基于自适应权重Retinex和小波变换的彩色图像增强算法  

Color Image Enhancement Algorithm Based on Adaptive Weight Retinex and Wavelet Transform

作　　者：冯红波 李萍 王博 FENG Hongbo;LI Ping;WANG Bo(School of Physics and Electronic-Electrical Engineering,Ningxia University,Yinchuan 750021,China)

机构地区：[1]宁夏大学物理与电子电气工程学院

出　　处：《无线电工程》2020年第1期28-33,共6页Radio Engineering

基　　金：2017年宁夏高等学校科研资助项目(NGY2017009)~~

摘　　要：针对现有图像增强技术容易出现细节丢失、局部曝光不足、过曝光或颜色失真,不能兼顾对比度和色彩保真的问题,提出了基于自适应权重Retinex与小波变换结合的彩色图像增强算法(AMSR-WT)。将图像从RGB空间转换到HSI空间,对亮度分量I进行小波变换分解为低频亮度图像和若干高频亮度图像,对低频图像使用自适应权重Retinex进行增强,对高频图像使用改进的阈值去噪算法进行去噪,通过小波逆变换重构亮度分量,经过Gamma校正进一步增强对比度并转换回RGB空间得到增强图像。实验结果表明,该算法有效提高了图像对比度和颜色保真度,较好地保留了图像的细节和纹理。For the existing image enhancement technology,it is easy to lose detail,cause partial underexposure or overexposure,and color distortion,and it cannot balance the contrast and color fidelity.A color image enhancement algorithm(AMSR-WT)based on adaptive weight Retinex and wavelet transform is proposed.The image is converted from RGB space to HSI space,and the luminance component I is wavelet-decomposed into low-frequency brightness image and several high-frequency luminance images.The low-frequency image is enhanced with adaptive weight Retinex,and the improved threshold is used for high-frequency image denoising.Finally the inverse wavelet transform is used to reconstruct the luminance component.After Gamma correction,the contrast is further enhanced and converted back to RGB space to obtain an enhanced image.The experimental results show that the algorithm effectively improves the contrast and color fidelity of the image,and better preserves the details and texture of the image.

关 键 词：图像增强 自适应权重 RETINEX算法 小波变换 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]