An unsupervised clustering method using the entropy minimization

Author

Palubinskas, Gintautas ; Descombes, Xavier ; Kruggel, Frithjof

Author_Institution

Deutsches Zentrum fur Luft- und Raumfahrt (DLR) e.V., Wessling, Germany

Volume

2

fYear

1998

fDate

16-20 Aug 1998

Firstpage

1816

Abstract

We address the problem of unsupervised clustering using a Bayesian framework. The entropy is considered to define a priori and enables one to overcome the problem of defining a priori the number of clusters and an initialization of their centers. A deterministic algorithm derived from the standard k-means algorithm is proposed and compared with simulated annealing algorithms. The robustness of the proposed method is shown on a magnetic resonance images database containing 65 volumetric (3D) images

Keywords

Bayes methods; image classification; magnetic resonance imaging; minimum entropy methods; optimisation; probability; Bayes method; Gaussian likelihood; deterministic algorithm; entropy minimization; image classification; k-means algorithm; magnetic resonance images; probability; simulated annealing; unsupervised clustering; Bayesian methods; Clustering algorithms; Clustering methods; Entropy; Histograms; Level set; Minimization methods; Neuroscience; Robustness; Simulated annealing;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 1998. Proceedings. Fourteenth International Conference on

Conference_Location

Brisbane, Qld.

ISSN

1051-4651

Print_ISBN

0-8186-8512-3

Type

conf

DOI

10.1109/ICPR.1998.712082

Filename

712082