A Retinex image enhancement based on L channel illumination estimation and gamma function

DOI

10.2991/jiaet-18.2018.55How to use a DOI?

Keywords

Low illumination; Color image enhancement; L channel; Gamma function

Abstract

In order to improve the contrast of low illumination image, enhance the processing effect and eliminate artifacts, a color Retinex image enhancement algorithm based on L channel illumination estimation and two dimensional gamma functions is proposed. Firstly, the L image intensity is regarded as the product of correlation reflectivity and illumination through Lab color space transformation, and the intensity of global illumination is estimated by bilateral filtering. Then, two dimensional gamma functions are used to complete the pixel mapping, and the local details can be adaptively adjusted. Experimental results show that compared with other Retinex image enhancement algorithms, the proposed algorithm enhances the effect more naturally and produces no enhancement artifacts, which can effectively preserve the local details of the image.

Copyright

© 2018, 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  - Yulei Huang
AU  - Yan Li
AU  - Yan Zhang
PY  - 2018/03
DA  - 2018/03
TI  - A Retinex image enhancement based on L channel illumination estimation and gamma function
BT  - Proceedings of the 2018 Joint International Advanced Engineering and Technology Research Conference (JIAET 2018)
PB  - Atlantis Press
SP  - 312
EP  - 317
SN  - 2352-5401
UR  - https://doi.org/10.2991/jiaet-18.2018.55
DO  - 10.2991/jiaet-18.2018.55
ID  - Huang2018/03
ER  -