An Improved Image Enhancement Approach Using Retinex
Download as PDF
DOI: 10.23977/CNCI2020033
Author(s)
Yilun Liu, Hui Ma, Chunxin Fang, Wenbo Tian, Yan Lv, Jianian Li
Corresponding Author
Yilun Liu
ABSTRACT
Aiming at the halo artifacts and over-enhancement of low-illumination image enhancement by Retinex algorithm, this paper introduced an improved low-illumination image enhancement algorithm based on Retinex theory. Convert the original image to the HSV color space and select the V channel as input. Use tone mapping to globally enhance the luminance channel to obtain detailed information of the image in the shadow. Select guided filter with edge preservation for filtering operations to reduce halo artifacts. Experimental results indicate that the proposed algorithm can effectively improve the overall luminance of low-illumination images, reduce the effects of halo artifacts, and solve the problem of image distortion.
KEYWORDS
Images enhancement; Tone mapping; Retinex; Luminance channel