwritten word recognition. In: 15th international conference on frontiers in handwriting recognition (ICFHR). IEEE, pp 399–4041Google Scholar
  24. 24.
    Lee J, Kim JH (1996) A unified network-based approach for online recognition of multi-lingual cursive handwritings. In: Proceeding of fifth international workshop on frontiers in handwriting recognition, pp 393–397Google Scholar
  25. 25.
    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 aystems (DAS). IEEE, pp 417–421Google Scholar
  26. 26.
    MacQueen J (1967) Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol 1, no 14, pp 281–297Google Scholar
  27. 27.
    Namboodiri AM, Jain AK (2004) Online handwritten script recognition. IEEE Trans Pattern Anal Mach Intell 26(1):124–130CrossRefGoogle Scholar
  28. 28.
    Nakkach H, Haboubi S, Amiri H (2016) Online Arabic character recognition using global and local features. In: 3rd international conference on automation control engineering and computer science, pp 120–124Google Scholar
  29. 29.
    Nguyen T, Zhu B, Nakagawa M (2014) A semi-incremental recognition method for on-line handwritten english text. In: 14th international conference on frontiers in handwriting recognition (ICFHR). IEEE, pp 234–239Google Scholar
  30. 30.
    O’Reilly C, Plamondon R (2009) Development of a Sigma–Lognormal representation for on-line signatures. Pattern Recog 42(12):3324–3337CrossRefGoogle Scholar
  31. 31.
    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 (ICFHR). IEEE, pp 285–290Google Scholar
  32. 32.
    Plamondon R, Alimi AM, Yergeau P, Franck L (1993) Modeling velocity profiles of rapid movements: a comparative study. Biol Cybern 69(2):119–128CrossRefGoogle Scholar
  33. 33.
    Plamondon R (1995) A kinematic theory of rapid human movements. Part-II. Movement time and control. Biol Cybern 72:309–320CrossRefGoogle Scholar
  34. 34.
    Samanta O, Anandarup R, Bhattacharya U, Ujjwal SK (2015) Script independent online handwriting recognition. In: 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 1251–1255Google Scholar
  35. 35.
    Sun L, Tonghua S, Wang R (2016) Deep LSTM networks for online chinese handwriting recognition. In: 15th international conference on frontiers in handwriting recognition (ICFHR). IEEE, pp 271–276Google Scholar
  36. 36.
    Tagougui N, Boubaker H, Kherallah M, Alimi AM (2013) A hybrid MLPNN/HMM recognition system for online Arabic handwritten script. In: World congress on computer and information technology (WCCIT). IEEE, pp 1–6Google Scholar
  37. 37.
    Tan GX, Viard-Gaudin C, Kot AC (2009) Information retrieval model for online handwritten script identification. In: 10th international conference on document analysis and recognition (ICDAR). IEEE, pp 336–340Google Scholar
  38. 38.
    Vapnik V (1998) Statistical learning theory, vol 1, 1735,1780Google Scholar
  39. 39.
    Viviani P, Terzuolo C (1982) Trajectory determines movement dynamics. Neuroscience 7(2):431–437CrossRefGoogle Scholar
  40. 40.
    Waibel A, Hanazawa T, Hinton G, Shikano K, Lang KJ (1989) Phoneme recognition using time-delay neural networks. IEEE Trans Acoust Speech Sig Process 37(3):328–339CrossRefGoogle Scholar
  41. 41.
    Yang W, Jin L, Xie Z, Feng Z (2015) Improved deep convolutional neural network for online handwritten Chinese character recognition using domain-specific knowledge. In: 13th international conference on document analysis and recognition (ICDAR). IEEE, pp 551–555Google Scholar
  42. 42.
    Zhou X, Zhang Y, Tian F, Wang H, Liu C (2014) Minimum-risk training for semi-Markov conditional random fields with application to handwritten Chinese/Japanese text recognition. Pattern Recog 47(5):1904–1916CrossRefGoogle Scholar
  43. 43.
    Zhu B, Shivram A, Govindaraju V, Nakagawa M (2016) Online handwritten cursive word recognition by combining segmentation-free and segmentation-based methods. In: 15th international conference on frontiers in handwriting recognition (ICFHR). IEEE, pp 417–422Google Scholar
  44. 44.
    Zouari R, Boubaker H, Kherallah M (2016) A time delay neural network for online arabic handwriting recognition. In: International conference on intelligent systems design and applications. Springer, pp 1005–1014Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.National School of Engineers of SfaxUniversity of SfaxSfaxTunisia
  2. 2.Faculty of Sciences of SfaxUniversity of SfaxSfaxTunisia

Personalised recommendations