RestoPPXA_Lab

Higher Edu - Research dev card
Development from the higher education and research community
  • Creation or important update: 04/03/11
  • Minor correction: 08/09/11

RestoPPXA_Lab : Matlab toolbox for image restoration

This software was developed (or is under development) within the higher education and research community. Its stability can vary (see fields below) and its working state is not guaranteed.
  • Web site
  • System:
  • Current version: v2.0 - August 2011
  • License(s): CeCILL-B
  • Status: stable release
  • Support: maintained, no ongoing development
  • Designer(s): Nelly Pustelnik
  • Contact designer(s): nelly.pustelnik_@_ims-bordeaux.fr
  • Laboratory, service:

 

General software features

This software allows to restore images degraded by a convolution operator and a noise (Poisson or Gaussian). The method behind is based on convex criterion minimization. This criterion includes a data fidelity term (Kullback-Leibler divergence or l2 norm), an indicator function (e.g. pixel range constraint) and a regularization term that can be:

  • a l1 norm applied on frame (DTT) coefficients
  • a total variation term (TV)
  • an hybrid regularization (l1 + TV)

PPXA (Parallel ProXimal Algorithm) is used to minimize the resulting criterion.

Context in which the software is used

This software allows to restore images degraded by a convolution operator and a noise (Poisson or Gaussian).

Publications related to the software
  • N. Pustelnik, Méthodes proximales pour la résolution de problèmes inverses. Application à la Tomographie par Emission de Positrons. Thèse Université Paris-Est, 2010.
  • N. Pustelnik, C. Chaux, and J.-C. Pesquet, Hybrid regularization for data restoration in the presence of Poisson noise, European Signal Processing Conference (EUSIPCO), Glasgow, Scotland, August 24-28, 2009.
  • http://nellypustelnik.perso.sfr.fr/