基于主成分分析的自适应低光照图像增强算法  

Adaptive Low-light Image Enhancement Algorithm Based on Principal Component Analysis

作　　者：郭苗苗 胡红萍[1] 白艳萍[1] 宋娜 GUO Miaomiao;HU Hongping;BAI Yanping;SONG Na(School of Mathematics,North University of China,Taiyuan 030051,China)

机构地区：[1]中北大学数学学院,太原030051

出　　处：《火力与指挥控制》2024年第11期184-192,共9页Fire Control & Command Control

基　　金：山西省回国留学人员科研项目(2020-104,2021-108);山西省基础研究计划资助项目(20210302123019,20210302124195,20210302124212,20210302123189,20210302123031)。

摘　　要：针对低光照图像能见度低、颜色退化、噪声大等问题,提出了一种基于主成分分析的自适应低光照图像增强算法。将原始RGB图像转换为HSV色彩空间,提取V分量;再根据估计的光照分量调整自适应亮度增强函数的参数,并利用图像融合增强图像的V分量;将图像从HSV空间转换回RGB空间。实验结果表明,提出的算法能够保留低光照图像的细节,且能很好地平衡图像颜色。Aiming at the problems of low visibility,color degradation and noise of low-light images,etc.an adaptive low-light image enhancement algorithm based on principal component analysis is proposed.Firstly,the original RGB image is converted to HSV color space and the V component is extracted.Then the parameters of the adaptive brightness enhancement function is adjusted according to the estimated illumination component,and the V component of the image is enhanced by image fusion.Finally,the image is converted from HSV space back to RGB space.Experimental results show that the proposed algorithm retains the details of low-light images and balances image colors well.

关 键 词：RETINEX理论 形态学梯度 主成分分析 图像融合 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]