Scale-invariant wave kernel signature for non-rigid 3D shape retrieval

被引:12
作者
Li, Haisheng [1 ]
Sun, Li
Wu, Xiaoqun
Cai, Qiang
机构
[1] Beijing Technol & Business Univ, Sch Comp & Informat Engn, Beijing 100048, Peoples R China
来源
2018 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING (BIGCOMP) | 2018年
基金
中国国家自然科学基金; 北京市自然科学基金;
关键词
non-rigid 3D shape retrieval; scale-invariant; wave kernel signature; MODEL RETRIEVAL;
D O I
10.1109/BigComp.2018.00072
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
The number of non-rigid 3D shapes increases steadily in various areas. It is imperative to develop efficient retrieval system for 3D non-rigid shapes. The wave kernel signature was introduced as an intrinsic local shape descriptor based on the wave function, which represents the average probability of a quantum mechanical particle at a specific location. In this paper, we develop a scale-invariant wave kernel signature normalizing with eigenvalues of the Laplace-Beltrami operator. The proposed descriptor is useful in coping with 3D shapes which have undergone scale transformation. Experimental results on public benchmarks show that our method outperforms the method based on the wave kernel signature for non-rigid 3D shape retrieval.
引用
收藏
页码:448 / 454
页数:7
相关论文
共 37 条
  • [1] [Anonymous], 2003, Visualization and Mathematics, DOI DOI 10.1007/978-3-662-05105-4_2
  • [2] [Anonymous], EPFL
  • [3] Aubry M, 2011, IEEE I CONF COMP VIS, P1411, DOI 10.1109/ICCV.2011.6126396
  • [4] A graph-theoretic approach to 3D shape classification
    Ben Hamza, A.
    [J]. NEUROCOMPUTING, 2016, 211 : 11 - 21
  • [5] Bronstein A., 2010, EUR WORKSH 3D OBJ RE
  • [6] Shape Google: Geometric Words and Expressions for Invariant Shape Retrieval
    Bronstein, Alexander M.
    Bronstein, Michael M.
    Guibas, Leonidas J.
    Ovsjanikov, Maks
    [J]. ACM TRANSACTIONS ON GRAPHICS, 2011, 30 (01):
  • [7] Scale-invariant heat kernel signatures for non-rigid shape recognition
    Bronstein, Michael M.
    Kokkinos, Iasonas
    [J]. 2010 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2010, : 1704 - 1711
  • [8] Learning High-Level Feature by Deep Belief Networks for 3-D Model Retrieval and Recognition
    Bu, Shuhui
    Liu, Zhenbao
    Han, Junwei
    Wu, Jun
    Ji, Rongrong
    [J]. IEEE TRANSACTIONS ON MULTIMEDIA, 2014, 16 (08) : 2154 - 2167
  • [9] On visual similarity based 3D model retrieval
    Chen, DY
    Tian, XP
    Shen, YT
    Ming, OY
    [J]. COMPUTER GRAPHICS FORUM, 2003, 22 (03) : 223 - 232
  • [10] Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder
    Dai, Guoxian
    Xie, Jin
    Zhu, Fan
    Fang, Yi
    [J]. PATTERN RECOGNITION LETTERS, 2016, 83 : 330 - 338