A comparative study of filter based texture operators using Mahalanobis distance

Author

Grigorescu, S.E. ; Petkov, N. ; Kruizinga, P.

Author_Institution

Dept. of Math. & Comput. Sci., Groningen Univ., Netherlands

Volume

3

fYear

2000

fDate

2000

Firstpage

885

Abstract

Texture feature extraction operators, which comprise linear filtering, eventually followed by post-processing, are considered. The filters used are Laws´ masks (1980), filters derived from well-known discrete transforms, and Gabor filters. The post-processing step comprises nonlinear point operations and/or local statistics computation. The performance is measured by means of the Mahalanobis distance between clusters of feature vectors derived from different textures. The results show that post-processing improves considerably the performance of filter based texture operators

Keywords

discrete transforms; feature extraction; filtering theory; image texture; statistical analysis; Gabor filters; Laws masks; Mahalanobis distance; discrete transforms; feature vector clusters; filter based texture operators; linear filtering; local statistics computation; nonlinear point operations; post-processing step; texture feature extraction; Channel bank filters; Discrete Fourier transforms; Filter bank; Filtering; Fourier transforms; Gabor filters; Maximum likelihood detection; Nonlinear filters; Statistics; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2000. Proceedings. 15th International Conference on

Conference_Location

Barcelona

ISSN

1051-4651

Print_ISBN

0-7695-0750-6

Type

conf

DOI

10.1109/ICPR.2000.903685

Filename

903685