Loading [MathJax]/extensions/MathZoom.js
Texture classification: are filter banks necessary? | IEEE Conference Publication | IEEE Xplore

Texture classification: are filter banks necessary?


Abstract:

We question the role that large scale filter banks have traditionally played in texture classification. It is demonstrated that textures can be classified using the joint...Show More

Abstract:

We question the role that large scale filter banks have traditionally played in texture classification. It is demonstrated that textures can be classified using the joint distribution of intensity values over extremely compact neighborhoods (starting from as small as 3 /spl times/ 3 pixels square), and that this outperforms classification using filter banks with large support. We develop a novel texton based representation, which is suited to modeling this joint neighborhood distribution for MRFs. The representation is learnt from training images, and then used to classify novel images (with unknown viewpoint and lighting) into texture classes. The power of the method is demonstrated by classifying over 2800 images of all 61 textures present in the Columbia-Utrecht database. The classification performance surpasses that of recent state-of-the-art filter bank based classifiers such as Leung & Malik, Cula & Dana, and Varma & Zisserman.
Date of Conference: 18-20 June 2003
Date Added to IEEE Xplore: 15 July 2003
Print ISBN:0-7695-1900-8
Print ISSN: 1063-6919
Conference Location: Madison, WI, USA

Contact IEEE to Subscribe

References

References is not available for this document.