Share Email Print
cover

Proceedings Paper

Curvilinear component analysis for nonlinear dimensionality reduction of hyperspectral images
Author(s): Marc Lennon; Gregoire Mercier; Marie-Catherine Mouchot; Laurence Hubert-Moy
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

This paper presents a multidimensional data nonlinear projection method applied to the dimensionality reduction of hyperspectral images. The method, called Curvilinear Component Analysis (CCA) consists in reproducing at best the topology of the joint distribution of the data in a projection subspace whose dimension is lower than the dimension of the initial space, thus preserving a maximum amount of information. The Curvilinear Distance Analysis (CDA) is an improvement of the CCA that allows data including high nonlinearities to be projected. Its interest for reducing the dimension of hyperspectral images is shown. The results are presented on real hyperspectral images and compared with usual linear projection methods.

Paper Details

Date Published: 28 January 2002
PDF: 12 pages
Proc. SPIE 4541, Image and Signal Processing for Remote Sensing VII, (28 January 2002); doi: 10.1117/12.454150
Show Author Affiliations
Marc Lennon, Ecole Nationale Superieure des Telecommunications de Bretagne (France)
Gregoire Mercier, Ecole Nationale Superieure des Telecommunications de Bretagne (France)
Marie-Catherine Mouchot, Ecole Nationale Superieure des Telecommunications de Bretagne (France)
Laurence Hubert-Moy, Univ. de Rennes II (France)


Published in SPIE Proceedings Vol. 4541:
Image and Signal Processing for Remote Sensing VII
Sebastiano Bruno Serpico, Editor(s)

© SPIE. Terms of Use
Back to Top