• DocumentCode
    384286
  • Title

    Fast on-line learning of point distribution models

  • Author

    Al-Shaher, Abdullah A. ; Hancock, Edwin R.

  • Author_Institution
    Dept. of Comput. Sci., York Univ., UK
  • Volume
    2
  • fYear
    2002
  • fDate
    2002
  • Firstpage
    208
  • Abstract
    We present a fast procedure for training point distribution models (PDM) using the EM algorithm. Rather than estimating the class means and covariance matrices needed to construct the PDM, the method iteratively refines the eigenvectors of the covariance matrix using a gradient ascent technique. We evaluate the method on the problem of learning class-structure of Arabic characters.
  • Keywords
    Gaussian distribution; character recognition; eigenvalues and eigenfunctions; iterative methods; unsupervised learning; Arabic character class-structure; EM algorithm; class means; covariance matrices; eigenvectors; fast on-line learning; gradient ascent technique; iterative refinement; learning; point distribution models; training; Computer science; Covariance matrix; Deformable models; Gaussian distribution; Iterative algorithms; Parameter estimation; Principal component analysis; Shape; Training data; Unsupervised learning;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Pattern Recognition, 2002. Proceedings. 16th International Conference on
  • ISSN
    1051-4651
  • Print_ISBN
    0-7695-1695-X
  • Type

    conf

  • DOI
    10.1109/ICPR.2002.1048274
  • Filename
    1048274