带曲波域约束的全变差正则化抑噪方法  

Total Variation Regularization Denoising Method with Constraint on Curvelet-Domain

作　　者：卢成武[1] 宋国乡[2] 

机构地区：[1]重庆文理学院数学与计算机科学系,重庆永川402160 [2]西安电子科技大学理学院,陕西西安710071

出　　处：《电子学报》2008年第4期646-649,共4页Acta Electronica Sinica

摘　　要：为了减小曲波变换在图像抑噪应用中所出现的伪吉布斯振荡和"曲波状"伪曲线,提出一种融合计算调和分析与变分法的图像抑噪方法.首先引入第二代曲波紧框架,对降质图像进行非线性曲波变换阈值,然后由所保留系数确定可行域,建立带曲波域约束条件的全变差正则化模型,最后通过投影梯度算法进行求解.实验结果表明该方法在抑噪和保持边缘的同时,使这些失真得到有效地抑制,取得了较为理想的视觉效果.To reduce the psudo-Gibbs effects and the＂curvelet like＂aliased curves resulted from using curvelet transform for image denoising, a noise removal method which combines computational harmonic analysis and variation is presented. Firstly, the nonlinear thresholding strategy is applied to the coefficients of the second generation curvelet transform of noisy image. And then, a total variation regulafization model with constraint condition on curvelet transform domain is established, whose feasible domain is determined by the coefficients remained. Finally, the projected gradient algorithm is used to solve the model. Experiments show that the method can remove noisy and remain edges, while the distortions are suppressed efficiently, and that the vision effect has an ad- vantage of improving.

关 键 词：曲波 抑噪 全变差 非线性阈值 

分 类 号：TN911.73[电子电信—通信与信息系统]