An Improved Single Image Haze Removal Algorithm Based on Dark Channel Prior and Histogram Specification

DOI

10.2991/icmt-13.2013.35How to use a DOI?

Keywords

haze removal, dark channel prior, histogram specification, intensity, contrast

Abstract

We introduce an improved single image haze removal algorithm, which combines dark channel prior (DCP) and histogram specification. First, the dark channel prior knowledge proposed by Kaiming He is analyzed and a conclusionis drawn that the haze removal image based on dark channel prior will have a ten-dency to dim and indistinct in some specific situations. Especially, when cleaning the haze in the image with large background area and low contrast, DCP resultappears obvious anamorphose. Next, in order to improve the dehazing result of this kind of image, we propose an approach to change the contrast and intensi-ty of haze removal image after DCP method by rebuilding the histogram of the image. Then, a modified approach is applied to fit general haze image. We ex-periment our method with a variety of outdoor haze images. The effectiveness ofour method is demonstrated in comparison with DCP result when the input image contains low contrast scene and large background area, such as thick fog or dark surroundings in dusk. Our job makes up the deficiency of the dark channel model for this kind of image and enhance the contrast of the scene. Furthermore, theexperimental results show that the dehazing effect on general haze image appears more close to real scene than dark channel model.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhu Qingsong
AU  - Yang Shuai
AU  - Xie Yaoqin
PY  - 2013/11
DA  - 2013/11
TI  - An Improved Single Image Haze Removal Algorithm Based on Dark Channel Prior and Histogram Specification
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 279
EP  - 292
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.35
DO  - 10.2991/icmt-13.2013.35
ID  - Qingsong2013/11
ER  -