Shadowed non-local image guided filter

Li Guo; Long Chen; C. L. Philip Chen

doi:10.1117/12.2302633

10 April 2018 Shadowed non-local image guided filter

Li Guo, Long Chen, C. L. Philip Chen

Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 1061552 (2018) https://doi.org/10.1117/12.2302633
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China

Abstract

Guided image filter has been widely used in image processing. Considering the Non-local model is an excellent method for global information accumulation, the non-local image guided filter has been proposed and shown good performance in many image processing tasks by utilizing the non-local similarity of the guidance image. In this paper, we introduce a shadowed non-local image guided filter derived from the concept of shadowed sets. The shadowed non-local model applies more reliable non-local information by suppressing the low similarity values of the guidance image to zero and boosting high similarity values to the maximum of the non-local similarity set. The thresholds of suppression and boosting are determined automatically based on the concept of shadowed sets. Experimental results on several image processing tasks including image denoising, depth super-resolution, and image dehazing demonstrate the superiority of shadowed set based approach.

Citation Download Citation

Li Guo, Long Chen, and C. L. Philip Chen "Shadowed non-local image guided filter", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 1061552 (10 April 2018); https://doi.org/10.1117/12.2302633

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