An adaptive band selection algorithm for dimension reduction of hyperspectral images

Author

Xijun, Li ; Jun, Liu

Author_Institution

Sch. of Remote Sensing & Inf. Eng., Wuhan Univ., Wuhan

fYear

2009

fDate

11-12 April 2009

Firstpage

114

Lastpage

118

Abstract

An adaptive band selection algorithm for dimension reduction of hyperspectral images is proposed. Considering the spatial correlation and spectral correlation, a selection rule, referring to spectral information and its correlation, is constructed for band selection. To test the efficiency of this algorithm, K-means algorithm for unsupervised classification was applied on images generated from the algorithm. The results showed that the proposed algorithm reduced the computation amount and improved the classification accuracy.

Keywords

correlation methods; geophysical signal processing; image classification; remote sensing; spectral analysis; K-means unsupervised classification algorithm; adaptive band selection rule algorithm; hyperspectral image dimension reduction; remote sensing; spatial correlation; spectral correlation; Data mining; Discrete wavelet transforms; Feature extraction; Hospitals; Hyperspectral imaging; Hyperspectral sensors; Partitioning algorithms; Principal component analysis; Remote sensing; Wavelet analysis; Adaptive Band Selection; Dimension Reduction; Hyperspetral Image; K-means; Remote Sensing;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Analysis and Signal Processing, 2009. IASP 2009. International Conference on

Conference_Location

Taizhou

Print_ISBN

978-1-4244-3987-4

Type

conf

DOI

10.1109/IASP.2009.5054596

Filename

5054596