A fast method for single image haze removal based on multiscale dark channel prior

Hanyu Hong; Zhao Liu; Yu Shi; Xia Hua

doi:10.1117/12.2282252

6 March 2018 A fast method for single image haze removal based on multiscale dark channel prior

Hanyu Hong, Zhao Liu, Yu Shi, Xia Hua

Proceedings Volume 10610, MIPPR 2017: Parallel Processing of Images and Optimization Techniques; and Medical Imaging; 1061002 (2018) https://doi.org/10.1117/12.2282252
Event: Tenth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2017), 2017, Xiangyang, China

Abstract

Aiming at the problem that the computational process in the method for image haze removal based on the dark channel prior is too complicated and too time-consuming, we propose a fast method for single image haze removal based on multiscale dark channel prior. In order to solve the problem that it takes too much time on a high resolution image, we choose to optimize the image haze removal based on dark channel prior algorithm by the method of multiple scales. We deal with rough resolution images and use fast minimum filtering and fast guided filtering to speed up the haze removal algorithm. Therefore, the speed of calculation is accelerated while maintaining the good image effect after haze removal.

Citation Download Citation

Hanyu Hong, Zhao Liu, Yu Shi, and Xia Hua "A fast method for single image haze removal based on multiscale dark channel prior", Proc. SPIE 10610, MIPPR 2017: Parallel Processing of Images and Optimization Techniques; and Medical Imaging, 1061002 (6 March 2018); https://doi.org/10.1117/12.2282252

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