Feature selection using Kernel based Local Fisher Discriminant Analysis for hyperspectral image classification

Author

Zhang, Guangyun ; Jia, Xiuping

Author_Institution

Sch. of Eng. & Inf. Technol., Univ. of New South Wales, Canberra, ACT, Australia

fYear

2011

fDate

24-29 July 2011

Firstpage

1728

Lastpage

1731

Abstract

Feature extraction is an important research aspect for hyperspectral remote sensing image classification to reduce the complexity and improve the classification accuracy. In this paper, a new feature extraction method, Kernel based Local Fisher Discriminative Analysis (KLFDA), is applied to hyperspectral remote sensing processing. This method integrates the advantages of conventional supervised Fisher Discriminative Analysis and unsupervised Locality Preserving Projection methods. Several experiments using the real images have been conducted, which indicate a high efficiency of this algorithm for hyperspectral image classification.

Keywords

feature extraction; geophysical image processing; image classification; remote sensing; statistical analysis; Fisher discriminant analysis; KLFDA; classification accuracy; feature extraction method; feature selection; hyperspectral image classification; hyperspectral remote sensing; kernel based local FDA; supervised Fisher discriminative analysis; unsupervised locality preserving projection; Feature extraction; Hyperspectral imaging; Image classification; Kernel; Principal component analysis; Gabor texture; KLFDA; feature extraction; hyperspectral images;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium (IGARSS), 2011 IEEE International

Conference_Location

Vancouver, BC

ISSN

2153-6996

Print_ISBN

978-1-4577-1003-2

Type

conf

DOI

10.1109/IGARSS.2011.6049569

Filename

6049569