3D Part identification based on local shape descriptors

This paper explores 3D object recognition based on local shape descriptor. 3D object recognition is becoming an increasingly important task in modern applications such as computer vision, CAD/CAM, multimedia, molecular biology, robotics, and so on. Compared with general objects, CAD models contain more complicated structures and subtle local features. It is especially challenging to recognize the CAD model from the point clouds which only contain partial data of the model. We adopt the Bag of Words framework to do the partial-to-global 3D CAD retrieval. In this paper the visual words dictionary is constructed based on the spin image local feature descriptor. The method is tested on the Purdue Engineering Benchmark. Furthermore, several experiments are performed to show how the size of query data and the dissimilarity measurement affect the retrieval results.

[1]  Satyandra K. Gupta,et al.  Retrieving Matching CAD Models by Using Partial 3D Point Clouds , 2007 .

[2]  Ming Ouhyoung,et al.  On Visual Similarity Based 3D Model Retrieval , 2003, Comput. Graph. Forum.

[3]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Bernard Chazelle,et al.  Shape distributions , 2002, TOGS.

[5]  Ryutarou Ohbuchi,et al.  Salient local visual features for shape-based 3D model retrieval , 2008, 2008 IEEE International Conference on Shape Modeling and Applications.

[6]  Frédéric Jurie,et al.  Randomized Clustering Forests for Image Classification , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Jitendra Malik,et al.  Recognizing Objects in Range Data Using Regional Point Descriptors , 2004, ECCV.

[8]  Karthik Ramani,et al.  Developing an engineering shape benchmark for CAD models , 2006, Comput. Aided Des..

[9]  Martial Hebert,et al.  Efficient multiple model recognition in cluttered 3-D scenes , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

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

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

[12]  Szymon Rusinkiewicz,et al.  Modeling by example , 2004, SIGGRAPH 2004.

[13]  Leonidas J. Guibas,et al.  Probabilistic fingerprints for shapes , 2006, SGP '06.

[14]  Pietro Perona,et al.  A Bayesian hierarchical model for learning natural scene categories , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Yi Liu,et al.  Shape Topics: A Compact Representation and New Algorithms for 3D Partial Shape Retrieval , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).