Advertisement

Erkennung handgeschriebener Wortsequenzen

  • Urs-Viktor Marti
  • Horst Bunke
Conference paper
Part of the Informatik aktuell book series (INFORMAT)

Zusammenfassung

Die vorliegende Arbeit stellt ein System vor, welches in der Lage ist, mit einfachen Satzmodellen eine Sequenz von hand-geschriebenen Wörtern zu erkennen. Hierzu werden Satzmodelle, welche ursprünglich in der Spracherkennung entwickelt wurden, verwendet. Durch die Verwendung dieser statistischen Modelle kann eine Reduzie-rung der Fehlerrate des Worterkenners von 23% auf 18% bzw. 15% er-reicht werden.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [BS89]
    R. Bozinovic, S.N. Srihari. Off-line cursive Script word recognition. IEEE Trans, on Pattern Analysis and Machine Intelligence, ll(l): 68–83, January 1989.Google Scholar
  2. [CDDEB+87]
    H. Cerf-Danon, A.-M. Derouault, M. El-Beze, B. Merialdo, and S. Soudoplatoff. Speech recognition experiment with lO’OOO words dictionary. In P.A. Devijver and J. Kittler, editors, Pattern Recognition Theory and Applications, volume F30 of NATO AS I Series. Springer Verlag, 1987.Google Scholar
  3. [GSS95]
    V. Govindaraju, R.K. Srihari, and S.N. Srihari. Handwritten text recognition. In A. L. Spitz and A. Dengel, editors, Document Analysis Systems, pages 288–304. World Scientific, 1995.Google Scholar
  4. [Hul92]
    J.J. Hull. Incorporation of a markov model of language syntax in a text recognition algorithm. In Proc. Symp. Document Analysis and Information Retrieval, pages 174–185, 1992.Google Scholar
  5. [Jel90]
    F. Jelinek. Self-organized language modeling for speech recognition. In A. Waibel and K.-F. Lee, editors, Readings in Speech Recognition, pages 450–506. Morgan Kaufmann Publishers, Inc., 1990.Google Scholar
  6. [JLG78]
    S. Johansson, G.N. Leech, and H. Goodluck. Manual of Information to accompany the Lancaster-Oslo/Bergen Corpus of British English, for use with digital Computers. Department of English, University of Oslo, Oslo, 1978.Google Scholar
  7. [KBH96]
    G. Kaufmann, H. Bunke, and T.M. Ha. Recognition of cursively handwritten words using a combined normalization/perturabation approach. In Proc. of the IWFHR-5, pages 17–22, 1996.Google Scholar
  8. [LB93]
    E. Lecolinet and Olivier Baret. Cursive word recognition: Methods and strategies. In Sebastiano Impedovo, editor, Fundamentals in Handwrit-ing Recognition, pages 235–263. NATO ASI Series, 1993.Google Scholar
  9. [Ots79]
    N. Otsu. A threshold selection method from gray-level histograms. IEEE Transaction on Systems, Man and Cybernetics, SMC-9:pp. 62–66, 1979.Google Scholar
  10. [RJ93]
    L. Rabiner and B.-H. Juang. Fundamentals of Speech Recognition. Prentice Hall, 1993.Google Scholar
  11. [SB93]
    R.K. Srihari and C. M. Baltus. Incorporating syntactic constraints in recognizing handwritten sentences. In Proc. of IJCAN-93, Chambery, volume 2, pages 1262–1267, 1993.Google Scholar
  12. [Sch96]
    J. Schuermann. Pattern Classification. John Wiley and Sons, Inc., 1996.Google Scholar
  13. [Sen94]
    A.W. Senior. Offline Cursive Handwriting Recognition using Recurrent Neural Networks. PhD thesis, Trinity Hall, Cambridge, England, September 1994.Google Scholar
  14. [SGS93]
    S.N. Srihari, V. Govindaraju, and A. Shekhawat. Interpretation of handwritten addresses in us mailstream. In ICDAR, pages 291–304, 1993.Google Scholar
  15. [Sto97]
    A. Stolcke. Linguistic knowledge and empirical methods in speech reco gnition. AI Magazine, Winter 1997: 25–31, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • Urs-Viktor Marti
    • 1
  • Horst Bunke
    • 1
  1. 1.Institut für Informatik und angewandte MathematikUniversität BernBernGermany

Personalised recommendations