Intelligent selection of useful features for optimal feature-based classification

Author

Hwee Pink, Tan ; Ramanathan, Umaiyal

Author_Institution

Defence Sci. Organ. Nat. Labs., Singapore

Volume

7

fYear

2000

fDate

2000

Firstpage

3012

Abstract

In feature-based classification, each target class is characterised by a reference feature vector that comprises a combination of physical and statistical attributes. Different combinations of features are useful to distinguish amongst different target classes. In this study, an intelligent features selection method is proposed which selects features with minimum intra-class variance/inter-class variance. Classification results obtained with MSTAR data for tanks, APCs and trucks have shown a significant improvement in classification performance over using all measured features

Keywords

artificial intelligence; feature extraction; geophysical signal processing; geophysical techniques; geophysics computing; image classification; remote sensing; terrain mapping; APC; artificial intelligence; feature extraction; feature-based classification; geophysical measurement technique; image classification; intelligent features selection method; intelligent selection; inter-class variance; land surface; military vehicle; minimum intra-class variance; optimal feature-based classification; reference feature vector; remote sensing; tank; target class; terrain mapping; truck; useful feature; Classification algorithms; Data mining; Euclidean distance; Fractals; Laboratories; Length measurement; Physics computing; Telephony; Testing; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2000. Proceedings. IGARSS 2000. IEEE 2000 International

Conference_Location

Honolulu, HI

Print_ISBN

0-7803-6359-0

Type

conf

DOI

10.1109/IGARSS.2000.860319

Filename

860319