Parametric Dictionary Design for Sparse Coding

Abstract : This paper introduces a new dictionary design method for sparse coding of a class of signals. It has been shown that one can sparsely approximate some natural signals using an overcomplete set of parametric functions, e.g. [1], [2]. A problem in using these parametric dictionaries is how to choose the parameters. In practice these parameters have been chosen by an expert or through a set of experiments. In the sparse approximation context, it has been shown that an incoherent dictionary is appropriate for the sparse approximation methods. In this paper we first characterize the dictionary design problem, subject to a minimum coherence constraint. Then we briefly explain that equiangular tight frames have minimum coherence. The parametric dictionary design is then to find an admissible dictionary close to being tight frame. The complexity of the problem does not allow it to be solved exactly. We introduce a practical method to approximately solve it. Some experiments show the advantages one gets by using these dictionaries. Index Terms—Sparse Approximation, Dictionary Design, Incoherent Dictionary, Parametric Dictionary, Gammatone Filter Banks, Exact Sparse Recovery.
Type de document :
Communication dans un congrès
Rémi Gribonval. SPARS'09 - Signal Processing with Adaptive Sparse Structured Representations, Apr 2009, Saint Malo, France. 2009
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00369364
Contributeur : Ist Rennes <>
Soumis le : jeudi 19 mars 2009 - 14:52:54
Dernière modification le : jeudi 22 novembre 2018 - 14:34:31
Document(s) archivé(s) le : mardi 8 juin 2010 - 21:40:41

Fichier

14.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00369364, version 1

Citation

Mehrdad Yaghoobi, Laurent Daudet, Mike E. Davies. Parametric Dictionary Design for Sparse Coding. Rémi Gribonval. SPARS'09 - Signal Processing with Adaptive Sparse Structured Representations, Apr 2009, Saint Malo, France. 2009. 〈inria-00369364〉

Partager

Métriques

Consultations de la notice

285

Téléchargements de fichiers

428