IS = { zkontrolovano 07 Dec 2003 },
  UPDATE  = { 2003-10-14 },
  author =       {De Ridder, Dick and Franc, Vojtech},
  title =        {Rubust subspace mixture models using $t$-distributions},
  booktitle =    {BMVC 2003: Proceedings of the 14th British
                  Machine Vision Conference},
  book_pages =   {813},
  pages =        {319--328},
  year =         {2003},
  editor =       {Harvey, Richard and Bangham, Andrew},
  venue =        {Norwich, UK},
  day =          {9--11},
  keywords =     {EM, t-distribution, mixture models },
  month =        {September},
  publisher =    {BMVA},
  address =      {London, UK},
  project =      {MIRACLE ICA1-CT-2000-70002, MSM 212300013},
  isbn =         {1-901725-24-3},
  annote =       {
    Probabilistic subspace mixture models, as proposed over the last few
    years, are interesting methods for learning image manifolds, i.e. nonlinear
    subspaces of spaces in which images are represented as vectors by their
    grey-values. However, for many practical applications, where outliers
    are common, these methods still lack robustness. Here, the idea of
    robust mixture modelling by t-distributions is combined with probabilistic
    subspace mixture models. The resulting robust subspace mixture model
    is shown experimentally to give advantages in density estimation and
    classification of image data sets},