L-0-Regularized image downscaling
Publication Type
Journal Article
Publication Date
3-2018
Abstract
In this paper, we propose a novel L-0-regularized optimization framework for image downscaling. The optimization is driven by two L-0-regularized priors. The first prior, gradient-ratio prior, is based on the observation that the number of edges in the downscaled image is approximately inverse square proportional to the downscaling factor. By introducing L-0 norm sparsity to the gradient ratio, the downscaled image is able to preserve the most salient edges as well as the visual perception of the original image. The second prior, downsampling prior, is to constrain the downsampling matrix so that pixels of the downscaled image are estimated according to those optimal neighboring pixels. Extensive experiments on the Urban100 and BSDS500 data sets show that the proposed algorithm achieves superior performance over the state-of-the-arts, in terms of both quality and robustness.
Keywords
Image downscaling, L-0 norm sparsity, salient edges preserving
Discipline
Information Security
Research Areas
Information Systems and Management
Publication
IEEE Transactions on Image Processing
Volume
27
Issue
3
First Page
1076
Last Page
1085
ISSN
1057-7149
Identifier
10.1109/TIP.2017.2772838
Publisher
Institute of Electrical and Electronics Engineers
Citation
LIU, Junjie; HE, Shengfeng; and LAU, Rynson W.H..
L-0-Regularized image downscaling. (2018). IEEE Transactions on Image Processing. 27, (3), 1076-1085.
Available at: https://ink.library.smu.edu.sg/sis_research/7869
Additional URL
https://doi.org/10.1109/TIP.2017.2772838