Classification performance of reduced color band hyperspectral imagery from JPEG2000 decompressed data

Author

Garces, Maximiliano ; Usevitch, Bryan E.

Author_Institution

Univ. of Texas at El Paso, TX, USA

fYear

2004

fDate

1-4 Aug. 2004

Firstpage

120

Lastpage

124

Abstract

This paper presents a study of the impact of the compression of a hyperspectral image (HSI) using the JPEG2000 standard. The impact measure was the accuracy of the classification. The goal of this study is to present an approach that proposes to reduce the computational and memory costs of processing this type of data. The results presented show a savings of storage and savings in the computational time by decompressing only a small portion of the color-bands.

Keywords

image classification; image coding; image colour analysis; principal component analysis; HSI compression; JPEG2000 decompressed data; PCA transform; color band transformation; color-band decompression; computational time reduction; hyperspectral imagery classification accuracy; reduced color band hyperspectral images; spectral signature; storage requirements reduction; Computational efficiency; Electromagnetic analysis; Hyperspectral imaging; Hyperspectral sensors; Image coding; Image storage; Infrared sensors; Object detection; Principal component analysis; Transform coding;

fLanguage

English

Publisher

ieee

Conference_Titel

Digital Signal Processing Workshop, 2004 and the 3rd IEEE Signal Processing Education Workshop. 2004 IEEE 11th

Print_ISBN

0-7803-8434-2

Type

conf

DOI

10.1109/DSPWS.2004.1437924

Filename

1437924