Learning semantic categories for 3D model retrieval

ABSTRACT

A shape similarity judgment among a pair of 3D models is often influenced by their semantics, in addition to their shapes. If we could somehow incorporate semantic knowledge into a "shape similarity" comparison method, retrieval performance of a shape-based 3D model retrieval system could be improved. This paper presents a 3D model retrieval method that successfully incorporates semantic information from human-made categories (labels) in a training database. Our off-line, 2-stage semi-supervised approach learns efficiently from a small set of labeled models. The method first performs unsupervised learning from a large set of unlabeled 3D models to find a non-linear subspace on which the shape features are distributed. It then performs a supervised learning from a much smaller set of labeled 3D models to learn multiple semantic categories at once. Our experimental evaluation showed that the retrieval performance using proposed method is significantly higher than those of both supervised-only and unsupervised-only learning methods.

REFERENCES

• 1: Indriyati Atmosukarto , Wee Kheng Leow , Zhiyong Huang, Feature Combination and Relevance Feedback for 3D Model Retrieval, Proceedings of the 11th International Multimedia Modelling Conference, p.334-339, January 12-14, 2005 [doi>10.1109/MMMC.2005.39]
• 2: Mikhail Belkin , Partha Niyogi, Laplacian Eigenmaps for dimensionality reduction and data representation, Neural Computation, v.15 n.6, p.1373-1396, June 2003 [doi>10.1162/089976603321780317]
• 3: P. Bratley, B. L. Fox, H. Niederreiter, Algorithm 738: Programs to Generate Niederreiter's Low-discrepancy Sequences, ACM TOMS Algorithm 738.
• 4: Benjamin Bustos , Daniel Keim , Dietmar Saupe , Tobias Schreck , Dejan Vranic, Automatic Selection and Combination of Descriptors for Effective 3D Similarity Search, Proceedings of the IEEE Sixth International Symposium on Multimedia Software Engineering, p.514-521, December 13-15, 2004
• 5: Chen, S., C.F.N. Cowan, P. M. Grant, Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks, IEEE Trans. on Neural Networks, 2(2), pp. 302--309, (1991)
• 6: D.-Y. Chen, X.-P. Tian, Y.-T. Shen, M. Ouh-young, On Visual Similarity Based 3D Model Retrieval, Computer Graphics Forum, 22(3), pp. 223--232, (2003).
• 7: Michael Elad , Ayellet Tal , Sigal Ar, Content based retrieval of VRML objects: an iterative and interactive approach, Proceedings of the sixth Eurographics workshop on Multimedia 2001, p.107-118, September 08-09, 2001, Manchester, UK
• 8: Simon Haykin, Neural Networks: A Comprehensive Foundation (3rd Edition), Prentice-Hall, Inc., Upper Saddle River, NJ, 2007
• 9: X. He, P. Niyogi, Locality Preserving Projections, Advances in Neural Information Processing Systems, 16, Vancouver, Canada, (2003). http://people.cs.uchicago.edu/~xiaofei/LPP.html
• 10: Xiaofei He , Wei-Ying Ma , Hong-Jiang Zhang, Learning an image manifold for retrieval, Proceedings of the 12th annual ACM international conference on Multimedia, October 10-16, 2004, New York, NY, USA [doi>10.1145/1027527.1027532]
• 11: M. Iyer, S. Jayanti, K. Lou, Y. Kalyanaraman, K. Ramani, Three Dimensional Shape Searching: State-of-the-art Review and Future Trends, Computer Aided Design, 5(15), pp. 509--530, (2005).
• 12: Michael Kazhdan , Thomas Funkhouser , Szymon Rusinkiewicz, Rotation invariant spherical harmonic representation of 3D shape descriptors, Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing, June 23-25, 2003, Aachen, Germany
• 13: G. Leifman, R. Meir, A. Tal, Semantic-oriented 3d shape retrieval using relevance feedback, The Visual Computer (Pacific Graphics 2005), 21(8-10), pp. 865--875, October 2005.
• 14: D. Lin, Statistical Learning Toolbox, http://www.mathworks.com/matlabcentral/files/12333/content/ sltoolbox_r101/sltdoc/index.html
• 15: M. Novotni, G.-J. Park, R. Wessel, R. Klein Evaluation of Kernel Based Methods for Relevance Feedback in 3D Shape Retrieval, Proc. The Fourth International Workshop on Content-Based Multimedia Indexing (CBMI'05), (2005).
• 16: NTU 3D Model Database ver.1 http://3d.csie.ntu.edu.tw/
• 17: Ryutarou Ohbuchi , Tsuyoshi Takei, Shape-Similarity Comparison of 3D Models Using Alpha Shapes, Proceedings of the 11th Pacific Conference on Computer Graphics and Applications, p.293, October 08-10, 2003
• 18: R. Ohbuchi, T. Minamitani, T. Takei, Shape-similarity search of 3D models by using enhanced shape functions, IJCAT, 23(3/4/5), pp. 70--85, (2005).
• 19: Ryutarou Ohbuchi , Jun Kobayashi, Unsupervised learning from a corpus for shape-based 3D model retrieval, Proceedings of the 8th ACM international workshop on Multimedia information retrieval, October 26-27, 2006, Santa Barbara, California, USA [doi>10.1145/1178677.1178701]
• 20: R. Ohbuchi, J. Kobayashi, A. Yamamoto, T. Shimizu, Comparison of dimension reduction methods for database-adaptive 3D model retrieval, accepted, Proc. 5th International Workshop on Adaptive Multimedia Retrieval (AMR) 2007, Paris, France, July, 2007.
• 21: D. de Ridder, O. Kouropteva, O. Okun, M. Pietikäinen, R. P. W. Duin, Supervised locally linear embedding, Proc. Joint Int. Conf. ICANN/ICONIP 2003, Lecture Notes in Computer Science, 2714, (2003).
• 22: S.T. Roweis, L.K. Saul, Nonlinear Dimensionality Reduction by Locally Linear Embedding, Science, 290(5500), pp. 2323--2326, (2000).
• 23: The Princeton Shape Benchmark, Proceedings of the Shape Modeling International 2004, p.167-178, June 07-09, 2004 [doi>10.1109/SMI.2004.63]
• 24: Masashi Sugiyama, Dimensionality Reduction of Multimodal Labeled Data by Local Fisher Discriminant Analysis, The Journal of Machine Learning Research, 8, p.1027-1061, 5/1/2007
• 25: Statistical Pattern Recognition Toolbox for Mat-lab, http://cmp.felk.cvut.cz/cmp/software/stprtool/index.html
• 26: A Survey of Content Based 3D Shape Retrieval Methods, Proceedings of the Shape Modeling International 2004, p.145-156, June 07-09, 2004 [doi>10.1109/SMI.2004.10]
• 27: J. B. Tanenbaum, V. de Silva, J.C. Langford, A Global Geometric Framework for Nonlinear Dimensionality Reduction, Science, 290(5500), pp. 2319--2323, (2000).
• 28: R. C. Veltkamp, R. Ruijsenaars, M. Spagnuolo, R. Van Zwol, F. ter Haar, SHREC2006 3D Shape Retrieval Contest, Utrecht University Dept. Information and Computing Sciences, Technical Report UU-CS-2006-030 (ISSN: 0924-3275) http://give-lab.cs.uu.nl/shrec/shrec2006/index.html
• 29: D. V. Vrani., 3D Model Retrieval, Ph.D. Thesis, University of Leipzig, 2004. http://merkur01.inf.uni-konstanz.de/CCCC/
• 30: E. Wahl, U. Hillenbrand, G. Hirzinger, Surflet-Pair-Relation Histograms: A Statistical 3D-Shape Representation for Rapid Classification, Proc. 3DIM 2003, pp. 474--481, (2003).

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Information filtering

Additional Classification:
  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.5 Computational Geometry and Object Modeling
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Object recognition

General Terms:
Algorithms, Experimentation, Measurement, Performance

Keywords:
content-based retrieval, manifold learning, shape-based 3D model retrieval