A unified unsupervised clustering algorithm and its first application to landcover classification

Author

Yu, Yong ; Bloch, Isabelle ; Trouvé, Alain

Author_Institution

Dept. TSL, Ecole Nat. Superieure des Telecommun., Paris, France

Volume

3

fYear

2003

fDate

6-10 April 2003

Abstract

The problem of classification is so fundamental that it has been intensively investigated by many researchers from different domains. In this paper, we present a novel unsupervised clustering algorithm derived from the techniques of probabilistic modeling which is implemented by a stochastic gradient algorithm. Then its application to challenging landcover classification based on Daedalus data of the SMART project is explored by combining both spectral feature and spatial contextual information. Our first experiments show its potential usefulness in remote sensing.

Keywords

feature extraction; image classification; pattern clustering; remote sensing; stochastic processes; Daedalus data; SMART project; landcover classification; probabilistic modeling; remote sensing; spatial contextual information; spectral feature information; stochastic gradient algorithm; unified unsupervised clustering algorithm; Classification algorithms; Clustering algorithms; Clustering methods; Image retrieval; Information retrieval; Optimization methods; Pattern recognition; Psychology; Remote sensing; Statistics;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1199568

Filename

1199568