Image restoration parameters adaptive selection algorithm basing on sparse representation model

Chenyao Bai

doi:10.1117/12.2581271

5 November 2020 Image restoration parameters adaptive selection algorithm basing on sparse representation model

Chenyao Bai

Proceedings Volume 11567, AOPC 2020: Optical Sensing and Imaging Technology; 115674L (2020) https://doi.org/10.1117/12.2581271
Event: Applied Optics and Photonics China (AOPC 2020), 2020, Beijing, China

Abstract

The SL0 algorithm is a sort of sparse reconstruction algorithm approximate to l0 norm, which has significant applications in the field of deblurring. In the SL0 algorithm, usually a number of important parameters need to be set to obtain deblurred images. This paper first introduces the basic of the SL0 algorithm, then it analyzes the operator, which has higher dipartite degree for blurred images in edge extraction algorithm, and choose the Roberts operator as the standard for judging parameter optimization. Finally, an algorithm for image restoration parameter adaptive selection is designed, and experiments are conducted. The experimental results show that comparing with the traditional SL0 algorithm, the algorithm in this paper has a great improvement in terms of repairing quality. The repairing effect of the algorithm in this paper is more natural, and the PSNR of images can be increased about 1.5dB.

Citation Download Citation

Chenyao Bai "Image restoration parameters adaptive selection algorithm basing on sparse representation model", Proc. SPIE 11567, AOPC 2020: Optical Sensing and Imaging Technology, 115674L (5 November 2020); https://doi.org/10.1117/12.2581271

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available