%0 Journal Article
%T Weighted Curvature-preserving PDE Based Image Regularization Method<br>加权型曲率保持 PDE 图像滤波方法
%A ZHENG Yu-Hui
%A ZHANG Jian-Wei
%A CHEN Yun-Jie
%A SUN Quan-Sen
%A <br>郑钰辉
%A 张建伟
%A 陈允杰
%A 孙权森
%J 自动化学报
%D 2011
%I 
%X A weighted curvature-preserving partial different equation (PDE) based filtering method is proposed. First, it is pointed out that the tensor-driven curvature-preserving PDE filtering methods can not preserve image edge very well because that the methods does not take into account the differences between integral curves. Then, we employ local image directional information to design weight coefficients for different integral curves, and present a new tensor-driven curvature-preserving PDE. Experimental results indicate that new method shows superior performance on preserving image edge and curvature geometric structure, as well as some image enhancement ability.
%K Image filtering
%K curvature-preserving
%K partial differential equation (PDE)
%K structure tensor<br>图像滤波
%K 曲率保持
%K 偏微分方程
%K 结构张量
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=E76622685B64B2AA896A7F777B64EB3A&aid=8464C423C76E272EFC12ABB6F2504637&yid=9377ED8094509821&vid=42425781F0B1C26E&iid=F3090AE9B60B7ED1&sid=C9B4EBB1C6A169D8&eid=7CCBDF94263DBB99&journal_id=0254-4156&journal_name=自动化学报&referenced_num=0&reference_num=12