Adaptive Blurring Estimation for Learning-Based Super Resolution

DOI

10.2991/cisia-15.2015.179How to use a DOI?

Keywords

Image super-resolution; Locality-constrained linear coding; K-means clustering; De-blurring

Abstract

In this paper, we address the problem of generating high-resolution (HR) image from a single low-resolution (LR) image, which is called image super-resolution (SR). Recently learning-based SR with sparse coding (SC), locality-constraint linear coding (LLC) and so on has been explored, and achieve acceptable performance. However, the conventional learning based methods cannot directly deal with a blurred LR input, which is usually considered as another research line of de-blurring, and extremely difficult to implement for real applications. This paper proposes to firstly estimate the blurring degree of an input image, and then generate the adaptive codebook (dictionary) for learning-based SR, which can simultaneously achieve the de-blurring and high-resolution image in the learning framework. We integrate our previous LLC based SR with the adaptive de-blurring procedure. Experimental results show that our proposed strategy can reconstruct the HR images more accurately than conventional methods, and its processing time is much faster.

Copyright

© 2015, 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  - Y.W Chen
AU  - K. Taniguchi
AU  - X.H Han
PY  - 2015/06
DA  - 2015/06
TI  - Adaptive Blurring Estimation for Learning-Based Super Resolution
BT  - Proceedings of the International Conference on Computer Information Systems and Industrial Applications
PB  - Atlantis Press
SP  - 655
EP  - 658
SN  - 2352-538X
UR  - https://doi.org/10.2991/cisia-15.2015.179
DO  - 10.2991/cisia-15.2015.179
ID  - Chen2015/06
ER  -