A Research of Defogging Algorithm Based on Clustering Segmentation

DOI

10.2991/mmetss-16.2017.112How to use a DOI?

Keywords

Cluster segmentation;defogging image;adaptive histogram equalization;image enhancement

Abstract

Under the condition of fog, the images captured by the mobile phone are blurred, because of the scattering effect of the suspended particles in the air. In order to obtain more information about the image, this paper presents an image dehazing algorithm based on K-means clustering, which will firstly transform foggy image color space, extract the luminance component of the image, use k-means clustering algorithm to segment the sky area of the image. The sky region keeps the same brightness and non-sky area are conducted with adaptive histogram equalization. The experimental results show that when the K is 20, the segmentation results are very close to the sky region of the fog image, and the image processing is improved greatly.

Copyright

© 2017, 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  - Yan-hai Wu
AU  - Kang Chen
AU  - Nan Wu
AU  - Jing Zhang
PY  - 2017/02
DA  - 2017/02
TI  - A Research of Defogging Algorithm Based on Clustering Segmentation
BT  - Proceedings of the 2016 International Conference on Modern Management, Education Technology, and Social Science (MMETSS 2016)
PB  - Atlantis Press
SP  - 160
EP  - 165
SN  - 2352-5398
UR  - https://doi.org/10.2991/mmetss-16.2017.112
DO  - 10.2991/mmetss-16.2017.112
ID  - Wu2017/02
ER  -