Word shape analysis for a hybrid recognition system

Article English OPEN
Powalka, RK; Sherkat, N; Whitrow, RJ;
(1997)
  • Publisher: Elsevier (not including Cell Press)

This paper describes two wholistic recognizers developed for use in a hybrid recognition system. The recognizers use information about the word shape. This information is strongly related to word zoning. One of the recognizers is explicitly limited by the accuracy of th... View more
  • References (8)

    17. Sh.A. Guberman, V.V. Rozentsveig. Algorithms for reading of handwritten texts (in Russian). Avtomatika i Telemekhanika, 5, 122-129 (1976).

    18. R.K. Powalka, N. Sherkat, R.J. Whitrow. A toolbox for recognition of varied handwritten script. First European Conf on Postal Technology JET POSTE 93, Nantes, France, 140-147 (June 1993).

    19. R.K. Powalka. An algorithm toolbox for on-line cursive script recognition. PhD Thesis, The Nottingham Trent University (1995).

    20. P.A.V. Hall, G.R. Dowling. Approximate string matching. ACM Computing Surveys, 12, 4, 381-402 (1980).

    21. J.J. Hull. Hypothesis generation in a computational model for visual word recognition. IEEE E.x,pert, 1, 3, 63-70 (1986).

    22. J. Franke. Statistical combination of multiple classifiers adapted on image parts. First European Conf, on Postal Technology JET POSTE 93, Nantes, France, 566-572 (June 1993).

    23. I.-M. Bertille, A.E. Yacoubi. Global cursive postal code recognition using Hidden Markov Models. First European Conf on Postal Technology JET POSTE 93, Nantes, France, 129-138 (June 1993).

    24. R.K. Powalka, N. Sherkat, R.J. Whitrow. Recognizer characterisation for combining handwriting recognition results at word level. Third Int. Con! on Document Analysis and Recognition ICDAR'95, Montreal, Canada. 68-73 (Aug. 1995).

  • Metrics
Share - Bookmark