In this talk, we address the issue of material classification from single images obtained under unknown viewpoint and illumination. It is demonstrated that materials can be classified using the joint distribution of intensity values over extremely compact neighbourhoods (starting from as small as 3x3 pixels square), and that this outperforms classification using filter banks with large support. It is also shown that the performance of filter banks is inferior to that of image patches with equivalent neighbourhoods. We develop a novel texton based representation which is suited to modelling this joint neighbourhood 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 classification performance surpasses that of recent state of the art filter bank based classifiers such as Leung and Malik (IJCV 01), Cula and Dana (IJCV 04), and Varma and Zisserman (IJCV 05).
Joint work with Andrew Zisserman at the University of Oxford