research-article

Deep learning with geodesic moments for 3D shape classification

Authors:

Lorenzo Luciano,

A. Ben HamzaAuthors Info & Claims

Pattern Recognition Letters, Volume 105, Issue C

Pages 182 - 190

https://doi.org/10.1016/j.patrec.2017.05.011

Published: 01 April 2018 Publication History

Abstract

We present an integrated framework for 3D shape classification using deep learning with geodesic moments.We construct high-level features using a two-layer stacked sparse autoencoder.We demonstrate the better classification accuracy of our approach on several 3D shape benchmarks.We conduct a comprehensive comparison with existing algorithms. In this paper, we present a deep learning framework for efficient 3D shape classification using geodesic moments. Our approach inherits many useful properties from the geodesic distance, most notably the capture of the intrinsic geometric structure of 3D shapes and the invariance to isometric deformations. Moreover, we show the similarity between the convergent series of the geodesic moments and the inverse-square eigenvalues of the LaplaceBeltrami operator in the continuous setting. The proposed algorithm uses a two-layer stacked sparse autoencoder to learn deep features from geodesic moments by training the hidden layers individually in an unsupervised fashion, followed by a softmax classifier. Experimental results on three standard 3D shape benchmarks demonstrate superior performance of the proposed approach compared to existing methods.

References

[1]

W. Shen, Y. Wang, X. Bai, H. Wang, L. Latecki, Shape clustering: common structure discovery, Pattern Recognit., 46 (2013) 539-550.

Digital Library

[2]

S. Biasotti, A. Cerri, M. Abdelrahman, M. Aono, A. Ben Hamza, M. El-Melegy, A. Farag, V. Garro, A. Giachetti, D. Giorgi, A. Godil, C. Li, Y.-J. Liu, H. Martono, C. Sanada, A. Tatsuma, S. Velasco-Forero, C.-X. Xu, SHREC14 track: retrieval and classification on textured 3d models, 2014.

[3]

C. Li, A. Stevens, C. Chen, Y. Pu, Z. Gan, L. Carin, Learning weight uncertainty with stochastic gradient MCMC for shape classification, 2016.

[4]

D. Pickup, X. Sun, P. Rosin, R. Martin, Z. Cheng, Z. Lian, M. Aono, A. Ben Hamza, A. Bronstein, M. Bronstein, S. Bu, U. Castellani, S. Cheng, V. Garro, A. Giachetti, A. Godil, L. Isaia, J. Han, H. Johan, L. Lai, B. Li, C. Li, H. Li, R. Litman, X. Liu, Z. Liu, Y. Lu, L. Sun, G. Tam, A. Tatsuma, J. Ye, Shape retrieval of non-rigid 3d human models, Int J. Comput. Vision, 120 (2016) 169-193.

Digital Library

[5]

M. Savva, F. Yu, H. Su, M. Aono, B. Chen, D. Cohen-Or, W. Deng, H. Su, S. Bai, X. Bai, J.H. N. Fish, E. Kalogerakis, E. Learned-Miller, Y. Li, M. Liao, S. Maji, Y. Wang, N. Zhang, Z. Zhou, SHREC16 track: large-scale 3D shape retrieval from ShapeNet Core55, 2016.

[6]

R. Rustamov, Laplace-Beltrami eigenfunctions for deformation invariant shape representation, 2007.

[7]

J. Sun, M. Ovsjanikov, L. Guibas, A concise and provably informative multi-scale signature based on heat diffusion, Comput. Graphics Forum, 28 (2009) 1383-1392.

Digital Library

[8]

M. Aubry, U. Schlickewei, D. Cremers, The wave kernel signature: a quantum mechanical approach to shape analysis, 2011.

[9]

M. Masoumi, A. Ben Hamza, A spectral graph wavelet approach for nonrigid 3D shape retrieval, Pattern Recognit. Lett., 83 (2016) 339-348.

Digital Library

[10]

M. Reuter, F. Wolter, N. Peinecke, Laplace-Beltrami spectra as Shape-DNA of surfaces and solids, Comput.-Aided Des., 38 (2006) 342-366.

Digital Library

[11]

A. Chaudhari, R. Leahy, B. Wise, N. Lane, R. Badawi, A. Joshi, Global point signature for shape analysis of carpal bones, Phys. Med. Biol., 59 (2014) 961-973.

[12]

Z. Gao, Z. Yu, X. Pang, A compact shape descriptor for triangular surface meshes, Comput.-Aided Des., 53 (2014) 62-69.

[13]

Z. Lian, A. Godil, B. Bustos, M. Daoudi, J. Hermans, S. Kawamura, Y. Kurita, G. Lavou, H. Nguyen, R. Ohbuchi, Y. Ohkita, Y. Ohishi, F. Porikli, M. Reuter, I. Sipiran, D. Smeets, P. Suetens, H. Tabia, D. Vandermeulen, A comparison of methods for non-rigid 3D shape retrieval, Pattern Recognit., 46 (2013) 449-461.

Digital Library

[14]

C. Li, A. Ben Hamza, Spatially aggregating spectral descriptors for nonrigid 3D shape retrieval: a comparative survey, Multimedia Syst., 20 (2014) 253-281.

Digital Library

[15]

J. Schmidhuber, Deep learning in neural networks: an overview, Neural Netw., 61 (2015) 85-117.

Digital Library

[16]

Y. Bengio, Learning deep architectures for AI, Found. Trends Mach. Learn., 2 (2009) 1-127.

Digital Library

[17]

S. Bu, Z. Liu, J. Han, J. Wu, R. Ji, Learning high-level feature by deep belief networks for 3-D model retrieval and recognition, IEEE Trans. Multimedia, 24 (2014) 2154-2167.

[18]

H. Su, S. Maji, E. Kalogerakis, E. Learned-Miller, Multi-view convolutional neural networks for 3D shape recognition, 2015.

[19]

C. Qi, H. Su, M. Niener, A. Dai, M. Yan, L. Guibas, Volumetric and multi-view CNNs for object classification on 3D data, 2016.

[20]

Z. Zhu, X. Wang, S. Bai, C. Yao, X. Bai, Deep learning representation using autoencoder for 3D shape retrieval, Neurocomputing (2016).

Digital Library

[21]

S. Rosenberg, The Laplacian on a Riemannian Manifold, Cambridge University Press, 1997.

[22]

D. Aouada, H. Krim, Squigraphs for fine and compact modeling of 3D shapes, IEEE Trans. Image Process., 19 (2010) 306-321.

Digital Library

[23]

O. Calin, D.-C. Chang, Gemetric Mechanics on Riemannian Manifolds: Applications to Partial Differential Equations, Birkhuser, 2005.

[24]

Z. Lian, A. Godil, B. Bustos, M. Daoudi, J. Hermans, S. Kawamura, Y. Kurita, G. Lavou, H. Nguyen, R. Ohbuchi, Y. Ohkita, Y. Ohishi, F. Porikli, M. Reuter, I. Sipiran, D. Smeets, P. Suetens, H. Tabia, D. Vandermeulen, SHREC11 track: shape retrieval on non-rigid 3D watertight meshes, 2011.

[25]

Z. Lian, A. Godil, T. Fabry, T. Furuya, J. Hermans, R. Ohbuchi, C. Shu, D. Smeets, P. Suetens, D. Vandermeulen, S. Wuhrer, SHREC10 track: non-rigid 3D shape retrieval, 2010.

[26]

J.Z. Z. Lian, S. Choi, H. ElNaghy, J. El-Sana, T. Furuya, A. Giachetti, R.G.L. Isaia, L. Lai, C. Li, H. Li, F. Limberger, R. Martin, R. Nakanishi, A.N.L. Nonato, R. Ohbuchi, K. Pevzner, D. Pickup, P. Rosin, A. Sharf, L. Sun, X. Sun, S. Tari, G. Unal, R. Wilson, SHREC15 track: non-rigid 3D shape retrieval, 2015.

[27]

M. Khabou, L. Hermi, M. Rhouma, Shape recognition using eigenvalues of the Dirichlet Laplacian, Pattern Recognit., 40 (2007) 141-153.

Digital Library

[28]

F. Hajati, A. Raie, Y. Gao, 2.5D face recognition using patch geodesic moments, Pattern Recognit., 45 (2012) 969-982.

Digital Library

Cited By

Han LHe JDou FMa HXie XYang W(2023)A viewpoint-guided prototype network for 3D shape classificationMultimedia Systems10.1007/s00530-023-01177-929:6(3531-3547)Online publication date: 1-Dec-2023
https://dl.acm.org/doi/10.1007/s00530-023-01177-9
Feng WZhang JZhou YXin S(2022)GDR-Net: A Geometric Detail Recovering Network for 3D Scanned ObjectsIEEE Transactions on Visualization and Computer Graphics10.1109/TVCG.2021.311065828:12(3959-3973)Online publication date: 1-Dec-2022
https://dl.acm.org/doi/10.1109/TVCG.2021.3110658
Han LLan PShi XWang XHe JLi G(2022)Topological and geometrical joint learning for 3D graph dataMultimedia Tools and Applications10.1007/s11042-022-13806-y82:10(15457-15474)Online publication date: 5-Oct-2022
https://dl.acm.org/doi/10.1007/s11042-022-13806-y
Show More Cited By

Index Terms

Deep learning with geodesic moments for 3D shape classification
1. Computing methodologies
  1. Machine learning
    1. Learning paradigms
      1. Supervised learning
        Supervised learning by classification
    2. Machine learning approaches
      1. Neural networks

Index terms have been assigned to the content through auto-classification.

Recommendations

Deep similarity network fusion for 3D shape classification

In this paper, we introduce a deep similarity network fusion framework for 3D shape classification using a graph convolutional neural network, which is an efficient and scalable deep learning model for graph-structured data. The proposed approach ...
Convolutional Shape-Aware Representation for 3D Object Classification

Deep learning has recently emerged as one of the most popular and powerful paradigms for learning tasks. In this paper, we present a deep learning approach to 3D shape classification using convolutional neural networks. The proposed framework takes a ...
A global geometric framework for 3D shape retrieval using deep learning
Highlights
- We present a geometric framework for 3D shape retrieval using geodesic moments.
Graphical abstract

Display Omitted

Abstract
Shape representations provide compact, parsimonious shape descriptions that are often used in object recognition and retrieval tasks. In light of the increased processing power of graphics cards and the availability of large-scale ...

Comments

Information & Contributors

Information

Published In

cover image Pattern Recognition Letters

Pattern Recognition Letters Volume 105, Issue C

April 2018

237 pages

ISSN:0167-8655

Issue’s Table of Contents

Publisher

Elsevier Science Inc.

United States

Publication History

Published: 01 April 2018

Author Tags

Qualifiers

Research-article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

8
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 27 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Han LHe JDou FMa HXie XYang W(2023)A viewpoint-guided prototype network for 3D shape classificationMultimedia Systems10.1007/s00530-023-01177-929:6(3531-3547)Online publication date: 1-Dec-2023
https://dl.acm.org/doi/10.1007/s00530-023-01177-9
Feng WZhang JZhou YXin S(2022)GDR-Net: A Geometric Detail Recovering Network for 3D Scanned ObjectsIEEE Transactions on Visualization and Computer Graphics10.1109/TVCG.2021.311065828:12(3959-3973)Online publication date: 1-Dec-2022
https://dl.acm.org/doi/10.1109/TVCG.2021.3110658
Han LLan PShi XWang XHe JLi G(2022)Topological and geometrical joint learning for 3D graph dataMultimedia Tools and Applications10.1007/s11042-022-13806-y82:10(15457-15474)Online publication date: 5-Oct-2022
https://dl.acm.org/doi/10.1007/s11042-022-13806-y
Lakhili ZEl Alami AMesbah ABerrahou AQjidaa H(2020)Robust classification of 3D objects using discrete orthogonal moments and deep neural networksMultimedia Tools and Applications10.1007/s11042-020-08654-779:27-28(18883-18907)Online publication date: 1-Jul-2020
https://dl.acm.org/doi/10.1007/s11042-020-08654-7
Lv CWu ZWang XZhou M(2019)Constructing 3D facial hierarchical structure based on surface measurementsMultimedia Tools and Applications10.1007/s11042-018-6839-y78:11(14753-14776)Online publication date: 1-Jun-2019
https://dl.acm.org/doi/10.1007/s11042-018-6839-y
Luciano LBen Hamza A(2019)Deep similarity network fusion for 3D shape classificationThe Visual Computer: International Journal of Computer Graphics10.1007/s00371-019-01668-935:6-8(1171-1180)Online publication date: 1-Jun-2019
https://dl.acm.org/doi/10.1007/s00371-019-01668-9
Setty SHegde SSatyappanavar SMudenagudi U(2018)Evaluation of Point Cloud Categorization for Rigid and Non-Rigid 3D ObjectsProceedings of the 11th Indian Conference on Computer Vision, Graphics and Image Processing10.1145/3293353.3293413(1-9)Online publication date: 18-Dec-2018
https://dl.acm.org/doi/10.1145/3293353.3293413
Wang LMeng WXi RZhang YLu LZhang X(2018)Large-scale 3D Point Cloud Classification Based On Feature Description Matrix By CNNProceedings of the 31st International Conference on Computer Animation and Social Agents10.1145/3205326.3205355(43-47)Online publication date: 21-May-2018
https://dl.acm.org/doi/10.1145/3205326.3205355

View Options

View options

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Issue’s Table of Contents