Geometrical image estimation with orthogonal bandlet bases

Peyré, Gabriel; Le Pennec, Erwan; Dossal, Charles; Mallat, Stéphane

Peyré, Gabriel; Le Pennec, Erwan; Dossal, Charles; Mallat, Stéphane (2007), Geometrical image estimation with orthogonal bandlet bases, in Van de Ville, Dimitri; Goyal, Vivek K.; Papadakis, Manos, Wavelets XII - Proceedings, International Society for Optical Engineering. http://dx.doi.org/10.1117/12.731227

Type

Communication / Conférence

External document link

http://hal.archives-ouvertes.fr/hal-00365606

Date

2007

Conference title

Wavelets XII

Conference date

2007-08

Conference city

San Diego

Conference country

États-Unis

Book title

Wavelets XII - Proceedings

Book author

Van de Ville, Dimitri; Goyal, Vivek K.; Papadakis, Manos

Publisher

International Society for Optical Engineering

Series title

SPIE Proceedings

Series number

6701

Abstract (EN)

This article presents the first adaptive quasi minimax estimator for geometrically regular images in the white noise model. This estimator is computed using a thresholding in an adapted orthogonal bandlet basis optimized for the noisy observed image. In order to analyze the quadratic risk of this best basis denoising, the thresholding in an orthogonal bandlets basis is recasted as a model selection process. The resulting estimator is computed with a fast algorithm whose theoretical performance can be derived. This efficiency is confirmed through numerical experiments on natural images.

Subjects / Keywords

model selection; minimax estimation; bandlets; Image denoising