Advertisement

BMVC92 pp 462-471 | Cite as

Evaluating a Hidden Markov Model Of Syntax In A Text Recognition System

  • Stephen Hanlon
  • Roger Boyle
Conference paper

Abstract

Recognition of text by whole word shapes generates a set of candidate words for each printed word. A Hidden Markov Model (HMM) of syntax may be used to find the most probable sequence of syntactic tags for a sentence given the sequence of candidate sets. Candidate sets are then reduced by removing all words which are not associated with the chosen tag. We show that the tagging performance of the HMM does not deteriorate despite an increasing proportion of mis-classified words. We also show that using the model significantly reduces the number of candidates.

Keywords

Hide Markov Model Viterbi Algorithm Test Sentence Word Image Chain Code 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    R D Boyle and R C Thomas. Interpretation of cursive script at the word level. Technical report, School of Computer Studies, University of Leeds, June 1990.Google Scholar
  2. [2]
    S A Dudani, K J Breeding, and R B Mcghee. Aircraft identification by moment invariants. IEEE Transactions on Computers ,26:39–45, 1977.CrossRefGoogle Scholar
  3. [3]
    G D Forney. The Viterbi algorithm. Proceedings of the IEEE ,61:268–278, March 1973.CrossRefMathSciNetGoogle Scholar
  4. [4]
    S J Hanlon and R D Boyle. Syntactic knowledge in word level text recognition. In R Beale and J Finlay, editors, Neural Networks and Pattern Recognition in Human-Computer Interaction. Ellis Horwood, 1992.Google Scholar
  5. [5]
    J Hull. Incorporation of a Markov Model of language syntax in a text recognition algorithm. In Symposium oh Document Analysis and Information Retrieval ,University of Nevada, Las Vegas. 16th -18th March, 1992.Google Scholar
  6. [6]
    J Hull. A computational theory of visual word recognition. Report number 88–07, University of NY at Buffalo, February 1988.Google Scholar
  7. [7]
    S Johansson, E Atwell, R Garside, and G Leech. The tagged LOB corpus. Norwegian Computing Centre for the Humanities, Bergen, 1986.Google Scholar
  8. [8]
    F G Keenan, L J Evett, and R J Whitrow. A large vocabulary stochastic syntax analyser for handwriting recognition. In First International Conference on Document Analysis and Recognition ,Saint-Malo, France. September 30 -October 2, 1991.Google Scholar
  9. [9]
    A Kundu, Y He, and P Bahl. Recognition of handwritten word : First and second order Hidden Markov Model based approach. Pattern Recognition ,22(3):283–297, 1989.CrossRefGoogle Scholar
  10. [10]
    M A O’Hair and M Kabrinsky. Beyond the OCR: reading whole words as single symbols based on the two dimensional, low frequency Fourier transform. In First International Conference on Document Analysis and Recognition ,Saint-Malo, France. September 30 -October 2, 1991.Google Scholar
  11. [11]
    T G Rose, L J Evett, and R J Whitrow. The use of semantic information as an aid to handwriting recognition. In First International Conference on Document Analysis and Recognition ,Saint-Malo, France. September 30 October 2, 1991.Google Scholar
  12. [12]
    M Shridhar and A Badreldin. High accuracy character recognition algorithm using Fourier and topological descriptors. Pattern Recognition ,17:515–524, 1984.CrossRefMATHGoogle Scholar
  13. [13]
    Q Zhang and R Boyle. A new clustering algorithm with multiple runs of iterative procedures. Pattern Recognition ,24(9):835–848, 1991.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 1992

Authors and Affiliations

  • Stephen Hanlon
    • 1
  • Roger Boyle
    • 1
  1. 1.Division of Artificial Intelligence, School of Computer StudiesThe University of LeedsUK

Personalised recommendations