Wavelet feature extraction and genetic feature selection for multisource data

Author

Ulfarsson, Magnus Orn ; Benediktsson, Jon Atli ; Sveinsson, Johannes R.

Author_Institution

Eng. Res. Inst., Iceland Univ., Reykjavik, Iceland

Volume

6

fYear

2002

fDate

2002

Firstpage

3329

Abstract

A linear feature extraction method based on the discrete wavelet transform (DWT) is applied. A binary genetic algorithm is used to select the best features from the different DWT representations in terms of cost. The feature extraction/selection methods are applied in classification of multisource remote sensing and geographic data. In experiments, the proposed methods performed well in terms of overall accuracies as compared to results obtained with other well-known feature extraction/selection methods.

Keywords

discrete wavelet transforms; feature extraction; genetic algorithms; geography; geophysical signal processing; image classification; image representation; neural nets; remote sensing; sensor fusion; wavelet transforms; DWT; binary genetic algorithm; classification; discrete wavelet transform; feature selection; genetic feature selection; geographic data; linear feature extraction; multisource data; remote sensing; representations; wavelet feature extraction; Costs; Discrete wavelet transforms; Energy resolution; Feature extraction; Genetic algorithms; Genetic mutations; Neural networks; Remote sensing; Signal resolution; Wavelet domain;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2002. IGARSS '02. 2002 IEEE International

Print_ISBN

0-7803-7536-X

Type

conf

DOI

10.1109/IGARSS.2002.1027172

Filename

1027172