Curvilinear Component Analysis for nonlinear dimensionality reduction of hyperspectral images

被引：7

作者：

Lennon, M ^{[1
]}

Mercier, G ^{[1
]}

Mouchot, MC ^{[1
]}

Hubert-Moy, L ^{[1
]}

机构：

[1] ENST Bretagne, Dept ITI, F-29285 Brest, France

来源：

IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING VII | 2002年 / 4541卷

关键词：

hyperspectral; dimensionality reduction; curvilinear component analysis;

D O I：

10.1117/12.454150

中图分类号：

TP7 [遥感技术];

学科分类号：

081102 ; 0816 ; 081602 ; 083002 ; 1404 ;

摘要：

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.

引用

页码：157 / 168

页数：12

共 15 条

[1]

[Anonymous], 1997, SPRINGER SERIES INFO

[2] Curvilinear component analysis: A self-organizing neural network for nonlinear mapping of data sets [J].