Principal component analysis with pre-emphasis for compression of hyperspectral imagery

Euisun Choi, Hyunsoo Choi, Chul Hee Lee

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

In this paper, we propose to use the principal component analysis for the compression of hyperspectral images. When hyperspectral images are compressed using conventional image compression algorithms, discriminant features of original data may be lost during compression process. In order to preserve such discriminant information, we first apply a linear feature extraction method to the original data. Then, we emphasize discriminant features and use the principal component analysis in order to compress the images whose discriminant features are enhanced. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.

Original languageEnglish
Title of host publication25th Anniversary IGARSS 2005
Subtitle of host publicationIEEE International Geoscience and Remote Sensing Symposium
Pages704-706
Number of pages3
DOIs
Publication statusPublished - 2005 Dec 1
Event2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005 - Seoul, Korea, Republic of
Duration: 2005 Jul 252005 Jul 29

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2

Other

Other2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005
CountryKorea, Republic of
CitySeoul
Period05/7/2505/7/29

Fingerprint

Principal component analysis
principal component analysis
imagery
compression
Image compression
Feature extraction
extraction method
Experiments
experiment

All Science Journal Classification (ASJC) codes

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

Cite this

Choi, E., Choi, H., & Lee, C. H. (2005). Principal component analysis with pre-emphasis for compression of hyperspectral imagery. In 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium (pp. 704-706). [1525203] (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2). https://doi.org/10.1109/IGARSS.2005.1525203
Choi, Euisun ; Choi, Hyunsoo ; Lee, Chul Hee. / Principal component analysis with pre-emphasis for compression of hyperspectral imagery. 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium. 2005. pp. 704-706 (International Geoscience and Remote Sensing Symposium (IGARSS)).
@inproceedings{56df1f3fd0e9499c82bc596ea438f4f8,
title = "Principal component analysis with pre-emphasis for compression of hyperspectral imagery",
abstract = "In this paper, we propose to use the principal component analysis for the compression of hyperspectral images. When hyperspectral images are compressed using conventional image compression algorithms, discriminant features of original data may be lost during compression process. In order to preserve such discriminant information, we first apply a linear feature extraction method to the original data. Then, we emphasize discriminant features and use the principal component analysis in order to compress the images whose discriminant features are enhanced. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.",
author = "Euisun Choi and Hyunsoo Choi and Lee, {Chul Hee}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/IGARSS.2005.1525203",
language = "English",
isbn = "0780390504",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
pages = "704--706",
booktitle = "25th Anniversary IGARSS 2005",

}

Choi, E, Choi, H & Lee, CH 2005, Principal component analysis with pre-emphasis for compression of hyperspectral imagery. in 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium., 1525203, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2, pp. 704-706, 2005 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2005, Seoul, Korea, Republic of, 05/7/25. https://doi.org/10.1109/IGARSS.2005.1525203

Principal component analysis with pre-emphasis for compression of hyperspectral imagery. / Choi, Euisun; Choi, Hyunsoo; Lee, Chul Hee.

25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium. 2005. p. 704-706 1525203 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Principal component analysis with pre-emphasis for compression of hyperspectral imagery

AU - Choi, Euisun

AU - Choi, Hyunsoo

AU - Lee, Chul Hee

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this paper, we propose to use the principal component analysis for the compression of hyperspectral images. When hyperspectral images are compressed using conventional image compression algorithms, discriminant features of original data may be lost during compression process. In order to preserve such discriminant information, we first apply a linear feature extraction method to the original data. Then, we emphasize discriminant features and use the principal component analysis in order to compress the images whose discriminant features are enhanced. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.

AB - In this paper, we propose to use the principal component analysis for the compression of hyperspectral images. When hyperspectral images are compressed using conventional image compression algorithms, discriminant features of original data may be lost during compression process. In order to preserve such discriminant information, we first apply a linear feature extraction method to the original data. Then, we emphasize discriminant features and use the principal component analysis in order to compress the images whose discriminant features are enhanced. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.

UR - http://www.scopus.com/inward/record.url?scp=33745727764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33745727764&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2005.1525203

DO - 10.1109/IGARSS.2005.1525203

M3 - Conference contribution

SN - 0780390504

SN - 9780780390508

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 704

EP - 706

BT - 25th Anniversary IGARSS 2005

ER -

Choi E, Choi H, Lee CH. Principal component analysis with pre-emphasis for compression of hyperspectral imagery. In 25th Anniversary IGARSS 2005: IEEE International Geoscience and Remote Sensing Symposium. 2005. p. 704-706. 1525203. (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2005.1525203