Classification with scattering operators

Author

Bruna, Joan ; Mallat, Stéphane

Author_Institution

CMAP, Ecole Polytech., Palaiseau, France

fYear

2011

fDate

20-25 June 2011

Firstpage

1561

Lastpage

1566

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.

Keywords

handwritten character recognition; image classification; image texture; learning (artificial intelligence); principal component analysis; wavelet transforms; PCA model selection; complex modulus; handwritten digit recognition; locally translation invariant; multidirection co-occurrence information; multiscale co-occurrence information; scattering operators; scattering representation; scattering vector; supervised classification algorithm; texture classification; wavelet decompositions; Convolution; Databases; Principal component analysis; Scattering; Training; Wavelet transforms;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on

Conference_Location

Providence, RI

ISSN

1063-6919

Print_ISBN

978-1-4577-0394-2

Type

conf

DOI

10.1109/CVPR.2011.5995635

Filename

5995635