Abstract | ||
---|---|---|
An affine invariant representation is constructed with a cascade of invariants, which preserves information for classification. A joint translation and rotation invariant representation of image patches is calculated with a scattering transform. It is implemented with a deep convolution network, which computes successive wavelet transforms and modulus non-linearities. Invariants to scaling, shearing and small deformations are calculated with linear operators in the scattering domain. State-of-the-art classification results are obtained over texture databases with uncontrolled viewing conditions. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/CVPR.2013.163 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
deep convolution network,deformation invariant scattering,linear operator,rotation invariant representation,texture discrimination,modulus non-linearities,image patch,scattering domain,small deformation,joint translation,affine invariant representation,state-of-the-art classification result,texture,scattering,image classification,neural,wavelet transforms,image texture,network,convolution,affine,scaling,rotation,classification,deformation,shearing,wavelet,invariant,computer architecture,translation | Affine transformation,Computer vision,Image texture,Convolution,Invariant (mathematics),Artificial intelligence,Scattering,Geometry,Scaling,Mathematics,Wavelet transform,Wavelet | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1063-6919 |
Citations | PageRank | References |
110 | 4.16 | 12 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Laurent Sifre | 1 | 2470 | 94.03 |
Stéphane Mallat | 2 | 4107 | 718.30 |