Non-rigid 3D Shape Classification Based on Low-Level Features

  • Yujuan Wu
  • Haisheng LiEmail author
  • Yujia Du
  • Qiang Cai
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 528)


Non-rigid 3D shape classification is an important issue in digital geometry processing. In this paper, we propose a novel non-rigid 3D shape classification method using Convolutional Neural Networks (CNNs) based on the scale-invariant heat kernel signature (SIHKS). Firstly, SIHKS feature is extracted and we can get a matrix for every 3D shape. Then CNNs is employed to shape classification. The matrix of 3D shapes can be the input of CNNs. Finally, we can obtain the category probability of 3D shapes. Experimental results demonstrate the proposed method can get better results compared with SVM.


Non-rigid 3D shape classification Low-level feature Scale-invariant heat kernel signature (SIHKS) Convolutional neural networks 



This work was partially supported by Beijing Natural Science Foundation (4162019).


  1. 1.
    J.W.H. Tangelder, R.C. Veltkamp, A survey of content based 3D shape retrieval methods, in Proceedings of International Conference on Shape Modeling Applications (2004), pp. 145–156Google Scholar
  2. 2.
    A.D. Bimbo, P. Pala, Content-based retrieval of three-dimensional models. ACM Trans. Multimedia Comput. Commun. Appl. (TOMM) 2(1), 20–43 (2006)Google Scholar
  3. 3.
    R. Jain, J. Tyagi, S.K. Singh et al., Hybrid context aware recommender systems, in Advance-ment in Mathematical Sciences: Proceedings of the, International Conference on Recent Advances in Mathematical Sciences and ITS Applications, pp. 020–028 (2017)Google Scholar
  4. 4.
    P.S. Wang, Y. Liu, Y.X. Guo et al., O-CNN: octree-based convolutional neural networks for 3D shape analysis. ACM Trans. Graph. 36(4), 72 (2017)Google Scholar
  5. 5.
    Y. Yubin, L. Hui, Z. Qing, Content-based 3D model retrieval: a survey. Chin. J. Comput. 27(10), 1297–1310 (2004)MathSciNetGoogle Scholar
  6. 6.
    C. Li, A.B. Hamza, A multiresolution descriptor for deformable 3D shape retrieval. Vis. Comput. 29(6–8), 513–524 (2013)CrossRefGoogle Scholar
  7. 7.
    G. Dai, J. Xie, F. Zhu et al., Learning a discriminative deformation-invariant 3D shape descriptor via many-to-one encoder. Pattern Recogn. Lett. 83, 330–338 (2016)CrossRefGoogle Scholar
  8. 8.
    R.M. Rustamov, Laplace-Beltrami eigenfunctions for deformation invariant shape representation, in Proceedings of the fifth Eurographics symposium on Geometry processing (Eurographics Association, 2007), pp. 225–233Google Scholar
  9. 9.
    R.M. Rustamov, Template based shape descriptor, in Proceedings of the 2nd Eurographics conference on 3D Object Retrieval (Eurographics Association, 2009), pp. 1–7Google Scholar
  10. 10.
    J. Sun, M. Ovsjanikov, L. Guibas, A concise and provably informative multi-scale signature based on heat diffusion. Comput. Graph. Forum 28(5), 1383–1392 (2010)CrossRefGoogle Scholar
  11. 11.
    M.M. Bronstein, I. Kokkinos, Scale-invariant heat kernel signatures for non-rigid shape recognition. Comput. Vis. Pattern Recog (IEEE), 1704–1711 (2010)Google Scholar
  12. 12.
    M. Aubry, U. Schlickewei, D. Cremers, The wave kernel signature: a quantum mechanical approach to shape analysis, in IEEE International Conference on Computer Vision Work-shops (IEEE, 2011), pp. 1626–1633Google Scholar
  13. 13.
    Z. Li, D. Wang, L. Boyang et al., 3D model classification using salient features for content representation, in International Conference on Natural Computation (IEEE, 2010), pp. 3541–3545Google Scholar
  14. 14.
    F.W. Qin, L.I. Lu-Ye, S.M. Gao et al., A deep learning approach to the classification of 3D CAD models. Front. Inf. Technol. Electr. Eng. 15(2), 91–106 (2014)Google Scholar
  15. 15.
    S. Bu, Z. Liu, J. Han et al., Learning high-level feature by deep belief networks for 3-D model retrieval and recognition. IEEE Trans. Multimed. 16(8), 2154–2167 (2014)CrossRefGoogle Scholar
  16. 16.
    B. Leng, X. Zhang, M. Yao et al., A 3D model recognition mechanism based on deep Boltz-mann machines. Neurocomputing 151(151), 593–602 (2015)CrossRefGoogle Scholar
  17. 17.
    Z. Lian, A. Godil, T. Fabry et al., SHREC’10 track: non-rigid 3D shape retrieval, in Eurographics Workshop on 3D Object Retrieval, Norrköping, Sweden, 2 May 2010, pp. 101–108Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Yujuan Wu
    • 1
    • 2
  • Haisheng Li
    • 1
    • 2
    Email author
  • Yujia Du
    • 1
    • 2
  • Qiang Cai
    • 1
    • 2
  1. 1.School of Computer and Information EngineeringBeijing Technology and Business UniversityBeijingChina
  2. 2.Beijing Key Laboratory of Big Data Technology for Food SafetyBeijingChina

Personalised recommendations