Image Reconstruction Based on Support Similarity between Lines CoSaMP Algorithm

DOI

10.2991/fmsmt-17.2017.113How to use a DOI?

Keywords

Image reconstruction, Support similarity, Lines CoSaMP algorithm

Abstract

The algorithm of compressive sampling matching pursuit (CoSaMP) is the performance of this algorithm is restricted to the choose of it's initial support set. If inaccurately choose the initial support set, it will not only affect the accuracy of reconsitution, but also reduce the speed of reconsitution. In order to solve this problem, the stucture of image in sparse domain is introduced into CoSaMP algorithm, and the concept of support set similarity is presented in this paper, and we raised one kind of CoSaMP algorithm which is based on Support Similarity between Lines and uses the high similarity between the adjoining rows in one digital image. The result of this experiment shows that under the condition with same sampling frequency, when don't increase the time complexity of the algorithm, the algorithm which we have raised has higher quality in reconsitution and the peak signal to noise ratio enhances 0.6~2.5dB, compared with the traditional CoSaMP algorithm.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Xiuli Du
AU  - Binbin Gu
AU  - Bo Chen
AU  - Xing Hu
PY  - 2017/04
DA  - 2017/04
TI  - Image Reconstruction Based on Support Similarity between Lines CoSaMP Algorithm
BT  - Proceedings of the 2017 5th International Conference on Frontiers of Manufacturing Science and Measuring Technology (FMSMT 2017)
PB  - Atlantis Press
SP  - 555
EP  - 561
SN  - 2352-5401
UR  - https://doi.org/10.2991/fmsmt-17.2017.113
DO  - 10.2991/fmsmt-17.2017.113
ID  - Du2017/04
ER  -