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

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 al...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Electronics letters Ročník 54; číslo 14; s. 874 - 876
Hlavní autori:	An, T.-H, Choi, D, Cho, S, Hong, K.-S, Lee, S
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	The Institution of Engineering and Technology 12.07.2018
Predmet:	blind deblurring blur information blur kernel estimation steps blurry image corresponding noise‐free version coupled convolutional sparse coding regularisation coupled dictionaries coupled dictionary concept deconvolution high‐quality latent image Image and vision processing and display technology image denoising image restoration input blurred image latent image estimation noise‐free blurred image noise‐free images noise‐free latent image noisy blurred images noisy‐blurry images sparse coefficients coupled dictionary concept noise-free blurred image blur kernel estimation steps image denoising blind deblurring coupled dictionaries noise-free images noisy blurred images deconvolution coupled convolutional sparse coding regularisation noise-free latent image noisy-blurry images latent image estimation corresponding noise-free version image restoration input blurred image sparse coefficients blur information blurry image high-quality latent image
ISSN:	0013-5194, 1350-911X, 1350-911X
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Popis
Shrnutí:	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.
ISSN:	0013-5194 1350-911X 1350-911X
DOI:	10.1049/el.2018.0901