The Community for Technology Leaders
Green Image
Issue No. 08 - August (2009 vol. 31)
ISSN: 0162-8828
pp: 1429-1443
Sabri Boutemedjet , Université de Sherbrooke, Sherbrooke
Nizar Bouguila , Concordia University, Montreal
Djemel Ziou , Université de Sherbrooke, Sherbrooke
This paper presents an unsupervised approach for feature selection and extraction in mixtures of generalized Dirichlet (GD) distributions. Our method defines a new mixture model that is able to extract independent and non-Gaussian features without loss of accuracy. The proposed model is learned using the Expectation-Maximization algorithm by minimizing the message length of the data set. Experimental results show the merits of the proposed methodology in the categorization of object images.
Unsupervised learning, mixture models, feature selection, dimensionality reduction, generalized Dirichlet mixture, EM, MML, information theory, object image categorization.

N. Bouguila, S. Boutemedjet and D. Ziou, "A Hybrid Feature Extraction Selection Approach for High-Dimensional Non-Gaussian Data Clustering," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 31, no. , pp. 1429-1443, 2008.
83 ms
(Ver 3.3 (11022016))