Fast two-level HMM decoding algorithm for large vocabulary handwriting recognition

@article{Koerich2004FastTH,
  title={Fast two-level HMM decoding algorithm for large vocabulary handwriting recognition},
  author={Alessandro L. Koerich and Robert Sabourin and Ching Y. Suen},
  journal={Ninth International Workshop on Frontiers in Handwriting Recognition},
  year={2004},
  pages={232-237}
}
To support large vocabulary handwriting recognition in standard computer platforms, a fast algorithm for hidden Markov model alignment is necessary. To address this problem, we propose a non-heuristic fast decoding algorithm which is based on hidden Markov model representation of characters. The decoding algorithm breaks up the computation of word likelihoods into two levels: state level and character level. Given an observation sequence, the two level decoding enables the reuse of character… CONTINUE READING
7 Citations
10 References
Similar Papers

References

Publications referenced by this paper.
Showing 1-10 of 10 references

Unconstrained handwritten word recognition using hidden markov models

  • A. El-Yacoubi, M. Gilloux, R. Sabourin, C. Y. Suen
  • IEEE Transactions on Pattern Analysis and Machine…
  • 1999
2 Excerpts

Legal amount recognition on french bank checks using a neural network– hidden markov model hybrid

  • E. Augustin, O. Baret, D. Price, S. Knerr
  • In Proc. 6th Int. Workshop on Frontiers in…
  • 1998
1 Excerpt

A prototype for Brazilian bankcheck recognition

  • L. L. Lee, M. E. Lizarraga, N. R. Gomes, A. L. Koerich
  • Automatic Bankcheck Processing,
  • 1997
1 Excerpt

Handwritten zip code recognition with multilayer networks

  • Y. LeCun, O. Matan, +5 authors L. Jackel
  • In Proc. 10th International Conference on Pattern…
  • 1990
1 Excerpt

Similar Papers

Loading similar papers…