Classification with Scattering Operators
Computer Vision and Pattern Recognition
2013-11-21 v4
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.
Cite
@article{arxiv.1011.3023,
title = {Classification with Scattering Operators},
author = {Joan Bruna and Stéphane Mallat},
journal= {arXiv preprint arXiv:1011.3023},
year = {2013}
}
Comments
6 pages. CVPR 2011