一种快速点模型去噪方法  

FAST DENOISING METHOD FOR POINT-SAMPLED MODEL

作　　者：倪彤光[1] 顾晓清[1] 马正华[1] 杨长春[1] 

机构地区：[1]江苏工业学院信息科学与工程学院,江苏常州213164

出　　处：《计算机应用与软件》2010年第9期69-71,90,共4页Computer Applications and Software

基　　金：江苏省高校自然科学研究计划(06KJB520022);江苏省教育厅自然科学研究指导性计划(06KJD310050);江苏工业学院校基金资助(ZMF09020017)

摘　　要：消除噪声是构造完美三维模型过程中必不可少的一步。胡国飞等提出了基于三维mean-shift过程的各向异性点模型去噪算法但该算法效率较低,为此提出用准柯西函数取代该算法所采用的高斯函数,提高了算法效率。实验结果表明,此方法能在有效剔除点模型表面噪声的同时较好地保持表面的尖锐特征。Denoising is an essential step in creating perfect 3D models. As 3D mean-shift procedure-based anisotropie algorithm proposed for point-sampled model denoising by Guofei Hu is not efficient enough, a method is proposed that using the quasi-Cauchy kernel to replace the Gauss kernel used in the anisotropic algorithm, so that the efficiency of the algorithm is improved. Experiments show that the method can eliminate the noise on the surface of the point-sampled model effectively and meanwhile the sharp features of the surface are preserved well.

关 键 词：点模型 mean-shift过程 高斯函数 柯西函数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]