Share Email Print

Proceedings Paper

Restoration of single image based on kernel estimation with L1-regularization method
Author(s): Minghua Zhao; Hui Cao; Xin Zhang; Zhenghao Shi; Peng Li
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Image restoration is a significant task in the fields of computer vision and image processing. Image restoration research consists of two aspects: kernel estimation and image restoration. A single image restoration method based on L1-regularized blur kernel estimation is proposed in this paper. First, a bilateral filter is used to remove the image noise effectively. Second, the improved shock filter is used to enhance the edge information of the image. Subsequently, L1-regularization method is used to estimate the blur kernel of the blurred image alternately, during which Split-Bregman algorithm is used to optimize the solution process. Finally, Hyper-Laplacian and sparse priors are applied to the image obtained from the non-blind deconvolution process. Experimental results show that compared to other methods, better restoration results as well as improved computational efficiency can be achieved with the proposed method.

Paper Details

Date Published: 21 July 2017
PDF: 5 pages
Proc. SPIE 10420, Ninth International Conference on Digital Image Processing (ICDIP 2017), 104201V (21 July 2017); doi: 10.1117/12.2282001
Show Author Affiliations
Minghua Zhao, Xi'an Univ. of Technology (China)
Hui Cao, Xi'an Univ. of Technology (China)
Xin Zhang, Xi'an Univ. of Technology (China)
Zhenghao Shi, Xi'an Univ. of Technology (China)
Peng Li, Xi'an Univ. of Technology (China)

Published in SPIE Proceedings Vol. 10420:
Ninth International Conference on Digital Image Processing (ICDIP 2017)
Charles M. Falco; Xudong Jiang, Editor(s)

© SPIE. Terms of Use
Back to Top