Feature-Based Methods in 3D Shape Analysis
Feature-Based Methods in 3D Shape Analysis
复制标题
3D 形状分析中基于特征的方法
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
M. Ovsjanikov
中科院分区：
文献类型：
--
作者：
A. Bronstein;M. Bronstein;M. Ovsjanikov
计算机视觉和模式识别社区最近见证了基于特征的方法在包括对象识别和图像检索在内的众多应用中的激增。类似的概念和类似的方法正在渗透到3D形状分析的各个领域，包括非刚性形状检索和匹配。在这一章中，我们提出了成熟的概念和国家的最先进的基于特征的方法在三维形状分析。特别是，兴趣点的检测和局部形状描述符的生成方法进行了讨论。涵盖了广泛的方法，包括基于曲率的方法、基于高斯尺度空间差的方法以及采用热核方法最新进展的方法。
The computer vision and pattern recognition communities have recently witnessed a surge in feature-based methods for numerous applications including object recognition and image retrieval. Similar concepts and analogous approaches are penetrating the world of 3D shape analysis in a variety of areas including non-rigid shape retrieval and matching. In this chapter, we present both mature concepts and the state-of-the-art of feature-based approaches in 3D shape analysis. In particular, approaches to the detection of interest points and the generation of local shape descriptors are discussed. A wide range of methods is covered including those based on curvature, those based on difference-of-Gaussian scale space, and those that employ recent advances in heat kernel methods.
基于多尺度热核的体积形态特征。
DOI：
10.1007/978-3-319-24574-4_90
发表时间：
2015
期刊：
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
影响因子：
--
作者：
Wang,Gang;Wang,Yalin
通讯作者：
Wang,Yalin