基于照明恢复算子的单幅图像高光去除方法  

Single Image Specular Highlight Removal Based on Illumination Recovering Operator

作　　者：侯成刚 金一[1] 竺长安[1] 

机构地区：[1]中国科学技术大学工程科学学院,安徽合肥230022

出　　处：《工业控制计算机》2020年第10期90-93,共4页Industrial Control Computer

摘　　要：现有的高光去除方法仅仅是处理在特定的背景和光照环境中拍摄的图像,通过人工干预减少了拍摄角度以及其它环境干扰因素的影响,然而这并不符合自然场景的特征,并且这些方法无法解决由高光导致的饱和像素问题,同时会在图像中引入新的伪影。针对高光图像中存在饱和像素的问题,提出一种基于照明恢复算子的单幅图像高光去除方法。首先利用基于前景背景分离原理的闭合式抠图法检测高光区域并得到高光检测系数矩阵;之后分别从实验和理论两个方面验证高光像素值和其在正常照明下的像素值之间存在的线性关系;最后从图像形成方程开始结合高光检测系数矩阵推导出照明恢复算子复原场景中被高光破坏的原始信息,实现高光去除。实验结果表明,所提出的方法能够有效地解决饱和像素的问题,并且不会引入伪影噪声,在各种场景下均取得了优于现有研究方法的高光去除效果。Previous methods of highlight removal only addressed images taken in specific background and illumination environments,reducing the influence of shooting angle and other environmental interference factors through the manual intervention.However,these methods do not conform to the features of natural scenes and can not solve the problem of saturated pixels caused by highlights and thus,introduce artifacts to images.To solve the problem of saturated pxiels in highlight images,a method of single image specular highlight removal based on illumination recovering operator is proposed.First,this paper detect the highlight areas and extract the highlight alpha matte using the closed-form matting method based on the separation of foreground and background.Second,this paper proves the linear relationship between the highlight pixel values and the pixel values under normal lighting experimentally and theoretically.Finally,starting with the image formation equation,derives the illumination recovering operator combined with the highlight detection coefficient matrix to restore the original information destroyed by highlights in the scene and achieve highlight removal.

关 键 词：高光去除 闭合式抠图法 高光形成模型 照明恢复算子 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]