基于分数阶偏微分方程和CB模型的彩色图像去噪方法  

Novel Color Image DenoisingMethod Based on Fractional-Order Partial Differential Equation and CB Model

作　　者：周千[1] 

机构地区：[1]西安航空学院理学院,西安710077

出　　处：《计算机与数字工程》2016年第8期1571-1575,共5页Computer & Digital Engineering

基　　金：陕西省教育厅专项科研计划项目(编号:15JK1379);西安航空学院科研基金项目(编号:13XP19;2014KY1210)资助

摘　　要：将分数阶偏微分理论和CB模型相结合应用于图像去噪,提出了一种基于分数阶偏微分方程和CB模型的彩色图像去噪方法。首先,将一副彩色图像分解为色度C和亮度B两部分,然后用分数阶偏微分模型处理亮度B,而对于色度C,由于其受到单位长度的限制,在处理时非常困难,利用拉格朗日乘数法并通过添加辅助变量,将色度转化为两个近似的子问题,从而得到色度的近似处理方法,最后将处理后的亮度B和色度C合成为新的彩色图像。最后通过实验证明了该方法的有效性。Combing fractional-order differential theory with Chromaticity-Brightness（CB） model, a novel image denoising model was proposed, which was based on fractional-order partial differential equation and CB model. Firstly, a color image was decomposed into chromaticity component and brightness component. Secondly, fractional-order differential model was used for brightness component. For chromaticity component, Lagrange multipliers method was used and an auxiliary variable was added to approximate the chromaticity. Thirdly, the retorted image was got by multiplying the recovered chromaticity with recovered brightness. Finally, it proved the validity of the proposed model through the experiment.

关 键 词：彩色图像去噪 分数阶偏微分方程 CB模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]