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.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Texture classification: are filter banks necessary?


    Contributors:
    Varma, M. (author) / Zisserman, A. (author)


    Publication date :

    2003-01-01


    Size :

    383462 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Texture Classification: Are Filter Banks Necessary?

    Varma, M. / Zisserman, A. / IEEE | British Library Conference Proceedings | 2003


    Deep Filter Banks for Texture Recognition, Description, and Segmentation

    Cimpoi, M. / Maji, S. / Kokkinos, I. et al. | British Library Online Contents | 2016


    Necessary and sufficient condition for perfect reconstruction matrix filter banks [3813-71]

    Wang, J. / SPIE | British Library Conference Proceedings | 1999


    Order Statistic Filter Banks

    Arce, G. R. / Tian, M. / IEEE; Signal Processing Society | British Library Conference Proceedings | 1994


    Optimizing Gabor Filter Design for Texture Edge Detection and Classification

    Sandler, R. / Lindenbaum, M. | British Library Online Contents | 2009