3D model metrieval based on volumetric extended gaussian image and hierarchical self organizing map

In this paper, we introduce a novel shape signature, called Volumetric Extended Gaussian Image (VEGI). It captures the volumetric distribution of a 3D mesh model along the latitude-longitude direction without conventional pose normalization and is translation and scaling invariant. Rotation invariance is accomplished by further calculating the spherical harmonic transform of this directional distribution. Due to the completeness and orthonormality properties of spherical harmonics, the VEGI also provides multi-resolution description of a model so that a multi-level indexing scheme based on Hierarchical Self Organizing Map (HSOM) can be established to improve retrieval efficiency. Experimental results show that our retrieval architecture has high discriminative power and outperforms many existing methods.

[1]  Berthold K. P. Horn.  Extended Gaussian images , 1984, Proceedings of the IEEE.

[2]  G. W. Chantry,et al.  Spherical Harmonics and Tensors for Classical Field Theory , 1986 .

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

[4]  Alain Fournier,et al.  Triangulating Simple Polygons and Equivalent Problems , 1984, TOGS.

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

[6]  José María Carazo,et al.  Smoothly distributed fuzzy c-means: a new self-organizing map , 2001, Pattern Recognit..

[7]  Thomas A. Funkhouser,et al.  Harmonic 3D shape matching , 2002, SIGGRAPH '02.

[8]  Dietmar Saupe,et al.  3D Shape Descriptor Based on 3D Fourier Transform , 2001 .

[9]  Michael Elad,et al.  Directed Search In A 3D Objects Database Using SVM , 2000 .

[10]  Hau-San Wong,et al.  Indexing and retrieval of 3D models by unsupervised clustering with hierarchical SOM , 2004, ICPR 2004.

[11]  Jouko Lampinen,et al.  Clustering properties of hierarchical self-organizing maps , 1992, Journal of Mathematical Imaging and Vision.

[12]  Hans-Peter Kriegel,et al.  Nearest Neighbor Classification in 3D Protein Databases , 1999, ISMB.

[13]  Tsuhan Chen,et al.  Efficient feature extraction for 2D/3D objects in mesh representation , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[14]  Matthew Goldstein,et al.  Kn -nearest Neighbor Classification , 1972, IEEE Trans. Inf. Theory.

[15]  Bernard Chazelle.  Triangulating a simple polygon in linear time , 1991, Discret. Comput. Geom..

[16]  Bernard Chazelle,et al.  Matching 3D models with shape distributions , 2001, Proceedings International Conference on Shape Modeling and Applications.

[17]  Hau-San Wong,et al.  Indexing and retrieval of 3D models by unsupervised clustering with hierarchical SOM , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[18]  Dietmar Saupe,et al.  Tools for 3D-object retrieval: Karhunen-Loeve transform and spherical harmonics , 2001, 2001 IEEE Fourth Workshop on Multimedia Signal Processing (Cat. No.01TH8564).