• DocumentCode
    3060018
  • Title

    Font segmentation of non-rotated, printed symbols in the vector representation

  • Author

    Weisteen, Katrine ; Taxt, Torfinn

  • Author_Institution
    Image Processing Group, NR Norwegian Comput. Center, Oslo, Norway
  • fYear
    1992
  • fDate
    30 Aug-3 Sep 1992
  • Firstpage
    669
  • Lastpage
    672
  • Abstract
    The ability of three different methods to separate nonrotated symbols of fonts with different slope angles is examined. The authors compare the properties of the elliptic Fourier descriptors of Kuhl and Giardina with the Fourier descriptors of Zahn and Roskies and the grid method
  • Keywords
    character recognition; character sets; image segmentation; elliptic Fourier descriptors; fonts; grid method; nonrotated symbols; printed symbols; slope angles; vector representation; Clocks; Covariance matrix; Fourier series; Gaussian distribution; Graphics; Image processing; Image segmentation; Technical drawing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 1992. Vol.II. Conference B: Pattern Recognition Methodology and Systems, Proceedings., 11th IAPR International Conference on
  • Conference_Location
    The Hague
  • Print_ISBN
    0-8186-2915-0
  • Type

    conf

  • DOI
    10.1109/ICPR.1992.201865
  • Filename
    201865