联合双边滤波的单幅图像去高光算法改进  

Improved Single Image Highlight Removal Algorithm Based on Joint Bilateral Filtering

作　　者：胡珍珍 刘汉明[1] 黎姿 李泽南 HU Zhen-zhen;LIU Han-ming;LI Zi;LI Ze-nan(Key Laboratory of Jiangxi Province for Numerical Simulation and Emulation Techniques,Gannan Normal University,Ganzhou Jiangxi,341000,China)

机构地区：[1]赣南师范大学江西省数值模拟与仿真技术重点实验室,江西赣州341000

出　　处：《计算机仿真》2025年第3期236-243,380,共9页Computer Simulation

基　　金：江西省数值模拟与仿真技术重点实验室招标项目(400297)。

摘　　要：为有效去除单幅图像的高光,同时保留图像颜色和纹理信息,提出了一种联合双边滤波的高光去除改进算法。算法首先通过优化的阈值将图像像素分为仅含漫反射和含有镜面反射的两类像素点,并分别估计这两类像素点的最大漫反射色度图,提高了最大漫反射色度的估计精度。然后利用最大漫反射色度具有局部平滑的特性,将最大漫反射色度估计图作为联合双边滤波器的引导图,对含高光图像最大色度图进行平滑滤波,以实现图像高光的去除。实验结果表明,与现有算法相比,上述算法不仅更有效地去除了图像高光,还更大程度上保留了原图像的颜色和纹理信息。算法的峰值信噪比平均提高了3.467,结构相似度平均提高了0.073。To effectively remove highlights from a single image while preserving more image color and texture information,an improved algorithm for removing highlights with joint bilateral filtering is proposed.The algorithm separates the image pixels into two categories,the pixels of only diffuse reflection and those of specular reflection,by an optimized threshold.Then it estimates the maximum diffuse chromaticity of the two categories of pixels respectively.The procedure improves the estimation precision of the maximum diffuse chromaticity.Finally,let the image with maximum diffuse chromaticity be a joint bilateral filtering guide map to smooth the image with maximum highlight chromaticity,and produce a specular-free image.The experiment results show that,compared to the existing algorithms,the improved algorithm not only removes the highlights more effectively,but also retains the more color and texture information of the original image.And,the average peak signal-to-noise ratio of the improved algorithm is increased by 3.467 while the average structure similarity is increased by 0.073.

关 键 词：改进算法 高光去除 联合双边滤波 最大漫反射色度 双色反射模型 优化阈值 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]