Locality-preserving discriminant analysis for hyperspectral image classification using local spatial information

Wei Li; Saurabh Prasad; Zhen Ye; James E. Fowler; Minshan Cui

doi:10.1109/IGARSS.2012.6351702

Locality-preserving discriminant analysis for hyperspectral image classification using local spatial information

Wei Li^*
, Saurabh Prasad
, Zhen Ye
, James E. Fowler
, Minshan Cui

^*Corresponding author for this work

Research output: Contribution to conference › Paper › peer-review

6 Citations (Scopus)

Abstract

Locality-preserving projection as well as local Fisher discriminant analysis is applied for dimensionality reduction of hyperspectral imagery based on both spatial and spectral information. These techniques preserve the local geometric structure of hyperspectral data into a low-dimensional subspace wherein a Gaussian-mixture-model classifier is then considered. In the proposed classification system, local spatial information - which is expected to be more multimodal than strictly spectral features - is used. Results with experimental hyperspectral data demonstrate that this system outperforms traditional classification approaches.

Original language	English
Pages	4134-4137
Number of pages	4
DOIs	https://doi.org/10.1109/IGARSS.2012.6351702
Publication status	Published - 2012
Externally published	Yes
Event	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 - Munich, Germany Duration: 22 Jul 2012 → 27 Jul 2012

Conference

Conference	2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012
Country/Territory	Germany
City	Munich
Period	22/07/12 → 27/07/12

Keywords

Dimensionality reduction
hyperspectral data
linear discriminant analysis
pattern classification

Access to Document

10.1109/IGARSS.2012.6351702

Cite this

@conference{b941d592dc3d44b3b0311c74345dc0b7,

title = "Locality-preserving discriminant analysis for hyperspectral image classification using local spatial information",

abstract = "Locality-preserving projection as well as local Fisher discriminant analysis is applied for dimensionality reduction of hyperspectral imagery based on both spatial and spectral information. These techniques preserve the local geometric structure of hyperspectral data into a low-dimensional subspace wherein a Gaussian-mixture-model classifier is then considered. In the proposed classification system, local spatial information - which is expected to be more multimodal than strictly spectral features - is used. Results with experimental hyperspectral data demonstrate that this system outperforms traditional classification approaches.",

keywords = "Dimensionality reduction, hyperspectral data, linear discriminant analysis, pattern classification",

author = "Wei Li and Saurabh Prasad and Zhen Ye and Fowler, \{James E.\} and Minshan Cui",

year = "2012",

doi = "10.1109/IGARSS.2012.6351702",

language = "English",

pages = "4134--4137",

note = "2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012 ; Conference date: 22-07-2012 Through 27-07-2012",

}

TY - CONF

T1 - Locality-preserving discriminant analysis for hyperspectral image classification using local spatial information

AU - Li, Wei

AU - Prasad, Saurabh

AU - Ye, Zhen

AU - Fowler, James E.

AU - Cui, Minshan

PY - 2012

Y1 - 2012

N2 - Locality-preserving projection as well as local Fisher discriminant analysis is applied for dimensionality reduction of hyperspectral imagery based on both spatial and spectral information. These techniques preserve the local geometric structure of hyperspectral data into a low-dimensional subspace wherein a Gaussian-mixture-model classifier is then considered. In the proposed classification system, local spatial information - which is expected to be more multimodal than strictly spectral features - is used. Results with experimental hyperspectral data demonstrate that this system outperforms traditional classification approaches.

AB - Locality-preserving projection as well as local Fisher discriminant analysis is applied for dimensionality reduction of hyperspectral imagery based on both spatial and spectral information. These techniques preserve the local geometric structure of hyperspectral data into a low-dimensional subspace wherein a Gaussian-mixture-model classifier is then considered. In the proposed classification system, local spatial information - which is expected to be more multimodal than strictly spectral features - is used. Results with experimental hyperspectral data demonstrate that this system outperforms traditional classification approaches.

KW - Dimensionality reduction

KW - hyperspectral data

KW - linear discriminant analysis

KW - pattern classification

UR - https://www.scopus.com/pages/publications/84873191300

U2 - 10.1109/IGARSS.2012.6351702

DO - 10.1109/IGARSS.2012.6351702

M3 - Paper

AN - SCOPUS:84873191300

SP - 4134

EP - 4137

T2 - 2012 32nd IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2012

Y2 - 22 July 2012 through 27 July 2012

ER -

Locality-preserving discriminant analysis for hyperspectral image classification using local spatial information

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this