一种全变差正则化流场的图像抑噪方法  

An Image Denoising Method Using Total Variation Regularization for Flow Field

作　　者：卢成武[1,2] 宋国乡[1] 

机构地区：[1]西安电子科技大学理学院,西安710071 [2]重庆文理学院数学与计算机系,重庆402160

出　　处：《电子与信息学报》2009年第1期112-115,共4页Journal of Electronics & Information Technology

基　　金：国家自然科学基金(60473119)资助课题

摘　　要：利用Meyer的图像分解理论,提出一种磨光流场的全变差正则化抑噪方法。该方法首先引入负指数Hilbert-Sobolev范数度量逼近项,对图像水平曲线的法向量场进行全变差正则化磨光,然后构造出一个曲面拟合模型,拟合磨光后的流场。最后,利用有限差分法对各模型所导出Euler-Lagrange方程进行数值求解。实验结果表明,该方法在有效去噪的同时,使边缘和纹理信息均得到较好的保持。Using image decomposition theory proposed by Meyer, a total variation image denoising method based on smoothing flow field is presented. Firstly, through applying Hilbert-Sobolev norm to measure fidelity term, a total variation filter is used to smooth the normal vectors of the level curves of a noise image. And then, a model is constructed to find a surface which fit smoothed normal vectors. Finally, finite difference schemes are used to solve the Euler-Lagrange functions derived from above models. The experiments show that the approach not only can remove noisy efficiently, but also can retain edges and texture.

关 键 词：图像分解 全变差 流场 Hilbert-Sobolev范数 

分 类 号：TN911.73[电子电信—通信与信息系统]