Compression of hyperspectral images with discriminant features enhanced

Chulhee Lee, Euisun Choi, Taeuk Jeong, Sangwook Lee, Jonghwa Lee

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

In this paper, we propose two compression methods for hyperspectral images with discriminant features enhanced. Generally, when hyperspectral images are compressed with conventional image compression algorithms, which mainly minimize mean squared errors, discriminant features of the original data may not be well preserved since they may not be necessarily large in energy. In this paper, we propose two compression methods that do preserve the discriminant information. In the first method, we enhanced the discriminant features and then compressed the enhanced data using conventional image compression algorithms such as 3D JPEG 2000. In the second method, we applied a feature extraction method and extracted the discriminantly dominant feature vectors. By examining the dominant feature vectors, we determined the discriminant usefulness of each spectral band. Based on these findings, we determined the bit allocation of each spectral band assuming 2D compression methods are used. Experiments show that the proposed methods effectively preserved the discriminant information and yielded improved classification accuracies compared to existing compression algorithms. Copy; 2010 Society of Photo-Optical Instrumentation Engineers.

Original languageEnglish
Article number041764
JournalJournal of Applied Remote Sensing
Volume4
Issue number1
DOIs
Publication statusPublished - 2010 Dec 1

Fingerprint

compression
extraction method
method
energy
experiment
spectral band

All Science Journal Classification (ASJC) codes

  • Earth and Planetary Sciences(all)

Cite this

Lee, Chulhee ; Choi, Euisun ; Jeong, Taeuk ; Lee, Sangwook ; Lee, Jonghwa. / Compression of hyperspectral images with discriminant features enhanced. In: Journal of Applied Remote Sensing. 2010 ; Vol. 4, No. 1.
@article{493c54fd58714700abc0c87d9149d6f1,
title = "Compression of hyperspectral images with discriminant features enhanced",
abstract = "In this paper, we propose two compression methods for hyperspectral images with discriminant features enhanced. Generally, when hyperspectral images are compressed with conventional image compression algorithms, which mainly minimize mean squared errors, discriminant features of the original data may not be well preserved since they may not be necessarily large in energy. In this paper, we propose two compression methods that do preserve the discriminant information. In the first method, we enhanced the discriminant features and then compressed the enhanced data using conventional image compression algorithms such as 3D JPEG 2000. In the second method, we applied a feature extraction method and extracted the discriminantly dominant feature vectors. By examining the dominant feature vectors, we determined the discriminant usefulness of each spectral band. Based on these findings, we determined the bit allocation of each spectral band assuming 2D compression methods are used. Experiments show that the proposed methods effectively preserved the discriminant information and yielded improved classification accuracies compared to existing compression algorithms. Copy; 2010 Society of Photo-Optical Instrumentation Engineers.",
author = "Chulhee Lee and Euisun Choi and Taeuk Jeong and Sangwook Lee and Jonghwa Lee",
year = "2010",
month = "12",
day = "1",
doi = "10.1117/1.3517719",
language = "English",
volume = "4",
journal = "Journal of Applied Remote Sensing",
issn = "1931-3195",
publisher = "SPIE",
number = "1",

}

Compression of hyperspectral images with discriminant features enhanced. / Lee, Chulhee; Choi, Euisun; Jeong, Taeuk; Lee, Sangwook; Lee, Jonghwa.

In: Journal of Applied Remote Sensing, Vol. 4, No. 1, 041764, 01.12.2010.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Compression of hyperspectral images with discriminant features enhanced

AU - Lee, Chulhee

AU - Choi, Euisun

AU - Jeong, Taeuk

AU - Lee, Sangwook

AU - Lee, Jonghwa

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In this paper, we propose two compression methods for hyperspectral images with discriminant features enhanced. Generally, when hyperspectral images are compressed with conventional image compression algorithms, which mainly minimize mean squared errors, discriminant features of the original data may not be well preserved since they may not be necessarily large in energy. In this paper, we propose two compression methods that do preserve the discriminant information. In the first method, we enhanced the discriminant features and then compressed the enhanced data using conventional image compression algorithms such as 3D JPEG 2000. In the second method, we applied a feature extraction method and extracted the discriminantly dominant feature vectors. By examining the dominant feature vectors, we determined the discriminant usefulness of each spectral band. Based on these findings, we determined the bit allocation of each spectral band assuming 2D compression methods are used. Experiments show that the proposed methods effectively preserved the discriminant information and yielded improved classification accuracies compared to existing compression algorithms. Copy; 2010 Society of Photo-Optical Instrumentation Engineers.

AB - In this paper, we propose two compression methods for hyperspectral images with discriminant features enhanced. Generally, when hyperspectral images are compressed with conventional image compression algorithms, which mainly minimize mean squared errors, discriminant features of the original data may not be well preserved since they may not be necessarily large in energy. In this paper, we propose two compression methods that do preserve the discriminant information. In the first method, we enhanced the discriminant features and then compressed the enhanced data using conventional image compression algorithms such as 3D JPEG 2000. In the second method, we applied a feature extraction method and extracted the discriminantly dominant feature vectors. By examining the dominant feature vectors, we determined the discriminant usefulness of each spectral band. Based on these findings, we determined the bit allocation of each spectral band assuming 2D compression methods are used. Experiments show that the proposed methods effectively preserved the discriminant information and yielded improved classification accuracies compared to existing compression algorithms. Copy; 2010 Society of Photo-Optical Instrumentation Engineers.

UR - http://www.scopus.com/inward/record.url?scp=80055005278&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055005278&partnerID=8YFLogxK

U2 - 10.1117/1.3517719

DO - 10.1117/1.3517719

M3 - Article

AN - SCOPUS:80055005278

VL - 4

JO - Journal of Applied Remote Sensing

JF - Journal of Applied Remote Sensing

SN - 1931-3195

IS - 1

M1 - 041764

ER -