Details

Autor(en) / Beteiligte

• Figueiredo, Málrio A. T.
• Leitão, José M. N.
• Jain, Anil K.
• Pelillo, Marcello
• Hancock, Edwin R.

Titel

On Fitting Mixture Models

Ist Teil von

• Energy Minimization Methods in Computer Vision and Pattern Recognition, 1999, p.54-69

Ort / Verlag

Berlin, Heidelberg: Springer Berlin Heidelberg

Erscheinungsjahr

1999

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• Consider the problem of fitting a finite Gaussian mixture, with an unknown number of components, to observed data. This paper proposes a new minimum description length (MDL) type criterion, termed MMDL(for mixture MDL), to select the number of components of the model. MMDLis based on the identification of an “equivalent sample size”, for each component, which does not coincide with the full sample size. We also introduce an algorithm based on the standard expectationmaximization (EM) approach together with a new agglomerative step, called agglomerative EM (AEM). The experiments here reported have shown that MMDLo utperforms existing criteria of comparable computational cost. The good behavior of AEM, namely its good robustness with respect to initialization, is also illustrated experimentally.