Principal component analysis for compression of hyperspectral images

Research output: Contribution to conferencePaper

38 Citations (Scopus)

Abstract

In this paper, we explore the possibility to use the principal component analysis for compression of hyperspectral images. When the principal component analysis is applied to AVIRIS data that has 220 channels, we found that most energy is concentrated on a few eigenvalues, indicating that it may be possible to compress hyperspectral images significantly. The performance of the proposed algorithm is evaluated in terms of SNR and classification accuracies of selected classes. Experiments with AVIRIS data show promising results.

Original languageEnglish
Pages97-99
Number of pages3
Publication statusPublished - 2001 Dec 1
Event2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001) - Sydney, NSW, Australia
Duration: 2001 Jul 92001 Jul 13

Other

Other2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001)
CountryAustralia
CitySydney, NSW
Period01/7/901/7/13

Fingerprint

AVIRIS
Principal component analysis
principal component analysis
compression
eigenvalue
energy
experiment
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Lim, S., Sohn, K. H., & Lee, C. (2001). Principal component analysis for compression of hyperspectral images. 97-99. Paper presented at 2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001), Sydney, NSW, Australia.
Lim, Sunghyun ; Sohn, Kwang Hoon ; Lee, Chulhee. / Principal component analysis for compression of hyperspectral images. Paper presented at 2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001), Sydney, NSW, Australia.3 p.
@conference{1d46ffbd50724f1aac5c3440d1b90b31,
title = "Principal component analysis for compression of hyperspectral images",
abstract = "In this paper, we explore the possibility to use the principal component analysis for compression of hyperspectral images. When the principal component analysis is applied to AVIRIS data that has 220 channels, we found that most energy is concentrated on a few eigenvalues, indicating that it may be possible to compress hyperspectral images significantly. The performance of the proposed algorithm is evaluated in terms of SNR and classification accuracies of selected classes. Experiments with AVIRIS data show promising results.",
author = "Sunghyun Lim and Sohn, {Kwang Hoon} and Chulhee Lee",
year = "2001",
month = "12",
day = "1",
language = "English",
pages = "97--99",
note = "2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001) ; Conference date: 09-07-2001 Through 13-07-2001",

}

Lim, S, Sohn, KH & Lee, C 2001, 'Principal component analysis for compression of hyperspectral images' Paper presented at 2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001), Sydney, NSW, Australia, 01/7/9 - 01/7/13, pp. 97-99.

Principal component analysis for compression of hyperspectral images. / Lim, Sunghyun; Sohn, Kwang Hoon; Lee, Chulhee.

2001. 97-99 Paper presented at 2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001), Sydney, NSW, Australia.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Principal component analysis for compression of hyperspectral images

AU - Lim, Sunghyun

AU - Sohn, Kwang Hoon

AU - Lee, Chulhee

PY - 2001/12/1

Y1 - 2001/12/1

N2 - In this paper, we explore the possibility to use the principal component analysis for compression of hyperspectral images. When the principal component analysis is applied to AVIRIS data that has 220 channels, we found that most energy is concentrated on a few eigenvalues, indicating that it may be possible to compress hyperspectral images significantly. The performance of the proposed algorithm is evaluated in terms of SNR and classification accuracies of selected classes. Experiments with AVIRIS data show promising results.

AB - In this paper, we explore the possibility to use the principal component analysis for compression of hyperspectral images. When the principal component analysis is applied to AVIRIS data that has 220 channels, we found that most energy is concentrated on a few eigenvalues, indicating that it may be possible to compress hyperspectral images significantly. The performance of the proposed algorithm is evaluated in terms of SNR and classification accuracies of selected classes. Experiments with AVIRIS data show promising results.

UR - http://www.scopus.com/inward/record.url?scp=0035573431&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035573431&partnerID=8YFLogxK

M3 - Paper

SP - 97

EP - 99

ER -

Lim S, Sohn KH, Lee C. Principal component analysis for compression of hyperspectral images. 2001. Paper presented at 2001 International Geoscience and Remote Sensing Symposium (IGARSS 2001), Sydney, NSW, Australia.