K-WEB: Nonnegative dictionary learning for sparse image representations - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

K-WEB: Nonnegative dictionary learning for sparse image representations

Abstract

This paper presents a new nonnegative dictionary learning method, to decompose an input data matrix into a dictionary of nonnegative atoms, and a representation matrix with a strict l0-sparsity constraint. This constraint makes each input vector representable by a limited combination of atoms. The proposed method consists of two steps which are alternatively iterated: a sparse coding and a dictionary update stage. As for the dictionary update, an original method is proposed, which we call K-WEB, as it involves the computation of k WEighted Barycenters. The so designed algorithm is shown to outperform other methods in the literature that address the same learning problem, in different applications, and both with synthetic and "real" data, i.e. coming from natural images.
Fichier principal
Vignette du fichier
icip13_main.pdf (222.67 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00876018 , version 1 (23-10-2013)

Identifiers

  • HAL Id : hal-00876018 , version 1

Cite

Marco Bevilacqua, Aline Roumy, Christine Guillemot, Marie-Line Alberi Morel. K-WEB: Nonnegative dictionary learning for sparse image representations. IEEE International Conference on Image Processing (ICIP), Sep 2013, Melbourne, Australia. ⟨hal-00876018⟩
446 View
173 Download

Share

Gmail Facebook X LinkedIn More