Classification with scattering operators

Joan Bruna; Stéphane Mallat

doi:10.1109/CVPR.2011.5995635

Classification with scattering operators

Joan Bruna, Stéphane Mallat

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

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.

Original language	English (US)
Title of host publication	2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011
Publisher	IEEE Computer Society
Pages	1561-1566
Number of pages	6
ISBN (Print)	9781457703942
DOIs	https://doi.org/10.1109/CVPR.2011.5995635
State	Published - 2011

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
ISSN (Print)	1063-6919

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition

Access to Document

10.1109/CVPR.2011.5995635

Cite this

Classification with scattering operators. / Bruna, Joan; Mallat, Stéphane.

2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011. IEEE Computer Society, 2011. p. 1561-1566 5995635 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

@inproceedings{6ec95dacef824e5fb690d251aaa4fc14,

title = "Classification with scattering operators",

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.",

author = "Joan Bruna and St{\'e}phane Mallat",

year = "2011",

doi = "10.1109/CVPR.2011.5995635",

language = "English (US)",

isbn = "9781457703942",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE Computer Society",

pages = "1561--1566",

booktitle = "2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011",

}

TY - GEN

T1 - Classification with scattering operators

AU - Bruna, Joan

AU - Mallat, Stéphane

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=80052870739&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80052870739&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2011.5995635

DO - 10.1109/CVPR.2011.5995635

M3 - Conference contribution

AN - SCOPUS:80052870739

SN - 9781457703942

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 1561

EP - 1566

BT - 2011 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2011

PB - IEEE Computer Society

ER -

Classification with scattering operators

Abstract

Publication series

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this