Creating and sharing knowledge for telecommunications

On the Role of Sparse and Redundant Representations in Image Processing

Elad, M. ; Figueiredo, M. A. T. ; Ma, Y.

Proceedings of the IEEE Vol. 98, Nº 6, pp. 972 - 982, June, 2010.

ISSN (print): 0018-9219
ISSN (online):

Journal Impact Factor: 4,613 (in 2008)

Digital Object Identifier: 10.1109/JPROC.2009.2037655

Abstract
Much of the progressmade in image processing in
the past decades can be attributed to better modeling of image
content and a wise deployment of these models in relevant
applications. This path ofmodels spans fromthe simple ‘2-norm
smoothness through robust, thus edge preserving, measures of
smoothness (e.g. total variation), and until the very recent
models that employ sparse and redundant representations. In
this paper, we review the role of this recent model in image
processing, its rationale, andmodels related to it. As it turns out,
the field of image processing is one of the main beneficiaries
from the recent progress made in the theory and practice of
sparse and redundant representations. We discuss ways to
employ these tools for various image-processing tasks and
present several applications in which state-of-the-art results
are obtained.