一种基于多尺度Retinex的夜间图像增强算法  

A Night Image Enhancement Algorithm Based on Multi-scale Retinex

作　　者：牛志忠 杨坤 NIU Zhizhong;YANG Kun(School of Computer and Information Engineering,Guizhou University of Commerce,Guiyang 550014,China)

机构地区：[1]贵州商学院计算机与信息工程学院,贵州贵阳550014

出　　处：《现代信息科技》2020年第17期66-68,71,共4页Modern Information Technology

基　　金：贵州商学院院级科研项目(2019YJZK02);贵州省青年科技人才成长项目(黔教合KY字〔2018〕269)。

摘　　要：现有的夜间图像增强算法存在着图像对比度过高和暗区细节不佳的情况。因此,文章提出了一种基于多尺度Retinex(MSR)的夜间图像增强方法,首先通过对图像进行MSR增强,将增强后的图像转换到YUV色彩空间,对Y通道进行伽马变换。实验表明,与传统的MSR方法对比,改进后的算法能够很好地提高图像的对比度,改进暗区的细节表现,具有很好的视觉效果。The existing night image enhancement algorithms have the problems of high image contrast and poor dark area details.Therefore,a night image enhancement method based on multi-scale Retinex(MSR)is proposed.Firstly,the image is enhanced by MSR,transforming the enhanced image into YUV color space,and using the gamma conversion to transformed Y channel.The experimental results show that compared with the traditional MSR method,the improved algorithm can improve the contrast of the image,improve the detail performance of the dark area,and has a good visual effect.

关 键 词：夜间图像增强 RETINEX算法 YUV颜色空间 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]