Blind Deconvolution With Nonlocal Similarity and $l_0$ Sparsity for Noisy Image

The blind image deconvolution techniques with sparsity prior in gradient domain are sensitive to noise, even a small amount of noise. To address this problem, in this letter, we propose a novel blind deconvolution model that combines low-rank property, nonlocal similarity, and $l_0$ sparsity prior....

Full description

Saved in:
Bibliographic Details
Published inIEEE signal processing letters Vol. 23; no. 4; pp. 439 - 443
Main Authors Ren, Weihong, Tian, Jiandong, Tang, Yandong
Format Journal Article
LanguageEnglish
Published 01.04.2016
Subjects
Blinds
Deconvolution
Kernels
Mathematical models
Noise
Similarity
State of the art
Online AccessGet full text

Cover

More Information
Summary:The blind image deconvolution techniques with sparsity prior in gradient domain are sensitive to noise, even a small amount of noise. To address this problem, in this letter, we propose a novel blind deconvolution model that combines low-rank property, nonlocal similarity, and $l_0$ sparsity prior. Low-rank property makes the proposed deblurring model robust to image noise. The joint utilization of nonlocal similarity and $l_0$ sparsity prior has improved the accuracy of blur kernel estimation and restores the fine image details. A numerical method is also given to solve the proposed problem. Experimental results on synthetic and real data show that our algorithm performs better against with the state-of-the-art methods for both noise and noise-free images.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
content type line 23
ObjectType-Feature-2
ISSN:1070-9908
1558-2361
DOI:10.1109/LSP.2016.2530855