Offline Handwritten Devanagari Word Recognition: An HMM Based Approach

  • Swapan Kumar Parui
  • Bikash Shaw
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4815)

Abstract

A hidden Markov model (HMM) for recognition of handwritten Devanagari words is proposed. The HMM has the property that its states are not defined a priori, but are determined automatically based on a database of handwritten word images. A handwritten word is assumed to be a string of several stroke primitives. These are in fact the states of the proposed HMM and are found using certain mixture distributions. One HMM is constructed for each word. To classify an unknown word image, its class conditional probability for each HMM is computed. The classification scheme has been tested on a small handwritten Devanagari word database developed recently. The classification accuracy is 87.71% and 82.89% for training and test sets respectively.

Keywords

Hidden Markov Model(HMM) Devanagari Word Recognition Stroke Primitives 

References

  1. 1.
    Rahman, A.F.R., Rahman, R., Fairhurst, M.C.: Recognition of handwritten Bengali characters: a novel multistage approach. Pattern Recognition 35, 997–1006 (2002)MATHCrossRefGoogle Scholar
  2. 2.
    Bhattacharya, U., Das, T.K., Datta, A., Parui, S.K., Chaudhuri, B.B.: A hybrid scheme for handprinted numeral recognition based on a self-organizing network and MLP classifiers. Int. J. Patt. Recog. & Art. Intell. 16(7), 845–864 (2002)CrossRefGoogle Scholar
  3. 3.
    Bhattacharya, U., Chaudhuri, B.B.: A majority voting scheme for multiresolution recognition of handprinted numerals. In: Proc. of the 7th ICDAR, Edinburgh, Scotland, vol. I, pp. 16–20 (2003)Google Scholar
  4. 4.
    Ramakrishnan, K.R., Srinivasan, S.H., Bhagavathy, S.: The independent components of characters are ’Strokes’. In: Proc. of the 5th ICDAR, pp. 414–417 (1999)Google Scholar
  5. 5.
    Lehal, G.S., Bhatt, N.: A recognition system for Devnagri and English handwritten numerals. Advances in Multimodal Interfaces. In: Tan, T., Shi, Y., Gao, W. (eds.) ICMI 2001. LNCS, vol. 1948, pp. 442–449. Springer, Heidelberg (2000)Google Scholar
  6. 6.
    Kim, G.: Recognition of offline handwritten words and its extension to phrase recognition, PhD Thesis. University of New York at Buffalo, USA (1996)Google Scholar
  7. 7.
    Guillevic, D.: Unconstrained Handwriting Recognition Applied to the Processing of Bank Cheques, Thesis of Doctor’s Degree in the Department of Computer Science at Concordia University, Canada (1995)Google Scholar
  8. 8.
    Park, H., Lee, S.: Off-line recognition of large-set handwritten characters with multiple hidden Markov models. Pattern Recognition 29, 231–244 (1996)CrossRefGoogle Scholar
  9. 9.
    Hull, J.J.: A database for handwritten text recognition research. IEEE Trans. Patt. Anal. Mach.Intel. 16, 550–554 (1994)CrossRefGoogle Scholar
  10. 10.
    Otsu, N.: A threshold selection method from gray-level histograms. IEEE Trans. on Systems, Man, and Cybernetics 9, 62–66 (1979)CrossRefGoogle Scholar
  11. 11.
    Bhattacharya, U., Parui, S.K., Shaw, B., Bhattacharya, K.: Neural Combination of ANN and HMM for Handwritten Devnagari Numeral Recognition. 10th-IWFHR, pp. 613–618 (2006)Google Scholar
  12. 12.
    Rabiner, L.R.: A tutorial on hidden Markov models and selected applications in speech recognition. Proceedings of the IEEE 77(2), 257–286 (1989)CrossRefGoogle Scholar
  13. 13.
    Fukunaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press, San Diego (1980)Google Scholar
  14. 14.
    Parui, S. K., Bhattacharya, U., Shaw, B., Poddar, D.: A Novel Hidden Markov Models for Recognition of Bangla Characters. 3rd-WCVGIP, pp. 174–179 (2006)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Swapan Kumar Parui
    • 1
  • Bikash Shaw
    • 1
  1. 1.Computer Vision & Pattern Recognition Unit, Indian Statistical Institute, 203, B.T. Road, Kolkata, 700108India

Personalised recommendations