基于人眼视觉的多尺度融合图像增强算法  

Multi-scale fusion image enhancement algorithm based on human vision

作　　者：王改云[1] 郭智超 路皓翔 陆家卓 张琦 WANG Gai-yun;GUO Zhi-chao+;LU Hao-xiang;LU Jia-zhuo;ZHANG Qi(School of Electronic Engineering and Automation,Guilin University of Electronic Technology,Guilin 541004,China;School of Computer Science and Information Security,Guilin University of Electronic Technology,Guilin 541004,China)

机构地区：[1]桂林电子科技大学电子工程与自动化学院,广西桂林541004 [2]桂林电子科技大学计算机与信息安全学院,广西桂林541004

出　　处：《计算机工程与设计》2022年第12期3468-3474,共7页Computer Engineering and Design

基　　金：广西自然科学基金面上基金项目(2017JJA170450y);广西人才专项基金项目(桂科2018AD19020);广西重点研发计划基金项目(桂科AB21076005)。

摘　　要：为解决低照度图像对比度低、细节模糊的问题,提出基于人眼视觉的多尺度融合图像增强算法。将图像从RGB空间转换到HSV空间,分离图像的色彩信息和亮度信息;将HSV空间的H和S通道的信息Image H和Image S转换为权重图,对V通道的亮度信息Image V进行增强;利用引导滤波算法增强图像的细节信息。为验证该算法的优越性,对比其它传统增强算法处理后的结果发现,该算法的增强效果优于几种传统的增强算法。To solve the problems of low-illuminance images such as low contrast and blurred details,a multi-scale fusion image enhancement algorithm based on human vision was proposed.The input image was converted from RGB space to HSV space,so that the color information and brightness information of the image were separated.The brightness channel V information in the HSV model Image V was enhanced by the H and S channel information Image H and Image S.The detailed information was enhanced using the guided filtering algorithm and then merged into the image with enhanced brightness.To verify the effectiveness of the algorithm,it was compared with the low-illuminance image result processed using the traditional enhancement algorithm.Through experimental comparison,it is found that the enhancement effect of this enhancement algorithm is better than that of several traditional enhancement algorithms.

关 键 词：图像增强 低照度图像 多尺度融合 引导滤波 细节锐化 对比度增强 人类视觉系统 

分 类 号：TP317.4[自动化与计算机技术—计算机软件与理论]