The advantage of using an HMM-based approach for faxed word recognition

@article{Elms1998TheAO,
  title={The advantage of using an HMM-based approach for faxed word recognition},
  author={A. J. Elms and Steve Procter and John Illingworth},
  journal={International Journal on Document Analysis and Recognition},
  year={1998},
  volume={1},
  pages={18-36}
}
A method for word recognition based on the use of hidden Markov models (HMMs) is described. An evaluation of its performance is presented using a test set of real printed documents that have been subjected to severe photocopy and fax transmission distortions. A comparison with a commercial OCR package highlights the inherent advantages of a segmentation-free recognition strategy when the word images are severely distorted, as well as the importance of using contextual knowledge. The HMM method… CONTINUE READING
Highly Cited
This paper has 46 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 30 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 30 references

The representation and recognition of text using hidden Markov models

  • A. J. Elms
  • PhD thesis,
  • 1996
2 Excerpts

The recognition of noisy polyfont printed text using combined HMMs

  • A. J. Elms, J. Illingworth
  • Proc. Fourth Annual Symp. Document Analysis and…
  • 1995
1 Excerpt

A hidden Markov model approach for degraded and connected character recognition

  • A. J. Elms, J. Illingworth
  • Proc. IEE European Workshop on Handwriting…
  • 1994
1 Excerpt

Combining hidden Markov models for the recognition of noisy printed characters

  • A. J. Elms, J. Illingworth
  • Proc. British Machine Vision Conf., pp 185–194,
  • 1994
1 Excerpt

Similar Papers

Loading similar papers…