Morphological hat-transform scale spaces and their use in texture classification

Author

Jalba, A.C. ; Roerdink, J.B.T.M. ; Wilkinson, M.H.F.

Author_Institution

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

Volume

1

fYear

2003

fDate

14-17 Sept. 2003

Abstract

In this paper we present a multiscale morphological method for use in texture classification. A connected operator similar to the morphological hat-transform is defined, and two scale-space representations are built. The most important features are extracted from the scale spaces by unsupervised cluster analysis, and the resulting pattern vectors provide the input of a decision tree classifier. We obtain 93.5 % correct classification for the Brodatz texture database.

Keywords

decision trees; feature extraction; image texture; multidimensional signal processing; pattern classification; pattern clustering; unsupervised learning; Brodatz texture database; decision tree classifier; feature extraction; morphological hat-transform; multiscale morphological method; pattern vectors; scale spaces; texture classification; two scale-space representation; unsupervised cluster analysis; Classification tree analysis; Decision trees; Feature extraction; Filters; Functional analysis; Image analysis; Image databases; Mathematics; Shape; Spatial databases;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing, 2003. ICIP 2003. Proceedings. 2003 International Conference on

ISSN

1522-4880

Print_ISBN

0-7803-7750-8

Type

conf

DOI

10.1109/ICIP.2003.1246965

Filename

1246965