online read us now
Paper details
Number 3 - September 2022
Volume 32 - 2022
A single image deblurring approach based on a fractional order dark channel prior
Xiaoyuan Yu, Wei Xie, Jinwei Yu
Abstract
The dark channel prior has been successfully applied to solve the blind deblurring problem on different scene images. Since
the dark channel of the blurry-noise image is similar to that of the corresponding clear image, the sparsity of the dark channel
is less effective for image blind deblurring. Inspired by the fact that a fractional order calculation can inhibit the noise and
preserve the texture information of the image, a fractional order dark channel prior is proposed for image deblurring in this
paper. It is appropriate for kernel estimation where input images and intermediate images are processed by using a fractional
order dark channel prior. Furthermore, the non-convex problem is solved by the half-quadratic splitting method, and some
metrics are used for deblurring image quality assessment. Finally, quantitative and qualitative experimental results show
that the proposed method achieves state-of-the-art results on synthetic and real blurry images.
Keywords
blind image deblurring, fractional order dark channel prior, non-convex problem