Research of algorithm for single gray-scale image haze removal

Yu-jiao Shen; Jun-ju Zhang; Si Tian; Kai Zhu; Ying-wang Feng

doi:10.1117/12.2504546

12 December 2018 Research of algorithm for single gray-scale image haze removal

Yu-jiao Shen, Jun-ju Zhang, Si Tian, Kai Zhu, Ying-wang Feng

Proceedings Volume 10846, Optical Sensing and Imaging Technologies and Applications; 1084617 (2018) https://doi.org/10.1117/12.2504546
Event: International Symposium on Optoelectronic Technology and Application 2018, 2018, Beijing, China

Abstract

The gray-scale image is widely used in remote sensing image and high-resolution image. The resolution and the contrast are declining, also the image quality is seriously damaged under haze weather. Non-model image enhancement mainly uses targeted image processing methods to improve the contrast and details, while the image degradation is considered in model image restoration. Considering the lack and the necessity of research on the gray-scale image haze removal, a method of single gray-scale image haze removal based on dark channel prior is proposed. This paper extends the method of dark channel haze removal to the gray-scale image. The method reduces the amount of calculation by sampling down the input single gray image. At the same time, different measures are taken on the edges, the flat areas and the noise points of the image to remove the block effect. In addition, a refined transmission is obtained by coefficient modulation. By comparing the experiments and the quality evaluation with other methods of haze removal, including guided filtering, gray stretch and adaptive histogram equalization with limited contrast. It fully shows that the proposed method can be effectively applied to the gray image haze removal.

Citation Download Citation

Yu-jiao Shen, Jun-ju Zhang, Si Tian, Kai Zhu, and Ying-wang Feng "Research of algorithm for single gray-scale image haze removal", Proc. SPIE 10846, Optical Sensing and Imaging Technologies and Applications, 1084617 (12 December 2018); https://doi.org/10.1117/12.2504546

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