三维模型匹配的谱图小波描述符  

Spectral graph wavelet descriptor for three-dimensional shape matching

作　　者：胡玲 李钦松 刘圣军[1] 刘新儒[1] HU Ling;LI Qin-song;LIU Sheng-jun;LIU Xin-ru(School of Mathematics and Statistics,Central South University,Changsha 410000,China;School of Mathematics and Computing,Hunan First Normal College,Changsha 410000,China)

机构地区：[1]中南大学数学与统计学院,湖南长沙410000 [2]湖南第一师范学院数学与计算科学学院,湖南长沙410000

出　　处：《浙江大学学报（工学版）》2019年第4期761-769,共9页Journal of Zhejiang University：Engineering Science

基　　金：国家自然科学基金资助项目(61572527;61628211;61602524);湖南省教育厅科学研究一般项目(16C0333)

摘　　要：为了实现三维模型的点-点匹配,基于谱图小波变换(SGWT)构建点的描述符.对三维模型各顶点处的脉冲函数进行多尺度谱图小波变换,因为这些小波系数能够充分反映模型各顶点处的多尺度几何信息,将它们依次作为元素形成多维向量.该向量即为模型各点的谱图小波描述符,点描述符的欧式距离可以度量点与点之间的几何差异性.由于谱图小波(SGW)同时使用低通和带通滤波器分析信号且能够稳定地重构信号,这使得提出的描述符具有很好的形状分辨能力、紧凑性和鲁棒性.实验结果显示,谱图小波描述符具有比同类方法更卓越的性能.A point descriptor was proposed based on the spectral graph wavelet transform(SGWT)for the pointwise three-dimensional shape matching.SGWT was performed for a series of impulse functions centered at each point on the shape.Since these wavelet coefficients can reflect sufficient multiscale geometric information around each point,they are orderly treated as elements of a high.dimensional vector.Such vector is the descriptor for each point and the geometric disparity between points can be measured by their Euclidean distance.The spectral graph wavelet(SGW)both use low-pass and band-pass filters to analyze the signals and can stably reconstruct them,which makes the proposed descriptor be significant discriminative,compact and robust.The experimental results show that the proposed descriptor can achieve better performance than similar methods.

关 键 词：拉普拉斯-贝尔特米算子 模型匹配 谱图小波(SGW) 点描述符 滤波器 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]