Cited 0 time in webofscience Cited 0 time in scopus

Blind deblurring using coupled convolutional sparse coding regularisation for noisy-blurry images

Title
Blind deblurring using coupled convolutional sparse coding regularisation for noisy-blurry images
Authors
An, T. H.Choi, D.Cho, SunghyunHong, K. S.Lee, S.
DGIST Authors
Cho, Sunghyun
Issue Date
2018-07
Citation
Electronics Letters, 54(14), 874-875
Type
Article
Article Type
Article
Keywords
image restorationdeconvolutionimage denoisinghigh-quality latent imagenoisy blurred imagesblind deblurringcoupled convolutional sparse coding regularisationnoisy-blurry imagesblurry imageinput blurred imagecorresponding noise-free versionblur informationcoupled dictionary conceptnoise-free blurred imagesparse coefficientsnoise-free latent imagecoupled dictionariesnoise-free imageslatent image estimationblur kernel estimation stepsDECONVOLUTION
ISSN
0013-5194
Abstract
This Letter proposes a novel method to deblur a blurry image corrupted by noise. The authors estimate a noise-free version of the input blurred image and a corresponding noise-free version of the latent image without damaging the blur information, as well as the latent image and blur kernel in an alternating fashion. To this end, they first propose coupled convolutional sparse coding, which incorporates the coupled dictionary concept into convolutional sparse coding. Then they model the noise-free blurred image to share the sparse coefficients with the noise-free latent image using the coupled dictionaries. By utilising these noise-free images as priors in alternating latent image estimation and blur kernel estimation steps, they can estimate a high-quality latent image and blur kernel in the presence of noise. Experimental results demonstrate that the proposed method outperforms previous methods in handling noisy blurred images. © The Institution of Engineering and Technology 2018.
URI
http://hdl.handle.net/20.500.11750/9023
DOI
10.1049/el.2018.0901
Publisher
Institution of Engineering and Technology
Related Researcher
  • Author Cho, Sunghyun Visual computing Lab
  • Research Interests 컴퓨터그래픽스, 컴퓨터 비전, 영상 처리, 계산사진학
Files:
There are no files associated with this item.
Collection:
Department of Information and Communication EngineeringVisual Computing Lab1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE