Classification with Scattering Operators

CVPR 2011 pp. 1561-1566

doi:10.1109/CVPR.2011.5995635 /cvpr/2011/bruna2011cvpr-classification/

Abstract

A scattering vector is a local descriptor including multiscale and multi-direction co-occurrence information. It is computed with a cascade of wavelet decompositions and complex modulus. This scattering representation is locally translation invariant and linearizes deformations. A supervised classification algorithm is computed with a PCA model selection on scattering vectors. State of the art results are obtained for handwritten digit recognition and texture classification.

PDF CVPR Semantic Scholar

Cite

Text

Bruna and Mallat. "Classification with Scattering Operators." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011. doi:10.1109/CVPR.2011.5995635

Markdown

[Bruna and Mallat. "Classification with Scattering Operators." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2011.](https://mlanthology.org/cvpr/2011/bruna2011cvpr-classification/) doi:10.1109/CVPR.2011.5995635

BibTeX

@inproceedings{bruna2011cvpr-classification,
  title     = {{Classification with Scattering Operators}},
  author    = {Bruna, Joan and Mallat, Stéphane},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2011},
  pages     = {1561-1566},
  doi       = {10.1109/CVPR.2011.5995635},
  url       = {https://mlanthology.org/cvpr/2011/bruna2011cvpr-classification/}
}