Kernel estimation for robust motion deblurring of noisy and blurry images | |
Sun SJ(孙世杰); Zhao HC(赵怀慈)![]() | |
Department | 光电信息技术研究室 |
Source Publication | Journal of Electronic Imaging
![]() |
ISSN | 1017-9909 |
2016 | |
Volume | 25Issue:3Pages:1-12 |
Indexed By | SCI ; EI |
EI Accession number | 20162602539079 |
WOS ID | WOS:000381379600019 |
Contribution Rank | 1 |
Funding Organization | General Scientific Research Project of Education Department of Liaoning of China under Grant No. L2015368 |
Keyword | Blind Image Deblurring Noisy And Blurry Image Salient Structure Image Edge Kernel Estimation |
Abstract | Most state-of-the-art single image blind deblurring techniques are still sensitive to image noise, leading to serious performance degradation in their blur kernel estimation when the input image noise increases. We found that reliable kernel estimation could not be given by directly using denoising and existing deblurring algorithms in many cases. We focus on how to estimate a good blur kernel from a noisy blurred image via using the image structure. First, we applied denoising as a preprocess to remove the input image noise and then computed salient image structure of the denoised result based on the total variation model. We also applied a gradient selection method to remove those salient edges that have a possible adverse effect on blur kernel estimation. Next, we adopted a two-phase estimation strategy to obtain higher quality blur kernel estimation by jointly applying kernel estimation from salient image structure and iterative support detection (ISD) kernel refinement. Finally, we used the nonblind deconvolution method based on sparse prior knowledge to restore the latent image. Extensive experiments testify to the superiority of the proposed method over state-of-the-art algorithms, both qualitatively and quantitatively. |
Language | 英语 |
WOS Headings | Science & Technology ; Technology ; Physical Sciences |
WOS Subject | Engineering, Electrical & Electronic ; Optics ; Imaging Science & Photographic Technology |
WOS Keyword | BLIND DECONVOLUTION ; REGULARIZATION ; FILTERS ; CAMERA |
WOS Research Area | Engineering ; Optics ; Imaging Science & Photographic Technology |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.sia.cn/handle/173321/18724 |
Collection | 光电信息技术研究室 |
Corresponding Author | Sun SJ(孙世杰) |
Affiliation | 1.Shenyang Institute of Automation, Chinese Academy of Sciences, No. 114, Nanta Street, Shenhe District, Shenyang City, 110016, China 2.University of Chinese Academy of Science, No. 19, Yuquan Road, Shijingshan District, Beijing City, 100049, China 3.Chinese Academy of Sciences, Key Laboratory of Optical-Electronics Information Processing, No. 114, Nanta Street, Shenhe District, Shenyang City, 110016, China 4.Key Laboratory of Image Understanding and Computer Vision, No. 114, Nanta Street, Shenhe District, Shenyang City, 110016, China 5.Shenyang Institute of Engineering, College of Information, No. 18, Puchang Road, Shenbei New Area, Shenyang City, 110136, China |
Recommended Citation GB/T 7714 | Sun SJ,Zhao HC,Li B,et al. Kernel estimation for robust motion deblurring of noisy and blurry images[J]. Journal of Electronic Imaging,2016,25(3):1-12. |
APA | Sun SJ,Zhao HC,Li B,Hao MG,&Lv JF.(2016).Kernel estimation for robust motion deblurring of noisy and blurry images.Journal of Electronic Imaging,25(3),1-12. |
MLA | Sun SJ,et al."Kernel estimation for robust motion deblurring of noisy and blurry images".Journal of Electronic Imaging 25.3(2016):1-12. |
Files in This Item: | ||||||
File Name/Size | DocType | Version | Access | License | ||
Kernel estimation fo(4303KB) | 期刊论文 | 作者接受稿 | 开放获取 | ODC PDDL | View Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment