Cited 0 time in
Cited 0 time in
Blind deblurring using coupled convolutional sparse coding regularisation for noisy-blurry images
- Blind deblurring using coupled convolutional sparse coding regularisation for noisy-blurry images
- An, T. H.; Choi, D.; Cho, Sunghyun; Hong, K. S.; Lee, S.
- DGIST Authors
- Cho, Sunghyun
- Issue Date
- Electronics Letters, 54(14), 874-875
- Article Type
- image restoration; deconvolution; image denoising; high-quality latent image; noisy blurred images; blind deblurring; coupled convolutional sparse coding regularisation; noisy-blurry images; blurry image; input blurred image; corresponding noise-free version; blur information; coupled dictionary concept; noise-free blurred image; sparse coefficients; noise-free latent image; coupled dictionaries; noise-free images; latent image estimation; blur kernel estimation steps; DECONVOLUTION
- 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.
- Institution of Engineering and Technology
There are no files associated with this item.
- Department of Information and Communication EngineeringVisual Computing Lab1. Journal Articles
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.