A self controlled RDP approach for feature extraction in online handwriting recognition using deep learning

Abstract

The identification of accurate features is the initial task for benchmarked handwriting recognition. For handwriting recognition, the objective of feature computation is to find those characteristics of a handwritten stroke that depict the class of a stroke and make it separable from the rest of the stroke classes. The present study proposes a feature extraction technique for online handwritten strokes based on a self controlled Ramer-Douglas-Peucker (RDP) algorithm. This novel approach prepares a smaller length feature vector for different shaped online handwritten strokes without preprocessing and without any control parameter to RDP. Thus, it also overcomes the shortcomings of the traditional chain code based feature extraction approach that requires preprocessing of data, and the original RDP algorithm that requires a control parameter as an input to RDP. We further propose a deep learning network of 1-dimensional convolutional neural networks (Conv1Ds) for recognition, which trains in few minutes due to the smaller dimension of the convolution combined with smaller length feature vectors. The proposed approach can be applied to different scripts and different writing styles. The key aim of the present study is to provide a script independent feature extraction technique that is well suited for smaller devices. It improves the recognition over the best reported accuracy in the literature which was achieved using hidden Markov models with directional features, from 87.67% to 95.61% on a Gurmukhi dataset. For Unipen online handwriting datasets the results are at par with the literature.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4

References

  1. 1.

    Parizeau M, Lemieux A, Gagne C (2001) Character recognition experiments using unipen data. In: Proceedings of Sixth International Conference on Document Analysis and Recognition, pp 481–485

  2. 2.

    Jaeger S, Manke S, Reichert J, Waibel A (2001) Online handwriting recognition: the npen++ recognizer. int j doc anal recognit 3:169-180. IJDAR 3:169–180

    Article  Google Scholar 

  3. 3.

    Chakraborty B, Chakraborty G (2002) A new feature extraction technique for on-line recognition of handwritten alphanumeric characters. Inf Sci 148(1):55–70

    MATH  Article  Google Scholar 

  4. 4.

    Hanmandlu M, Mohan KM, Chakraborty S, Goyal S, Choudhury D (2003) Unconstrained handwritten character recognition based on fuzzy logic. Pattern Recognit 36(3):603–623

    Article  Google Scholar 

  5. 5.

    Abandah G, Malas TM (2010) Feature selection for recognizing handwritten arabic letters. Dirasat Engineering Sciences Journal, 37

  6. 6.

    Al-Taani DA, Al-Haj S (2010) Recognition of on-line arabic handwritten characters using structural features. J Pattern Recognit Res 5:23–37

    Article  Google Scholar 

  7. 7.

    Ghods V, Kabir E (2010) Feature extraction for online farsi characters. In: 2010 12Th International Conference on Frontiers in Handwriting Recognition, pp 477–482

  8. 8.

    Verma B, Lu J, Ghosh M, Ghosh R (2004) . A feature extraction technique for online handwriting recognition 2:1337–1341

    Google Scholar 

  9. 9.

    Ghosh R, Roy PP (2015) A novel feature extraction approach for online bengali and devanagari character recognition. In: 2015 2Nd International Conference on Signal Processing and Integrated Networks (SPIN), pp 483–488

  10. 10.

    Rani M, Meena Y (2011) An efficient feature extraction method for handwritten character recognition. pp 302–309, 12

  11. 11.

    Fink GA, Vajda S, Bhattacharya U, Parui SK, Chaudhuri BB (2010) Online bangla word recognition using sub-stroke level features and hidden markov models. In: 2010 12th International Conference on Frontiers in Handwriting Recognition, pp 393–398

  12. 12.

    Bluche T, Ney H, Kermorvant C (2013) Feature extraction with convolutional neural networks for handwritten word recognition. In: Proceedings of the Twelfth International Conference on Document Analysis and Recognition, pp 285–289

  13. 13.

    Zanchettin C, Bezerra BLD, Azevedo WW (2012) A KNN-SVM hybrid model for cursive handwriting recognition. In: Proceedings of the International Joint Conference on Neural Networks, pp 1–8

  14. 14.

    Chauhan VK, Dahiya K, Sharma A Problem formulations and solvers in linear SVM: a review’,’ Artificial Intelligence Review, 2018. [Online]. Available: https://doi.org/10.1007/s10462-018-9614-6

  15. 15.

    Jaeger S, Manke S, Reichert J, Waibel A (2001) Online handwriting recognition: the npen++ recognizer. Int J Doc Anal Recognit 3:169–180

    Article  Google Scholar 

  16. 16.

    Ciresan DC, Meier U, Gambardella LM, Schmidhuber J (2011) Convolutional neural network committees for handwritten character classification. In: Proceedings of the International Conference on Document Analysis and Recognition, pp 1135–1139

  17. 17.

    Artieres T, Marukatat S, Gallinari P (2007) Online handwritten shape recognition using segmental hidden Markov models. IEEE Trans Pattern Anal Mach Intell 29(2):205–217

    Article  Google Scholar 

  18. 18.

    Nebti S, Boukerram A (2012) Handwritten characters recognition based on nature-inspired computing and neuro-evolution. Appl Intell 38(2):146–159

    Article  Google Scholar 

  19. 19.

    Mahmoud SA, Al-Khatib WG (2010) Recognition of arabic (indian) bank check digits using log-gabor filters. Appl Intell 35(3):445–456

    Article  Google Scholar 

  20. 20.

    Bharath A, Madhvanath S (2012) HMM-Based lexicon-driven and lexicon-free word recognition for online handwritten Indic scripts. IEEE Trans Pattern Anal Mach Intell 34:670–682

    Article  Google Scholar 

  21. 21.

    Ren G, Ganapathy V (2019) Recognition of online handwriting with variability on smart devices. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp 7605–7609

  22. 22.

    Mandal S, Mahadeva Prasanna SR, Sundaram S (2019) An improved discriminative region selection methodology for online handwriting recognition. Int J Doc Anal Recog (IJDAR) 22(1):1–14

    Article  Google Scholar 

  23. 23.

    Bilgin-Tasdemir E, Yanikoglu B (2018) A comparative study of delayed stroke handling approaches in online handwriting. Int J Doc Anal Recog (IJDAR) 22(1):15–28

    Article  Google Scholar 

  24. 24.

    Zouari R, Boubaker H, Kherallah M (2019) Multi-language online handwriting recognition based on beta-elliptic model and hybrid tdnn-svm classifier. Multimedia Tools Appl 78(9):12103– 12123

    Article  Google Scholar 

  25. 25.

    Carbune V, Gonnet P, Deselaers T, Rowley H, Daryin A, Calvo M, Wang L. -L., Keysers D, Feuz S, Gervais P (2019) Fast multi-language lstm-based online handwriting recognition. ArXiv, 02

  26. 26.

    Douglas DH, Peucker TK (1973) Algorithms for the reuduction of the number of points required to represent a digitized line or its caricature. The International Journal for Geographic Information and Geovisualization 10 (2):112–122

    Article  Google Scholar 

  27. 27.

    Guyon I, Schomaker L, Plamondon R, Liberman M, Janet S (1994) Unipen project of on-line data exchange and recognizer benchmarks. In: Proceedings of International Conference on Pattern Recognition. pp 29–33

  28. 28.

    Singh S, Sharma A, Chhabra I (2016) Online handwritten Gurmukhi strokes dataset based on minimal set of words. ACM Transactions on Asian and Low-Resource Language Information Processing 16(1):1–20

    Article  Google Scholar 

  29. 29.

    Prasad DK, Leung MKH, Quek C, Cho SY (2012) A novel framework for making dominant point detection methods non-parametric. Image Vis Comput 30:843–859

    Article  Google Scholar 

  30. 30.

    Masood A (2008) Dominant point detection by reverse polygonization of digital curves. Image Vis Comput 26(5):702–715

    Article  Google Scholar 

  31. 31.

    Carmona-Poyato A, Madrid-Cuevas FJ, Medina-Carnicer R, Munoz-Salinas R (2010) Polygonal approximation of digital planar curves through break point suppression. Pattern Recogn 43(1):14–25

    MATH  Article  Google Scholar 

  32. 32.

    Wu WY (2003) An adaptive method for detecting dominant points. Pattern Recogn 36(10):2231–2237

    MATH  Article  Google Scholar 

  33. 33.

    Kolesnikov A, Franti P (2003) Reduced-search dynamic programming for approximation of polygonal curves. Pattern Recogn 24(14):2243–2254

    MATH  Article  Google Scholar 

  34. 34.

    Marji M, Siy P (2004) Polygonal representation of digital planar curves through dominant point detection a nonparametric algorithm. Pattern Recogn 37(11):2113–2130

    Article  Google Scholar 

  35. 35.

    Kolesnikov A, Franti P (2007) Polygonal approximation of closed discrete curves. Pattersn Recogn 40 (4):1282–1293

    MATH  Article  Google Scholar 

  36. 36.

    Masood A, Haq SA (2007) A novel approach to polygonal approximation of digital curves. Image Vis Comput 18(3):264–274

    Google Scholar 

  37. 37.

    Bhowmick P, Bhattacharya BB (2007) Fast polygonal approximation of digital curves using relaxed straightness properties. IEEE Trans Pattern Anal Mach Intell 29(9):1590–1602

    Article  Google Scholar 

  38. 38.

    Nguyen TP, Debled-Rennesson I (2011) A discrete geometry approach for dominant point detection. Pattern Recogn 44(1):32–44

    MATH  Article  Google Scholar 

  39. 39.

    Li X, Yeung DY (1997) Online handwritten alphanumeric character recognition using dominant points in strokes. Pattern Recogn 30(1):31–44

    Article  Google Scholar 

  40. 40.

    Bai Z, Huo Q (2005) A study on the use of 8 directional features for online handwritten Chinese character recognition. In: Proceedings of the International Conference on Document Analysis and Recognition, pp 262–266

  41. 41.

    Liu CL, Zhou XD (2006) Online Japanese character recognition using trajectory based normalization and direction feature extraction. In: Proceedings of the International Workshop on Frontiers in Handwriting Recognition, pp 217–222

  42. 42.

    LaViola J, Zeleznik R (2007) A practical approach for writer-dependent symbol recognition using a writer-independent symbol recognizer. IEEE Trans Pattern Anal Mach Intell 29:1917–1926

    Article  Google Scholar 

  43. 43.

    Delaye A, Anquetil E (2013) Hbf49 feature set: A first unified baseline for online symbol recognition. Pattern Recogn 46(1):117–130

    Article  Google Scholar 

  44. 44.

    Li Z, Jin L, Lai S (2018) Rotation-free online handwritten Chinese character recognition using two-stage convolutional neural network. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp 205–210

  45. 45.

    Zhang X-Y, Yin F, Zhang Y-M, Liu C-L, Bengio Y (2018) Drawing and recognizing chinese characters with recurrent neural network. IEEE Trans Pattern Anal Mach Intell 40(4):849–862

    Article  Google Scholar 

  46. 46.

    Keysers D, Deselaers T, Rowley HA, Wang L, Carbune V (2017) Multi-language online handwriting recognition. IEEE Trans Pattern Anal Mach Intell 39(6):1180–1194

    Article  Google Scholar 

  47. 47.

    Ding H, Chen K, Hu W, Cai M, Huo Q (2018) Building compact CNN-dblstm based character models for handwriting recognition and ocr by teacher-student learning. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp 139–144

  48. 48.

    Dutta K, Krishnan P, Mathew M, Jawahar CV (2018) Improving CNN-RNN hybrid networks for handwriting recognition. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp 80–85

  49. 49.

    Gan J, Wang W, Lu K (2019) A new perspective: Recognizing online handwritten chinese characters via 1-dimensional cnn. Inf Sci 478:375–390

    Article  Google Scholar 

  50. 50.

    Singh S, Sharma A, Chhabra I (2017) A dominant points-based feature extraction approach to recognize online handwritten strokes. Int J Doc Anal Recogn 20(1):37–58

    Article  Google Scholar 

  51. 51.

    Li X, Parizeau M, Plamondon R (1998) Model-based on-line handwritten digit recognition. In: Proceedings of the Fourteenth International Conference on Pattern Recognition

  52. 52.

    Prevost L, Milgram M (2000) Modelizing character allographs in omni-scriptor frame: a new non-supervised clustering algorithm. Pattern Recogn Lett, 295–302

  53. 53.

    Hu J, Lim SG, Brown MK Writer independent on-line handwriting recognition using an HMM approach. Pattern Recognit, (33)

  54. 54.

    Teredesai A, Ratzlaff EH, Subrahmonia J, Govindaraju V (2002) On-line digit recognition using off-line features. In: Indian Conference on Computer Vision, Graphics & Image Processing, 01

  55. 55.

    Bahlmann C, Burkhardt H (2001) Measuring HMM similarity with the bayes probability of error and its application to online handwriting recognition. In: Proceedings of the Sixth International Conference on Document Analysis and Recognition

  56. 56.

    Bahlmann C, Haasdonk B, Burkhardt H (2002) On-line handwriting recognition with support vector machines a kernel approach. In: Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition, pp 49–54

  57. 57.

    Ratzlaff EH (2003) Methods, report and survey for the comparison of diverse isolated character recognition results on the unipen database. In: Proceedings of the Seventh International Conference on Document Analysis and Recognition (ICDAR), vol 1. pp 623–628

  58. 58.

    Bahlmann C, Burkhardt H (2004) The writer independent online handwriting recognition system flog on hand and cluster generative statistical dynamic time warping. IEEE Trans Pattern Anal Mach Intell 26(3):299–310

    Article  Google Scholar 

  59. 59.

    Mitoma H, Uchida S, Sakoe H (2005) Online character recognition based on elastic matching and quadratic discrimination. In: Proceedings of the Eighth International Conference on Document Analysis and Recognition

  60. 60.

    Kherallah M, Haddad L, Alimi AM, Mitiche A (2008) On-line handwritten digit recognition based on trajectory and velocity modeling. Pattern Recogn Lett 29(5):580–594

    Article  Google Scholar 

  61. 61.

    Do TMT, Artieres T (2009) Learning mixture models with support vector machines for sequence classification and segmentation. Pattern Recogn 42(12):3224–3230

    MATH  Article  Google Scholar 

  62. 62.

    Mirvaziri H, Javidi M, Mansouri N (2009) Handwriting recognition algorithm in different languages survey. In: IVIC 2009: International Visual Informatics Conference, pp 487–497, 11

  63. 63.

    Pham DV (2012) Online handwriting recognition using multi convolution neural networks. SEAL 2012: Simulated Evolution and Learning, 310–319

  64. 64.

    Mori M, Uchida S, Sakano H (2014) Global feature for online character recognition. Pattern Recogn Lett 35:142–148

    Article  Google Scholar 

  65. 65.

    Verma K, Kumar Sharma R (2017) Recognition of online handwritten Gurmukhi characters based on zone and stroke identification. Sadhana 42:05

    MathSciNet  Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Sukhdeep Singh.

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

Verify currency and authenticity via CrossMark

Cite this article

Singh, S., Chauhan, V.K. & Smith, E.H.B. A self controlled RDP approach for feature extraction in online handwriting recognition using deep learning. Appl Intell 50, 2093–2104 (2020). https://doi.org/10.1007/s10489-020-01632-4

Download citation

Keywords

  • Online handwriting recognition
  • Feature extraction
  • Ramer-Douglas-Peucker
  • Gurmukhi
  • Unipen
  • Deep learning