基于非局部总广义变分的图像去噪

TP391.1; 针对全变分(TV)模型在去除图像噪声时容易产生阶梯效应的缺点,将二阶总广义变分(TGV)作为正则项应用于全变分模型中可以有效地去除阶梯效应,并且还能够更好地保持图像边缘纹理结构;利用非局部均值滤波算法的思想来构造非局部微分算子,将非局部微分算子应用于总广义变分模型中,综合提出了一种基于非局部总广义变分的图像去噪新模型.新模型充分利用了图像的全局信息进行去噪.实验结果显示了该模型的有效性和优越性....

Full description

Saved in:
Bibliographic Details
Published in计算机工程与科学 Vol. 39; no. 8; pp. 1520 - 1524
Main Author 王小玉 郭晓中
Format Journal Article
LanguageChinese
Published 哈尔滨理工大学计算机科学与技术学院,黑龙江哈尔滨,150080 2017
Subjects
全变分模型
图像去噪
总广义变分
非局部均值滤波
非局部微分算子
图像去噪
全变分模型
总广义变分
total generalized variation
非局部均值滤波
nonlocal means filtering
非局部微分算子
total variational model
image denoising
nonlocal differential operators
Online AccessGet full text
ISSN1007-130X
DOI10.3969/j.issn.1007-130X.2017.08.021

Cover

More Information
Summary:TP391.1; 针对全变分(TV)模型在去除图像噪声时容易产生阶梯效应的缺点,将二阶总广义变分(TGV)作为正则项应用于全变分模型中可以有效地去除阶梯效应,并且还能够更好地保持图像边缘纹理结构;利用非局部均值滤波算法的思想来构造非局部微分算子,将非局部微分算子应用于总广义变分模型中,综合提出了一种基于非局部总广义变分的图像去噪新模型.新模型充分利用了图像的全局信息进行去噪.实验结果显示了该模型的有效性和优越性.
Bibliography:total variational model; total generalized variation ; nonlocal means filtering ; nonlocal differential operators ;image denoising
The total variation model can remove noise effectively, however, it also brings in staircase effect. To overcome this shortco regularization term in the new d effect, which model ming, we use the second order total generalized variation （TGV） as the enoising model. The TGV model can not only eliminate the staircase also preserve structures are constructed based on , and the new method ma perimental results demonstrate such as edges and textures better. The nonlocal differential operators idea of the nonlocal means filtering algorithm are applied to the TGV good use of the global information of the image to remove noise. Exvalidity and superiority of the proposed method.
43-1258/TP
WANG Xiao-yu,GUO Xiao-zhong （School of Computer Science and Technology, Harbin University of Science and Technology, Harbin 150080, China）
ISSN:1007-130X
DOI:10.3969/j.issn.1007-130X.2017.08.021