Multiscale asymmetry signatures for texture analysis

Author

Van de Wouver, G. ; Weyn, B. ; Van Dyck, D.

Author_Institution

Dept. of Phys., Antwerp Univ., Belgium

Volume

3

fYear

2004

fDate

24-27 Oct. 2004

Firstpage

1517

Abstract

This paper investigates model-based texture feature extraction from image multiscale representations. This approach offers a better texture characterization compared to using the classical energy output of a multiscale filterbank. The existing models assume symmetric density functions and we observe that this assumption is violated for some texture classes. This property is exploited to obtain improved texture characterization which can be used for texture classification, segmentation and retrieval.

Keywords

channel bank filters; feature extraction; image classification; image representation; image retrieval; image segmentation; image texture; wavelet transforms; image multiscale representation; image retrieval; image segmentation; model-based texture feature extraction; multiscale asymmetry signature; multiscale filterbank; symmetric density function; wavelet transform; Density functional theory; Feature extraction; Filters; Histograms; Image analysis; Image segmentation; Image texture analysis; Physics; Wavelet analysis; Wavelet coefficients;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2004. ICIP '04. 2004 International Conference on

ISSN

1522-4880

Print_ISBN

0-7803-8554-3

Type

conf

DOI

10.1109/ICIP.2004.1421353

Filename

1421353