Abstract
Extracting features with strong expressive and discriminative ability is one of key factors for the effectiveness of 3D model classifier. Lots of research work has illustrated that deep belief networks (DBN) have enough power to represent the distributions of input data. In this paper, we apply DBN for extracting the features of 3D model. After implementing a contrastive divergence method, we obtain a trained-well DBN, which can powerfully represent the input data. Therefore, the feature from the output of last layer is acquired. This procedure is unsupervised. Due to the limit of labeled data, a semi-supervised method is utilized to recognize 3D objects using the feature obtained from the trained DBN. The experiments are conducted in the publicly available Princeton Shape Benchmark (PSB), and the experimental results demonstrate the effectiveness of our method.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Ansary, T.F., Daoudi, M., Vandeborre, J.P.: A bayesian 3-d search engine using adaptive views clustering. IEEE Transaction on Multimedia 9(1), 78–88 (2007)
Bengio, Y.: Learning deep architectures for ai. Foundations and Trends® in Machine Learning 2(1), 1–127 (2009)
Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H.: Greedy layer-wise training of deep networks. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 153–160 (2007)
Blum, A., Chawla, S.: Learning from labeled and unlabeled data using graph mincuts. In: Proceedings of the Eighteenth International Conference on Machine Learning, pp. 19–26 (2001)
Carreira-Perpinan, M.A., Hinton, G.E.: On contrastive divergence learning. In: Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics, pp. 33–40 (2005)
Daras, P., Axenopoulos, A.: A 3D shape retrieval framework supporting multimodal queries. International Journal of Computer Vision 89(2-3), 229–247 (2010)
Daras, P., Zarpalas, D., Tzovaras, D., Strintzis, M.G.: Efficient 3D model search and retrieval using generalized 3D radon transforms. IEEE Transactions on Multimedia 8(1), 101–114 (2006)
Gao, Y., Dai, Q.H., Zhang, N.Y.: 3D model comparison using spatial structure circular descriptor. Pattern Recognition 43(3), 1142–1151 (2010)
Gao, Y., Tang, J.H., Hong, R.C., Yan, S.C., Dai, Q.H., Zhang, N.Y., Chua, T.S.: Camera constraint-free view-based 3-d object retrieval. IEEE Transactions on Image Processing 21(4), 2269–2281 (2012)
Gao, Y., Tang, J.H., Li, H.J., Dai, Q.H., Zhang, N.Y.: View-based 3D model retrieval with probabilistic graph model. Neurocomputing 73(10), 1900–1905 (2010)
Gao, Y., Wang, M., Ji, R.R., Wu, X.D., Dai, Q.H.: 3D object retrieval with hausdorff distance learning. Accepted for Publication in IEEE Transactions on Industrial Electronics (2013)
Gao, Y., Wang, M., Tao, D.C., Ji, R.R., Dai, Q.H.: 3-d object retrieval and recognition with hypergraph analysis. IEEE Transactions on Image Processing 21(9), 4290–4303 (2012)
Gao, Y., Wang, M., Zha, Z.J., Tian, Q., Dai, Q.H., Zhang, N.Y.: Less is more: efficient 3-d object retrieval with query view selection. IEEE Transactions on Multimedia 13(5), 1007–1018 (2011)
Gao, Y., Yang, Y., Dai, Q., Zhang, N.: 3D object retrieval with bag-of-region-words. In: Proceedings of the ACM International Conference on Multimedia, Firenze, Italy, pp. 955–958 (2010)
Goldfeder, C., Allen, P.: Autotagging to improve text search for 3D models. In: ACM/IEEE-CS Joint Conference on Digital Libraries, Pittsburgh, PA, USA, pp. 355–358 (2008)
Goldfeder, C., Feng, H., Allen, P.: Shrec08 entry: Training set expansion via autotags. In: Proceedings of the IEEE International Conference on Shape Modeling and Applications, Stony Brook, NY, USA, pp. 233–234 (2008)
Hinton, G.E.: A practical guide to training restricted boltzmann machines. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) Neural Networks: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 599–619. Springer, Heidelberg (2012)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation 18(7), 1527–1554 (2006)
Ji, R.R., Gao, Y., Hong, R.C., Liu, Q., Tao, D.C., Li, X.L.: Spectral-Spatial Constraint Hyperspectral Image Classification. Accepted for Publication in IEEE Transactions on Geoscience and Remote Sensing (2013)
Ji, R.R., Yao, H., Liu, W., Sun, X., Tian, Q.: Task-dependent visual-codebook compression. IEEE Transactions on Image Processing 21(4), 2282–2293 (2012)
Le Roux, N., Bengio, Y.: Representational power of restricted boltzmann machines and deep belief networks. Neural Computation 20(6), 1631–1649 (2008)
Leng, B., Li, L., Qin, Z.: MADE: A composite visual-based 3D shape descriptor. In: Gagalowicz, A., Philips, W. (eds.) MIRAGE 2007. LNCS, vol. 4418, pp. 93–104. Springer, Heidelberg (2007)
Leng, B., Qin, Z.: Automatic combination of feature descriptors for effective 3D shape retrieval. In: Gagalowicz, A., Philips, W. (eds.) MIRAGE 2007. LNCS, vol. 4418, pp. 36–46. Springer, Heidelberg (2007)
Leng, B., Qin, Z.: A powerful relevance feedback mechanism for content-based 3D model retrieval. Multimedia Tools and Applications 40(1), 135–150 (2008)
Leng, B., Qin, Z., Cao, X.M., Wei, T., Zhang, Z.X.: Mate: a visual based 3D shape descriptor. Chinese Journal of Electronics 18(2), 291–296 (2009)
Leng, B., Qin, Z., Li, L.Q.: Support vector machine active learning for 3D model retrieval. Journal of Zhejiang University SCIENCE A 8(12), 1953–1961 (2007)
Leng, B., Xiong, Z.: Modelseek: an effective 3D model retrieval system. Multimedia Tools and Applications 51(3), 935–962 (2011)
Leng, B., Xiong, Z., Fu, X.W.: A 3D shape retrieval framework for 3D smart cities. Frontiers of Computer Science 4(3), 394–404 (2010)
Li, J.B., Sun, W.H., Wang, Y.H., Tang, L.L.: 3D model classification based on nonparametric discriminant analysis with kernels. Neural Computing and Applications 22(3-4), 771–781 (2013)
Papadakis, P., Pratikakis, I., Perantonis, S., Theoharis, T.: Efficient 3D shape matching and retrieval using a concrete radialized spherical projection representation. Pattern Recognition 40(9), 2437–2452 (2007)
Papadakis, P., Pratikakis, I., Theoharis, T., Perantonis, S.: Panorama: A 3D shape descriptor based on panoramic views for unsupervised 3D object retrieval. International Journal of Computer Vision 89(2), 177–192 (2010)
Park, Y.S., Yun, Y.I., Choi, J.S.: A new shape descriptor using sliced image histogram for 3D model retrieval. IEEE Transactions on Consumer Electronics 55(1), 240–247 (2009)
Patane, G., Spagnuolo, M., Falcidieno, B.: A minimal contouring approach to the computation of the reeb graph. IEEE Transactions on Visualization and Computer Graphics 15(4), 583–595 (2009)
Shilane, P., Min, P., Kazhdan, M., Funkhouser, T.: The princeton shape benchmark. In: Proceedings of Shape Modeling and Applications, Palazzo Ducale, Genova, Italy, pp. 167–178 (2004)
Sutskever, I., Hinton, G.E.: Deep, narrow sigmoid belief networks are universal approximators. Neural Computation 20(11), 2629–2636 (2008)
Vranic, D.V.: Desire: a composite 3D-shape descriptor. In: Proceedings of IEEE International Conference on Multimedia and Expo, Amsterdam, Netherlands, pp. 962–965 (2005)
Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. The Journal of Machine Learning Research 10(6), 207–244 (2009)
Wen, Y., Gao, Y., Hong, R.C., Luan, H.B., Liu, Q., Shen, J.L., Ji, R.R.: View-based 3D object retrieval by bipartite graph matching. In: Proceedings of the ACM Multimedia, Nara, Japan, pp. 897–900 (2012)
Zhou, D., Bousquet, O., Lal, T.N., Weston, J., Schölkopf, B.: Learning with local and global consistency. In: Proceedings of the Advances in Neural Information Processing Systems, pp. 321–328 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Leng, B., Zhang, X., Yao, M., Xiong, Z. (2014). 3D Object Classification Using Deep Belief Networks. In: Gurrin, C., Hopfgartner, F., Hurst, W., Johansen, H., Lee, H., O’Connor, N. (eds) MultiMedia Modeling. MMM 2014. Lecture Notes in Computer Science, vol 8326. Springer, Cham. https://doi.org/10.1007/978-3-319-04117-9_12
Download citation
DOI: https://doi.org/10.1007/978-3-319-04117-9_12
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-04116-2
Online ISBN: 978-3-319-04117-9
eBook Packages: Computer ScienceComputer Science (R0)