A database-adaptive distance measure for 3D model retrieval

The distance measure, in addition to the shape feature is a key factor in shape based 3D model retrieval. We employed a database adaptive distance measure for 3D model retrieval in the SHREC 2007 CAD track. The method described in this paper uses a feature dimension reduction based on an unsupervised learning of features to produce salient, lower dimensional feature from the original feature. Our method also combines a multiresolution shape comparison approach with the database adaptive distance measure. Our experiments the SHREC 2007 CAD track showed that both adaptive distance measure and multiresolution shape comparison approach added a few percent each to the original shape feature. Our method came in first in the SHREC 2007 CAD track despite the fact that the distance measure was trained by using a set of “generic” 3D models that are not CAD specific.

[1]  Szymon Rusinkiewicz,et al.  Rotation Invariant Spherical Harmonic Representation of 3D Shape Descriptors , 2003, Symposium on Geometry Processing.

[2]  Ron Meir,et al.  Semantic-oriented 3d shape retrieval using relevance feedback , 2005, The Visual Computer.

[3]  Eric Wahl,et al.  Surflet-pair-relation histograms: a statistical 3D-shape representation for rapid classification , 2003, Fourth International Conference on 3-D Digital Imaging and Modeling, 2003. 3DIM 2003. Proceedings..

[4]  Remco C. Veltkamp,et al.  A survey of content based 3D shape retrieval methods , 2004, Proceedings Shape Modeling Applications, 2004..

[5]  Akihiro Yamamoto,et al.  Comparison of Dimension Reduction Methods for Database-Adaptive 3D Model Retrieval , 2007, Adaptive Multimedia Retrieval.

[6]  Daniel A. Keim,et al.  Automatic selection and combination of descriptors for effective 3D similarity search , 2004, IEEE Sixth International Symposium on Multimedia Software Engineering.

[7]  Ryutarou Ohbuchi,et al.  Shape similarity comparison of 3D models using alpha shapes , 2003, 11th Pacific Conference onComputer Graphics and Applications, 2003. Proceedings..

[8]  Remco C. Veltkamp,et al.  SHREC2006: 3D Shape Retrieval Contest , 2006 .

[9]  Ryutarou Ohbuchi,et al.  Unsupervised learning from a corpus for shape-based 3D model retrieval , 2006, MIR '06.

[10]  Thomas A. Funkhouser,et al.  The Princeton Shape Benchmark , 2004, Proceedings Shape Modeling Applications, 2004..

[11]  Wei-Ying Ma,et al.  Learning an image manifold for retrieval , 2004, MULTIMEDIA '04.

[12]  S T Roweis,et al.  Nonlinear dimensionality reduction by locally linear embedding. , 2000, Science.

[13]  Mikhail Belkin,et al.  Laplacian Eigenmaps for Dimensionality Reduction and Data Representation , 2003, Neural Computation.