By Topic

The reconstruction of high resolution image based on compressed sensing

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

3 Author(s)
Yan Zhou ; Department of Computer Science and Technology, Foshan University, Foshan 528000, China ; Yong Zhong ; Dong Wang

Constrained by traditional sampling theory, it is difficult to obtain high resolution image directly by signal acquisition system. The method that uses compressed sensing technology to measure the high resolution image and reconstruct with measurements breaks the bottleneck of Nyquist sampling theory, which is a new application for compressed sensing in image processing field. In CS, the reconstruction of super resolution image can be converted to how to construct measurement matrix and design reconstruction algorithm. For the reason that Gaussian measurement matrix requires a great number of high dimensional projection computations, we introduce sparse random projection into compressed sensing, proposing a measurement matrix which obeys sparse random projection distribution: sparse projection matrix. For the reason that the existing OMP algorithms require a lot of linear measurements to ensure accurate reconstruction, we propose an improved OMP algorithm. Experimental results show that, with sparse projection matrix and the improved OMP algorithm, high resolution image can be reconstructed accurately with little number of measurements.

Published in:

2010 International Conference on Machine Learning and Cybernetics  (Volume:2 )

Date of Conference:

11-14 July 2010