Effective image block compressed sensing with quantized measurement

Ying Hou, Yanning Zhang

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

4 Scopus citations

Abstract

In this paper, we propose an effective quantized block compressed sensing algorithm using projected Landweber based on vicariate shrinkage (BCS PL-BS) for natural images. Moreover, an improved noise variance estimation method is presented by using soft-thresholding vicariate shrinkage model for wavelet-based image demising, which can more effectively estimate the noise variance and achieve better image reconstruction quality. Experimental results demonstrate that the reconstruction performances of the proposed algorithm outperform those of several state-of-the-art compressed sensing algorithms.

Original languageEnglish
Title of host publicationProceedings - DCC 2014
Subtitle of host publication2014 Data Compression Conference
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages407
Number of pages1
ISBN (Print)9781479938827
DOIs
StatePublished - 2014
Event2014 Data Compression Conference, DCC 2014 - Snowbird, UT, United States
Duration: 26 Mar 201428 Mar 2014

Publication series

NameData Compression Conference Proceedings
ISSN (Print)1068-0314

Conference

Conference2014 Data Compression Conference, DCC 2014
Country/TerritoryUnited States
CitySnowbird, UT
Period26/03/1428/03/14

Keywords

  • bivariate shrinkage
  • compressed sensing
  • dual-tree discrete wavelet transform
  • projected Landweber

Fingerprint

Dive into the research topics of 'Effective image block compressed sensing with quantized measurement'. Together they form a unique fingerprint.

Cite this