Statistical texture characterization from discrete wavelet representations

Author

Van de Wouwer, G. ; Scheunders, P. ; Van Dyck, D.

Author_Institution

Dept. of Phys., Antwerp Univ., Belgium

Volume

8

Issue

4

fYear

1999

fDate

4/1/1999 12:00:00 AM

Firstpage

592

Lastpage

598

Abstract

We conjecture that texture can be characterized by the statistics of the wavelet detail coefficients and therefore introduce two feature sets: (1) the wavelet histogram signatures which capture all first order statistics using a model based approach and (2) the wavelet co-occurrence signatures, which reflect the coefficients´ second-order statistics. The introduced feature sets outperform the traditionally used energy. Best performance is achieved by combining histogram and co-occurrence signatures

Keywords

discrete wavelet transforms; feature extraction; image classification; image representation; image texture; statistical analysis; discrete wavelet representations; feature sets; first order statistics; image texture; model based approach; second-order statistics; statistical texture characterization; wavelet co-occurrence signatures; wavelet detail coefficients; wavelet histogram signatures; Discrete wavelet transforms; Energy resolution; Feature extraction; Histograms; Image analysis; Image resolution; Image segmentation; Image texture analysis; Statistics; Wavelet analysis;

fLanguage

English

Journal_Title

Image Processing, IEEE Transactions on

Publisher

ieee

ISSN

1057-7149

Type

jour

DOI

10.1109/83.753747

Filename

753747