Sparse representation of images using alternating linear programming

Yuanqing Li, Andrzej Cichocki

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)

Abstract

Based on nonnegative matrix factorization, a set of images are represented by a product of two nonnegative matrices, over-complete basis matrix (features) and nonnegative coefficient matrix (sparse coding) in this paper. Under the objective that both basis matrix and coefficient matrix are sparse, an alternating linear programming (ALP) algorithm is proposed. And the ALP algorithm is proved to be convergent. After the very large scale alternating linear programming problems are converted to equivalent sets of linear programming subproblems, they can be solved much more efficiently. Furthermore, the ALP algorithm is extended and generalized to an alternating iterative optimization (AIO) algorithm. At last, simulation results show the validity of the proposed approach.

Original languageEnglish
Title of host publicationProceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
PublisherIEEE Computer Society
Pages57-60
Number of pages4
ISBN (Print)0780379462, 9780780379466
DOIs
Publication statusPublished - 2003
Externally publishedYes
Event7th International Symposium on Signal Processing and Its Applications, ISSPA 2003 - Paris, France
Duration: 1 Jul 20034 Jul 2003

Publication series

NameProceedings - 7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
Volume1

Conference

Conference7th International Symposium on Signal Processing and Its Applications, ISSPA 2003
Country/TerritoryFrance
CityParis
Period1/07/034/07/03

Fingerprint

Dive into the research topics of 'Sparse representation of images using alternating linear programming'. Together they form a unique fingerprint.

Cite this