Neural Computing and Applications

, Volume 28, Supplement 1, pp 51–63 | Cite as

Comparison of HMM- and SVM-based stroke classifiers for Gurmukhi script

Original Article

Abstract

With the evolution of touch-based devices, development of handwriting recognition systems has received attention from many researchers. An online handwriting recognition system for Gurmukhi script is proposed in this paper. In this work, 74 stroke classes have been identified and implemented for character recognition of Gurmukhi script. Seventy-two different combinations of SVM- and HMM-based stroke classifiers with five different features have been experimented. The results of recognition of 35 basic characters of Gurmukhi script on a data set of 1750 Gurmukhi characters written by 10 writers have been reported using three best classifiers and a voting-based classifier built with the help of these classifiers. A character recognition rate of 96.7 % has been achieved using the voting-based classifier, whereas a recognition rate of 96.4 % has been achieved with an HMM-based classifier.

Keywords

Gurmukhi script SVM HMM Features extraction Online handwritten character recognition 

Notes

Acknowledgments

We take this opportunity to extend our special thanks to Technology Development for Indian Languages (TDIL), DeitY, MoCIT, Government of India, for sponsoring this research work.

References

  1. 1.
    Almuallim H, Yamaguchi S (1987) A method of recognition of Arabic cursive handwriting. IEEE Trans Pattern Anal Mach Intell 9(5):715–722CrossRefGoogle Scholar
  2. 2.
    Bellegarda EJ, Bellegarda JR, Nahamoo D, Nathan KS (1993) A continuous parameter hidden markov model approach to automatic handwriting recognition, 1993. EP Patent 0,550,865Google Scholar
  3. 3.
    Kumar R, Sharma RK (2013) An efficient post processing algorithm for online handwriting Gurmukhi character recognition using set theory. Int J Pattern Recognit Artif Intell 27(04):1–17CrossRefGoogle Scholar
  4. 4.
    Verma K, Sharma R (2015) Performance analysis of zone based features for online handwritten Gurmukhi script recognition using support vector machine. In: Selvaraj H, Zydek D, Chmaj G (eds) Progress in systems engineering. Volume 330 of advances in intelligent systems and computing. Springer International Publishing, Berlin, pp 747–753Google Scholar
  5. 5.
    Jäger S, Liu C-L, Nakagawa M (2003) The state of the art in Japanese online handwriting recognition compared to techniques in western handwriting recognition. Doc Anal Recognit 6(2):75–88CrossRefGoogle Scholar
  6. 6.
    Liu C-L, Jaeger S, Nakagawa M (2004) Online recognition of Chinese characters: the state-of-the-art. IEEE Trans Pattern Anal Mach Intell 26(2):198–213CrossRefGoogle Scholar
  7. 7.
    Tappert CC, Suen CY, Wakahara T (1990) The state of the art in online handwriting recognition. IEEE Trans Pattern Anal Mach Intell 12(8):787–808CrossRefGoogle Scholar
  8. 8.
    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(4):670–682CrossRefGoogle Scholar
  9. 9.
    Bhattacharya N, Pal U (2012) Stroke segmentation and recognition from Bangla online handwritten text. In: IEEE 2012 international conference on frontiers in handwriting recognition (ICFHR). pp 740–745Google Scholar
  10. 10.
    Biswas C, Bhattacharya U, Parui SK (2012) Hmm based online handwritten Bangla character recognition using dirichlet distributions. In: IEEE 2012 international conference on frontiers in handwriting recognition (ICFHR). pp 600–605Google Scholar
  11. 11.
    Sundaram S, Ramakrishnan A (2013) Attention-feedback based robust segmentation of online handwritten isolated Tamil words. ACM Trans Asian Lang Inf Process (TALIP) 12(1):4Google Scholar
  12. 12.
    Yaeger LS, Richard WFI, Pagallo GM (2009) Method and apparatus for acquiring and organizing ink information in pen-aware computer systems, 21 July 2009. US Patent 7,564,995Google Scholar
  13. 13.
    Plamondon R, Srihari SN (2000) Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans Pattern Anal Mach Intell 22(1):63–84CrossRefGoogle Scholar
  14. 14.
    Bhattacharya U, Gupta BK, Parui SK (2007) Direction code based features for recognition of online handwritten characters of Bangla. In: IEEE ninth international conference on document analysis and recognition, 2007. ICDAR 2007, vol 1. pp 58–62Google Scholar
  15. 15.
    Bhowmik TK, Ghanty P, Roy A, Parui SK (2009) Svm-based hierarchical architectures for handwritten Bangla character recognition. Int J Doc Anal Recognit 12(2):97–108CrossRefGoogle Scholar
  16. 16.
    Dutta A, Chaudhury S (1993) Bengali alpha-numeric character recognition using curvature features. Pattern Recognit 26(12):1757–1770CrossRefGoogle Scholar
  17. 17.
    Parui SK, Guin K, Bhattacharya U, Chaudhuri BB (2008) Online handwritten Bangla character recognition using hmm. In: IEEE 19th international conference on pattern recognition, 2008, ICPR 2008. pp 1–4Google Scholar
  18. 18.
    Garcia-Salicetti S, Doizzi B, Gallinari P, Mellouk A, Fanchon D (1995) A hidden markov model extension of a neural predictive system for online character recognition. In: IEEE proceedings of the third international conference on document analysis and recognition, 1995, vol 1. pp 50–53Google Scholar
  19. 19.
    Hu J, Brown MK, Turin W (1996) Hmm based online handwriting recognition. IEEE Trans Pattern Anal Mach Intell 18(10):1039–1045CrossRefGoogle Scholar
  20. 20.
    Connell SD, Sinha R, Jain AK (2000) Recognition of unconstrained online Devanagari characters. In: IEEE proceedings of 15th international conference on pattern recognition, 2000, vol 2. pp 368–371Google Scholar
  21. 21.
    Joshi N, Sita G, Ramakrishnan A, Deepu V, Madhvanath S (2005) Machine recognition of online handwritten Devanagari characters. In: IEEE proceedings of eighth international conference on document analysis and recognition, 2005. pp 1156–1160Google Scholar
  22. 22.
    Bhattacharya U, Parui S, Shaw B, Bhattacharya K et al (2006) Neural combination of ann and hmm for handwritten Devanagari numeral recognition. In: Tenth international workshop on frontiers in handwriting recognitionGoogle Scholar
  23. 23.
    Takahashi K, Yasuda H, Matsumoto T (1997) A fast hmm algorithm for on-line handwritten character recognition. In: IEEE proceedings of the fourth international conference on document analysis and recognition, 1997, vol 1. pp 369–375Google Scholar
  24. 24.
    Prasad MM, Sukumar M, Ramakrishnan A (2009) Divide and conquer technique in online handwritten Kannada character recognition. In: Proceedings of the international workshop on multilingual OCR. pp 1–7Google Scholar
  25. 25.
    Lehal G, Singh C (2000) A Gurmukhi script recognition system. In: IEEE proceedings of the15th international conference on pattern recognition, 2000, vol 2. pp 557–560Google Scholar
  26. 26.
    Sharma A, Kumar R, Sharma R (2008) Online handwritten Gurmukhi character recognition using elastic matching. In: IEEE congress on image and signal processing, 2008. CISP’08, vol 2. pp 391–396Google Scholar
  27. 27.
    Sharma A (2009) Online handwritten Gurmukhi character recognition. Ph.D. thesis, Thapar UniversityGoogle Scholar
  28. 28.
    Sharma A, Kumar R, Sharma R (2010) Hmm-based online handwritten Gurmukhi character recognition. Mach Gr Vis Int J 19(4):439–449Google Scholar
  29. 29.
    Kumar R, Sharma RK, Sharma A (2015) Recognition of multi-stroke based online handwritten Gurmukhi aksharas. Proc Natl Acad Sci India Sect A Phys Sci 85(1):159–168CrossRefGoogle Scholar
  30. 30.
    Bharath A, Madhvanath S (2007) Hidden markov models for online handwritten Tamil word recognition. In: IEEE ninth international conference on document analysis and recognition, 2007. ICDAR 2007, vol 1. pp 506–510Google Scholar
  31. 31.
    Joshi N, Sita G, Ramakrishnan A, Madhvanath S (2004) Comparison of elastic matching algorithms for online Tamil handwritten character recognition. In: IEEE ninth international workshop on frontiers in handwriting recognition, 2004. IWFHR-9 2004. pp 444–449Google Scholar
  32. 32.
    Aparna K, Subramanian V, Kasirajan M, Prakash GV, Chakravarthy V, Madhvanath S (2004) Online handwriting recognition for Tamil. In: IEEE ninth international workshop on frontiers in handwriting recognition, 2004. IWFHR-9 2004. pp 438–443Google Scholar
  33. 33.
    Jayaraman A, Chandra SC, Srinivasa CV (2007) Modular approach to recognition of strokes in Telugu script. In: IEEE ninth international conference on document analysis and recognition, 2007. ICDAR 2007, vol 1. pp 501–505Google Scholar
  34. 34.
    Kline M (2013) Calculus: an intuitive and physical approach. Courier Corporation, ChelmsfordGoogle Scholar
  35. 35.
    Rabiner LR, Juang B-H (1986) An introduction to hidden markov models. IEEE ASSP Mag 3(1):4–16CrossRefGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2016

Authors and Affiliations

  1. 1.Computer Science and Engineering DepartmentThapar UniversityPatialaIndia

Personalised recommendations