Multiscale sparse image representation with learned dictionaries
Published
Journal Article
This paper introduces a new framework for learning multiscale sparse representations of natural images with overcomplete dictionaries. Our work extends the K-SVD algorithm [1], which learns sparse single-scale dictionaries for natural images. Recent work has shown that the K-SVD can lead to state-of-the-art image restoration results [2, 3]. We show that these are further improved with a multiscale approach, based on a Quadtree decomposition. Our framework provides an alternative to multiscale pre-defined dictionaries such as wavelets, curvelets, and contourlets, with dictionaries optimized for the data and application instead of pre-modelled ones. © 2007 IEEE.
Full Text
Duke Authors
Cited Authors
- Mairal, J; Sapiro, G; Elad, M
Published Date
- December 1, 2006
Published In
Volume / Issue
- 3 /
International Standard Serial Number (ISSN)
- 1522-4880
Digital Object Identifier (DOI)
- 10.1109/ICIP.2007.4379257
Citation Source
- Scopus