Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination

CVPR 2013

doi:10.1109/CVPR.2013.163 /cvpr/2013/sifre2013cvpr-rotation/

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.

PDF CVPR Semantic Scholar

Cite

Text

Sifre and Mallat. "Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.163

Markdown

[Sifre and Mallat. "Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/sifre2013cvpr-rotation/) doi:10.1109/CVPR.2013.163

BibTeX

@inproceedings{sifre2013cvpr-rotation,
  title     = {{Rotation, Scaling and Deformation Invariant Scattering for Texture Discrimination}},
  author    = {Sifre, Laurent and Mallat, Stephane},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.163},
  url       = {https://mlanthology.org/cvpr/2013/sifre2013cvpr-rotation/}
}