Share Email Print
cover

Proceedings Paper

Improved image haze removal algorithm based on fast guided filter
Author(s): Tianhe Yu; Ting Pan
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In haze removal algorithm based on dark channel prior, the global atmospheric light is influenced easily by the white objects in the image, the sky region of recovered image has distortion phenomenon, and the optimization of the transmission is complicated by the soft matting. In this paper, an improved haze removal algorithm is proposed based on dark channel prior. We combine the prior knowledge with the atmospheric scattering model, estimate the global atmospheric light accurately with quadtree search algorithm, modify the transmission of sky area to avoid distortion, and optimize the transmission using the fast guided filter to recover a high-quality haze-free image. Experimental results demonstrate the superiority of the proposed algorithm. Moreover, the recovered image is clearer and the processing speed improves tenfold nearly compared with dark channel prior.

Paper Details

Date Published: 9 August 2018
PDF: 7 pages
Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108063Y (9 August 2018); doi: 10.1117/12.2503119
Show Author Affiliations
Tianhe Yu, Harbin Univ. of Science and Technology (China)
Ting Pan, Harbin Univ. of Science and Technology (China)


Published in SPIE Proceedings Vol. 10806:
Tenth International Conference on Digital Image Processing (ICDIP 2018)
Xudong Jiang; Jenq-Neng Hwang, Editor(s)

© SPIE. Terms of Use
Back to Top