A two-stage feature extraction for hyperspectral image data classification

Guey Shya Chen; Li-Wei Ko; Bor Chen Kuo; Shu Chuan Shih

A two-stage feature extraction for hyperspectral image data classification

Guey Shya Chen^*, Li-Wei Ko, Bor Chen Kuo, Shu Chuan Shih

^*Corresponding author for this work

Institute of Bioinformatics and Systems Biology

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

4 Scopus citations

Abstract

In this study, a two-stage feature extraction algorithm cooperated with feature selection is proposed for improving hyperspectral data classification. The first stage feature extraction extracts the features for separating all classes and second stage feature extraction extracts the features for separating individual pair of classes, which can not be well separated in first stage feature space. Then feature selection is applied for selecting the best features. Real data experimental result show that the proposed 2-stage feature extraction outperforms single stage feature extraction.

Original language	English
Pages	1212-1215
Number of pages	4
State	Published - 1 Dec 2004
Event	2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004 - Anchorage, AK, United States Duration: 20 Sep 2004 → 24 Sep 2004

Conference

Conference	2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004
Country	United States
City	Anchorage, AK
Period	20/09/04 → 24/09/04

Keywords

Feature extraction
Hyperspectral data classification

Access to Document

Link to publication in Scopus

Fingerprint Dive into the research topics of 'A two-stage feature extraction for hyperspectral image data classification'. Together they form a unique fingerprint.

Cite this

@conference{b7bb816ca2854087bd82df7ef49f86aa,

title = "A two-stage feature extraction for hyperspectral image data classification",

abstract = "In this study, a two-stage feature extraction algorithm cooperated with feature selection is proposed for improving hyperspectral data classification. The first stage feature extraction extracts the features for separating all classes and second stage feature extraction extracts the features for separating individual pair of classes, which can not be well separated in first stage feature space. Then feature selection is applied for selecting the best features. Real data experimental result show that the proposed 2-stage feature extraction outperforms single stage feature extraction.",

keywords = "Feature extraction, Hyperspectral data classification",

author = "Chen, {Guey Shya} and Li-Wei Ko and Kuo, {Bor Chen} and Shih, {Shu Chuan}",

year = "2004",

month = dec,

day = "1",

language = "English",

pages = "1212--1215",

note = "null ; Conference date: 20-09-2004 Through 24-09-2004",

}

A two-stage feature extraction for hyperspectral image data classification. / Chen, Guey Shya; Ko, Li-Wei; Kuo, Bor Chen; Shih, Shu Chuan.

2004. 1212-1215 Paper presented at 2004 IEEE International Geoscience and Remote Sensing Symposium Proceedings: Science for Society: Exploring and Managing a Changing Planet. IGARSS 2004, Anchorage, AK, United States.

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

TY - CONF

T1 - A two-stage feature extraction for hyperspectral image data classification

AU - Chen, Guey Shya

AU - Ko, Li-Wei

AU - Kuo, Bor Chen

AU - Shih, Shu Chuan

PY - 2004/12/1

Y1 - 2004/12/1

N2 - In this study, a two-stage feature extraction algorithm cooperated with feature selection is proposed for improving hyperspectral data classification. The first stage feature extraction extracts the features for separating all classes and second stage feature extraction extracts the features for separating individual pair of classes, which can not be well separated in first stage feature space. Then feature selection is applied for selecting the best features. Real data experimental result show that the proposed 2-stage feature extraction outperforms single stage feature extraction.

AB - In this study, a two-stage feature extraction algorithm cooperated with feature selection is proposed for improving hyperspectral data classification. The first stage feature extraction extracts the features for separating all classes and second stage feature extraction extracts the features for separating individual pair of classes, which can not be well separated in first stage feature space. Then feature selection is applied for selecting the best features. Real data experimental result show that the proposed 2-stage feature extraction outperforms single stage feature extraction.

KW - Feature extraction

KW - Hyperspectral data classification

UR - http://www.scopus.com/inward/record.url?scp=15944371561&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:15944371561

SP - 1212

EP - 1215

Y2 - 20 September 2004 through 24 September 2004

ER -