Proceedings of the International Conference on Computer Networks and Communication Technology (CNCT 2016)

Image Super-resolution Reconstruction based on Deep Learning and Sparse Representation

Authors
Qian LEI, Zhao-hui ZHANG, Cun-ming HAO
Corresponding Author
Qian LEI
Available Online December 2016.
DOI
https://doi.org/10.2991/cnct-16.2017.75How to use a DOI?
Keywords
Super-resolution, Deep learning, Denoising auto-encoders, Joint dictionary learning, Sparse Representation
Abstract

This paper addresses the problem of super-resolution(SR) image reconstruction based on sparse representation and deep learning. we approached this problem from the dictionary learning. Firstly, in order to realize the correspondence between the sparse representation coefficients, we proposed the method of joint dictionary learning based on Sparse Denoising Auto-Encoders(NSDAE). Secondly, at the stage of reconstruction, in order to achieve high frequency compensation, we proposed the algorithm of iterative error back projection. Finally, experimental results show that the recovered high-resolution image is competitive in quality to images produced by other SR methods.

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)

Volume Title
Proceedings of the International Conference on Computer Networks and Communication Technology (CNCT 2016)
Series
Advances in Computer Science Research
Publication Date
December 2016
ISBN
978-94-6252-301-2
ISSN
2352-538X
DOI
https://doi.org/10.2991/cnct-16.2017.75How to use a DOI?
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/).

Cite this article

TY  - CONF
AU  - Qian LEI
AU  - Zhao-hui ZHANG
AU  - Cun-ming HAO
PY  - 2016/12
DA  - 2016/12
TI  - Image Super-resolution Reconstruction based on Deep Learning and Sparse Representation
BT  - Proceedings of the International Conference on Computer Networks and Communication Technology (CNCT 2016)
PB  - Atlantis Press
SP  - 546
EP  - 555
SN  - 2352-538X
UR  - https://doi.org/10.2991/cnct-16.2017.75
DO  - https://doi.org/10.2991/cnct-16.2017.75
ID  - LEI2016/12
ER  -