Download:
|
by Manik Varma, Andrew Zisserman
in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition
http://www.robots.ox.ac.uk/~vgg/publications/html/../papers/varma03.ps.gz
Add To MetaCart
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 neighbouthoods (starting from as small as 3 x 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 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 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
Citations
|
2961
|
Pattern Classification and Scene Analysis
– Duda, Hart
- 1973
|
|
2322
|
Stochastic relaxation, Gibbs distributions and the Bayesian restoration of images
– Geman, Geman
- 1984
|
|
361
|
Texture Synthesis by Non-parametric Sampling
– Efros, Leung
- 1999
|
|
310
|
Computer Vision, A Modern Approach
– Forsyth, Ponce
- 2003
|
|
254
|
Koenderink,"Reflectance and texture of real world surfaces
– Dana, Ginneken, et al.
- 1999
|
|
254
|
Pyramid-Based Texture Analysis/Synthesis
– Heeger, Bergen
- 1995
|
|
235
|
Image Quilting for Texture Synthesis and Transfer
– EFROS, FREEMAN
|
|
166
|
Multiresolution sampling procedure for analysis and synthesis of textured images
– BONET
- 1997
|
|
145
|
A parametric texture model based on joint statistics of complex wavelet coefficients
– Portilla, Simoncelli
- 2000
|
|
133
|
Filters, random fields and maximum entropy (frame
– Zhu, Wu, et al.
- 1998
|
|
108
|
Representing and recognizing the visual appearance of materials using three-dimensional textons
– Leung, Malik
|
|
98
|
Markov Random Field Modeling in Image Analisys
– Li
- 2001
|
|
58
|
Constructing models for content-based image retrieval
– Schmid
|
|
41
|
Compact representation of bidirectional texture functions
– Cula, Dana
- 2001
|
|
35
|
Classifying images of materials: achieving viewpoint and illumination independence
– Varma, Zisserman
- 2002
|
|
26
|
A cluster-based statistical model for object detection
– Rikert, Jones, et al.
- 1999
|
|
25
|
Statistical cues for domain specific image segmentation with performance analysis
– Konishi, Yuille
- 1999
|
|
20
|
Gool. A compact model for viewpoint dependent texture synthesis
– Zalesny, Van
- 2000
|
|
19
|
Pyramid-based texture analysis /synthesis
– HEEGER, BERGEN
- 1995
|
