Image denoising via collaborative support-agnostic recovery

Handle URI:
http://hdl.handle.net/10754/625625
Title:
Image denoising via collaborative support-agnostic recovery
Authors:
Behzad, Muzammil; Masood, Mudassir; Ballal, Tarig; Shadaydeh, Maha; Al-Naffouri, Tareq Y.
Abstract:
In this paper, we propose a novel patch-based image denoising algorithm using collaborative support-agnostic sparse reconstruction. In the proposed collaborative scheme, similar patches are assumed to share the same support taps. For sparse reconstruction, the likelihood of a tap being active in a patch is computed and refined through a collaboration process with other similar patches in the similarity group. This provides a very good patch support estimation, hence enhancing the quality of image restoration. Performance comparisons with state-of-the-art algorithms, in terms of PSNR and SSIM, demonstrate the superiority of the proposed algorithm.
KAUST Department:
King Abdullah University of Science & Technology (KAUST), Thuwal, Makkah Province, Saudi Arabia
Citation:
Behzad M, Masood M, Ballal T, Shadaydeh M, Al-Naffouri TY (2017) Image denoising via collaborative support-agnostic recovery. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Available: http://dx.doi.org/10.1109/ICASSP.2017.7952375.
Publisher:
IEEE
Journal:
2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
KAUST Grant Number:
OSR 2016-KKI-2899
Conference/Event name:
2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
Issue Date:
20-Jun-2017
DOI:
10.1109/ICASSP.2017.7952375
Type:
Conference Paper
Sponsors:
This work is supported in part by the KAUST Office of Sponsored Research under Award No. OSR 2016-KKI-2899, and by Deanship of Scientific Research at KFUPM, Saudi Arabia, through project number KAUST-002.
Additional Links:
http://ieeexplore.ieee.org/document/7952375/
Appears in Collections:
Conference Papers

Full metadata record

DC FieldValue Language
dc.contributor.authorBehzad, Muzammilen
dc.contributor.authorMasood, Mudassiren
dc.contributor.authorBallal, Tarigen
dc.contributor.authorShadaydeh, Mahaen
dc.contributor.authorAl-Naffouri, Tareq Y.en
dc.date.accessioned2017-10-03T12:49:30Z-
dc.date.available2017-10-03T12:49:30Z-
dc.date.issued2017-06-20en
dc.identifier.citationBehzad M, Masood M, Ballal T, Shadaydeh M, Al-Naffouri TY (2017) Image denoising via collaborative support-agnostic recovery. 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Available: http://dx.doi.org/10.1109/ICASSP.2017.7952375.en
dc.identifier.doi10.1109/ICASSP.2017.7952375en
dc.identifier.urihttp://hdl.handle.net/10754/625625-
dc.description.abstractIn this paper, we propose a novel patch-based image denoising algorithm using collaborative support-agnostic sparse reconstruction. In the proposed collaborative scheme, similar patches are assumed to share the same support taps. For sparse reconstruction, the likelihood of a tap being active in a patch is computed and refined through a collaboration process with other similar patches in the similarity group. This provides a very good patch support estimation, hence enhancing the quality of image restoration. Performance comparisons with state-of-the-art algorithms, in terms of PSNR and SSIM, demonstrate the superiority of the proposed algorithm.en
dc.description.sponsorshipThis work is supported in part by the KAUST Office of Sponsored Research under Award No. OSR 2016-KKI-2899, and by Deanship of Scientific Research at KFUPM, Saudi Arabia, through project number KAUST-002.en
dc.publisherIEEEen
dc.relation.urlhttp://ieeexplore.ieee.org/document/7952375/en
dc.subjectCollaborationen
dc.subjectComputational complexityen
dc.subjectDictionariesen
dc.subjectEstimationen
dc.subjectImage denoisingen
dc.subjectNoise reductionen
dc.subjectSignal to noise ratioen
dc.titleImage denoising via collaborative support-agnostic recoveryen
dc.typeConference Paperen
dc.contributor.departmentKing Abdullah University of Science & Technology (KAUST), Thuwal, Makkah Province, Saudi Arabiaen
dc.identifier.journal2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)en
dc.conference.date2017-03-05 to 2017-03-09en
dc.conference.name2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017en
dc.conference.locationNew Orleans, LA, USAen
dc.contributor.institutionCOMSATS Institute of Information Technology (CIIT), Islamabad, Pakistanen
dc.contributor.institutionKing Fahd University of Petroleum & Minerals (KFUPM), Dhahran, Eastern Province, Saudi Arabiaen
dc.contributor.institutionInstitute for Computer Science and Control, Hungarian Academy of Sciences, Budapest, Hungaryen
kaust.authorBallal, Tarigen
kaust.authorAl-Naffouri, Tareq Y.en
kaust.grant.numberOSR 2016-KKI-2899en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.