Effects of lossy wavelet-based compression on classification accuracy

Author

Schmanske, Brian M. ; Loew, Murray H.

Author_Institution

Dept. of Electr. & Comput. Eng., George Washington Univ., DC, USA

Volume

1

fYear

2001

fDate

2001

Firstpage

106

Abstract

The effect of 2D wavelet-based compression on overall classification accuracy is examined using simulated univariate images containing two classes of objects. Compressed images are analyzed using a maximum-likelihood estimator. Errors are separated into "pure" and "mixed" pixel categories. The study considers images of varying scale. The lowpass images resulting from wavelet decomposition showed similar results observed by decreasing spatial resolution. Specifically, a valley may occur in the relationship between classification error and compression ratio

Keywords

data compression; geophysical signal processing; geophysical techniques; image classification; image coding; remote sensing; terrain mapping; wavelet transforms; 2D wavelet method; accuracy; compression ratio; data compression; geophysical measurement technique; image classification; image compression; land surface; lossy wavelet based compression; lowpass image; maximum-likelihood estimator; remote sensing; terrain mapping; two object classes; univariate images; wavelet decomposition; Computational modeling; Computer simulation; Hyperspectral sensors; Image analysis; Image coding; Image resolution; Maximum likelihood estimation; Pixel; Spatial resolution; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 2001. IGARSS '01. IEEE 2001 International

Conference_Location

Sydney, NSW

Print_ISBN

0-7803-7031-7

Type

conf

DOI

10.1109/IGARSS.2001.976071

Filename

976071