A new low-complexity patch-based image super-resolution

In this study, a novel single image super-resolution (SR) method, which uses a generated dictionary from pairs of high-resolution (HR) images and their corresponding low-resolution (LR) representations, is proposed. First, HR and LR dictionaries are created by dividing HR and LR images into patches...

Full description

Saved in:
Bibliographic Details
Published in:IET computer vision 2017-10, Vol.11 (7), p.567-576
Main Authors: Rasti, Pejman, Nasrollahi, Kamal, Orlova, Olga, Tamberg, Gert, Ozcinar, Cagri, Moeslund, Thomas B, Anbarjafari, Gholamreza
Format: Article
Language:English
Subjects:
chemical analysis
Engineering Sciences
high-resolution images
HR images
illumination enhancement process
image enhancement
image representation
image resolution
interpolated image
low-complexity patch
low-resolution representations
LR dictionary
LR images
neighbour patches
qualitative analyses
quantitative analyses
Research Article
single image super-resolution method
SR method
Citations: Items that this one cites
Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this study, a novel single image super-resolution (SR) method, which uses a generated dictionary from pairs of high-resolution (HR) images and their corresponding low-resolution (LR) representations, is proposed. First, HR and LR dictionaries are created by dividing HR and LR images into patches Afterwards, when performing SR, the distance between every patch of the input LR image and those of available LR patches in the LR dictionary are calculated. The minimum distance between the input LR patch and those in the LR dictionary is taken, and its counterpart from the HR dictionary will be passed through an illumination enhancement process resulting in consistency of illumination between neighbour patches. This process is applied to all patches of the LR image. Finally, in order to remove the blocking effect caused by merging the patches, an average of the obtained HR image and the interpolated image is calculated. Furthermore, it is shown that the stabe of dictionaries is reducible to a great degree. The speed of the system is improved by 62.5%. The quantitative and qualitative analyses of the experimental results show the superiority of the proposed technique over the conventional and state-of-the-art methods.
ISSN:1751-9632
1751-9640
1751-9640
DOI:10.1049/iet-cvi.2016.0463