Skip to main navigation Skip to search Skip to main content

The weight-block compressed sensing and its application to image reconstruction

  • Harbin Institute of Technology

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

Abstract

Compressed sensing (CS) is a novel theory for simultaneous data sampling and compression. The block compressed sensing can reduce the computation complexity and storage space for compressed sensing. In this paper, the weightblock compressed sensing technique coupled with the edge information is presented for improving the reconstructed image quality. Firstly, we segment the original image into block by block. Based on the edge characteristic of every sub-block, we will select the different measurements that needed for each block. This algorithm can preserve the edge and reduce the aliasing in comparison to the traditional block-compressed sensing. Experimental results show that the proposed algorithm can improve the PSNR comparing with the usual method.

Original languageEnglish
Title of host publicationProceedings of the 2012 2nd International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2012
Pages723-727
Number of pages5
DOIs
StatePublished - 2012
Event2012 2nd International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2012 - Harbin, Heilongjiang, China
Duration: 8 Dec 201210 Dec 2012

Publication series

NameProceedings of the 2012 2nd International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2012

Conference

Conference2012 2nd International Conference on Instrumentation and Measurement, Computer, Communication and Control, IMCCC 2012
Country/TerritoryChina
CityHarbin, Heilongjiang
Period8/12/1210/12/12

Keywords

  • Block
  • Compressed sensing
  • Sampling rate
  • Weight-block

Fingerprint

Dive into the research topics of 'The weight-block compressed sensing and its application to image reconstruction'. Together they form a unique fingerprint.

Cite this