Compressive Superresolution Imaging Based on Local and Nonlocal Regularizations

Compressive sensing based on a redundant dictionary has been successfully applied in superresolution imaging. However, due to the neglect of the local and nonlocal interactions of patches of a single image, the reconstructed results are not satisfactory in noise suppression and edge sharpness. In th...

Full description

Saved in:
Bibliographic Details
Main Authors: Yicheng Sun, Guohua Gu, Xiubao Sui, Yuan Liu
Format: Article
Language:English
Published: IEEE 2016-01-01
Series:IEEE Photonics Journal
Subjects:
Online Access:https://ieeexplore.ieee.org/document/7377008/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1839645280089145344
author Yicheng Sun
Guohua Gu
Xiubao Sui
Yuan Liu
author_facet Yicheng Sun
Guohua Gu
Xiubao Sui
Yuan Liu
author_sort Yicheng Sun
collection DOAJ
description Compressive sensing based on a redundant dictionary has been successfully applied in superresolution imaging. However, due to the neglect of the local and nonlocal interactions of patches of a single image, the reconstructed results are not satisfactory in noise suppression and edge sharpness. In this paper, we propose an improved method by adding steering kernel regression and a nonlocal means filter as two regularization terms and use an efficient clustering subdictionary learning scheme. We further demonstrate better results on true images in terms of traditional image quality assessment metrics.
format Article
id doaj-art-a3e471b01a614e89bce388f33a9c5a5d
institution Matheson Library
issn 1943-0655
language English
publishDate 2016-01-01
publisher IEEE
record_format Article
series IEEE Photonics Journal
spelling doaj-art-a3e471b01a614e89bce388f33a9c5a5d2025-07-01T23:01:52ZengIEEEIEEE Photonics Journal1943-06552016-01-018111210.1109/JPHOT.2016.25162517377008Compressive Superresolution Imaging Based on Local and Nonlocal RegularizationsYicheng Sun0Guohua Gu1Xiubao Sui2https://orcid.org/0000-0002-1638-0701Yuan Liu3Sch. of Electron. & Opt. Eng., Nanjing Univ. of Sci. & Technol., Nanjing, ChinaSch. of Electron. & Opt. Eng., Nanjing Univ. of Sci. & Technol., Nanjing, ChinaSch. of Electron. & Opt. Eng., Nanjing Univ. of Sci. & Technol., Nanjing, ChinaSch. of Electron. & Opt. Eng., Nanjing Univ. of Sci. & Technol., Nanjing, ChinaCompressive sensing based on a redundant dictionary has been successfully applied in superresolution imaging. However, due to the neglect of the local and nonlocal interactions of patches of a single image, the reconstructed results are not satisfactory in noise suppression and edge sharpness. In this paper, we propose an improved method by adding steering kernel regression and a nonlocal means filter as two regularization terms and use an efficient clustering subdictionary learning scheme. We further demonstrate better results on true images in terms of traditional image quality assessment metrics.https://ieeexplore.ieee.org/document/7377008/super-resolutioncompressive sensingnonlocal means filtersteering kernel regressionclustering sub-dictionaries
spellingShingle Yicheng Sun
Guohua Gu
Xiubao Sui
Yuan Liu
Compressive Superresolution Imaging Based on Local and Nonlocal Regularizations
IEEE Photonics Journal
super-resolution
compressive sensing
nonlocal means filter
steering kernel regression
clustering sub-dictionaries
title Compressive Superresolution Imaging Based on Local and Nonlocal Regularizations
title_full Compressive Superresolution Imaging Based on Local and Nonlocal Regularizations
title_fullStr Compressive Superresolution Imaging Based on Local and Nonlocal Regularizations
title_full_unstemmed Compressive Superresolution Imaging Based on Local and Nonlocal Regularizations
title_short Compressive Superresolution Imaging Based on Local and Nonlocal Regularizations
title_sort compressive superresolution imaging based on local and nonlocal regularizations
topic super-resolution
compressive sensing
nonlocal means filter
steering kernel regression
clustering sub-dictionaries
url https://ieeexplore.ieee.org/document/7377008/
work_keys_str_mv AT yichengsun compressivesuperresolutionimagingbasedonlocalandnonlocalregularizations
AT guohuagu compressivesuperresolutionimagingbasedonlocalandnonlocalregularizations
AT xiubaosui compressivesuperresolutionimagingbasedonlocalandnonlocalregularizations
AT yuanliu compressivesuperresolutionimagingbasedonlocalandnonlocalregularizations