Compression of hyperspectral images with pre-emphasis

Chulhee Lee, Euisun Choi

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

Abstract

In this paper, we propose compression algorithms for hyperspectral images with pre-emphasizing discriminantly dominant features. When hyperspectral images are compressed using a conventional image compression algorithm, which has been developed to minimize mean squared errors, discriminant features of the original data may be lost during compression process since such discriminant features may not be large in energies. In order to address this problem, we propose to apply preprocessing prior to compression in order to preserve such discriminant information. In particular, we preemphasize discriminantly dominant features before a compression algorithm is applied. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.

Original languageEnglish
Title of host publication2004 Sensor Array and Multichannel Signal Processing Workshop
Pages653-656
Number of pages4
Publication statusPublished - 2004 Dec 1
Event2004 Sensor Array and Multichannel Signal Processing Workshop - Barcelona, Spain
Duration: 2004 Jul 182004 Jul 21

Other

Other2004 Sensor Array and Multichannel Signal Processing Workshop
CountrySpain
CityBarcelona
Period04/7/1804/7/21

Fingerprint

Image compression
Experiments

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Cite this

Lee, C., & Choi, E. (2004). Compression of hyperspectral images with pre-emphasis. In 2004 Sensor Array and Multichannel Signal Processing Workshop (pp. 653-656)
Lee, Chulhee ; Choi, Euisun. / Compression of hyperspectral images with pre-emphasis. 2004 Sensor Array and Multichannel Signal Processing Workshop. 2004. pp. 653-656
@inproceedings{6b9639f639a54cf4a9983a4aa77ebabb,
title = "Compression of hyperspectral images with pre-emphasis",
abstract = "In this paper, we propose compression algorithms for hyperspectral images with pre-emphasizing discriminantly dominant features. When hyperspectral images are compressed using a conventional image compression algorithm, which has been developed to minimize mean squared errors, discriminant features of the original data may be lost during compression process since such discriminant features may not be large in energies. In order to address this problem, we propose to apply preprocessing prior to compression in order to preserve such discriminant information. In particular, we preemphasize discriminantly dominant features before a compression algorithm is applied. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.",
author = "Chulhee Lee and Euisun Choi",
year = "2004",
month = "12",
day = "1",
language = "English",
isbn = "0780385454",
pages = "653--656",
booktitle = "2004 Sensor Array and Multichannel Signal Processing Workshop",

}

Lee, C & Choi, E 2004, Compression of hyperspectral images with pre-emphasis. in 2004 Sensor Array and Multichannel Signal Processing Workshop. pp. 653-656, 2004 Sensor Array and Multichannel Signal Processing Workshop, Barcelona, Spain, 04/7/18.

Compression of hyperspectral images with pre-emphasis. / Lee, Chulhee; Choi, Euisun.

2004 Sensor Array and Multichannel Signal Processing Workshop. 2004. p. 653-656.

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

TY - GEN

T1 - Compression of hyperspectral images with pre-emphasis

AU - Lee, Chulhee

AU - Choi, Euisun

PY - 2004/12/1

Y1 - 2004/12/1

N2 - In this paper, we propose compression algorithms for hyperspectral images with pre-emphasizing discriminantly dominant features. When hyperspectral images are compressed using a conventional image compression algorithm, which has been developed to minimize mean squared errors, discriminant features of the original data may be lost during compression process since such discriminant features may not be large in energies. In order to address this problem, we propose to apply preprocessing prior to compression in order to preserve such discriminant information. In particular, we preemphasize discriminantly dominant features before a compression algorithm is applied. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.

AB - In this paper, we propose compression algorithms for hyperspectral images with pre-emphasizing discriminantly dominant features. When hyperspectral images are compressed using a conventional image compression algorithm, which has been developed to minimize mean squared errors, discriminant features of the original data may be lost during compression process since such discriminant features may not be large in energies. In order to address this problem, we propose to apply preprocessing prior to compression in order to preserve such discriminant information. In particular, we preemphasize discriminantly dominant features before a compression algorithm is applied. Experiments show that the proposed method provides improved classification accuracies than existing compression algorithms.

UR - http://www.scopus.com/inward/record.url?scp=28244439076&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28244439076&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:28244439076

SN - 0780385454

SP - 653

EP - 656

BT - 2004 Sensor Array and Multichannel Signal Processing Workshop

ER -

Lee C, Choi E. Compression of hyperspectral images with pre-emphasis. In 2004 Sensor Array and Multichannel Signal Processing Workshop. 2004. p. 653-656