A fast iterative kernel PCA feature extraction for hyperspectral images

Author

Liao, Wenzhi ; Pizurica, Aleksandra ; Philips, Wilfried ; Pi, Youguo

Author_Institution

Ghent Univ.-TELIN-IPI-IBBT, Ghent, Belgium

fYear

2010

fDate

26-29 Sept. 2010

Firstpage

1317

Lastpage

1320

Abstract

A fast iterative Kernel Principal Component Analysis (KPCA) is proposed to extract features from hyperspectral images. The proposed method is a kernel version of the Candid Covariance-Free Incremental Principal Component Analysis, which solves the eigenvectors through iteration. Without performing eigen decomposition on Gram matrix, our method can reduce the space complexity and time complexity greatly. Experimental results were validated in comparison with the standard KPCA and linear version methods.

Keywords

computational complexity; eigenvalues and eigenfunctions; feature extraction; geophysical image processing; iterative methods; matrix algebra; principal component analysis; Gram matrix; and complexity; candid covariance-free incremental principal component analysis; eigenvectors; fast iterative kernel PCA feature extraction; hyperspectral images; linear version methods; space complexity; Complexity theory; Covariance matrix; Feature extraction; Hyperspectral imaging; Kernel; Principal component analysis; Feature extraction; hyperspectral images; incremental principal component analysis; kernel vesion;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2010 17th IEEE International Conference on

Conference_Location

Hong Kong

ISSN

1522-4880

Print_ISBN

978-1-4244-7992-4

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2010.5651670

Filename

5651670