Share Email Print

Proceedings Paper

Highly overcomplete sparse coding
Author(s): Bruno A. Olshausen
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

This paper explores sparse coding of natural images in the highly overcomplete regime. We show that as the overcompleteness ratio approaches l0x, new types of dictionary elements emerge beyond the classical Gabor function shape obtained from complete or only modestly overcomplete sparse coding. These more diverse dic­ tionaries allow images to be approximated with lower L1 norm (for a fixed SNR), and the coefficients exhibit steeper decay. We also evaluate the learned dictionaries in a denoising task, showing that higher degrees of overcompleteness yield modest gains in peformance.

Paper Details

Date Published: 14 March 2013
PDF: 9 pages
Proc. SPIE 8651, Human Vision and Electronic Imaging XVIII, 86510S (14 March 2013); doi: 10.1117/12.2013504
Show Author Affiliations
Bruno A. Olshausen, Univ. of California, Berkeley (United States)

Published in SPIE Proceedings Vol. 8651:
Human Vision and Electronic Imaging XVIII
Bernice E. Rogowitz; Thrasyvoulos N. Pappas; Huib de Ridder, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?