Inelastic deformation invariant modal representation for non-rigid 3D object recognition

Authors:
Dirk Smeets;Thomas Fabry;Jeroen Hermans;Dirk Vandermeulen;Paul Suetens
Affiliations:
K.U. Leuven, Faculty of Engineering, ESAT, PSI, Medical Imaging Research Center, UZ Gasthuisberg, Leuven, Belgium;K.U. Leuven, Faculty of Engineering, ESAT, PSI, Medical Imaging Research Center, UZ Gasthuisberg, Leuven, Belgium;K.U. Leuven, Faculty of Engineering, ESAT, PSI, Medical Imaging Research Center, UZ Gasthuisberg, Leuven, Belgium;K.U. Leuven, Faculty of Engineering, ESAT, PSI, Medical Imaging Research Center, UZ Gasthuisberg, Leuven, Belgium;K.U. Leuven, Faculty of Engineering, ESAT, PSI, Medical Imaging Research Center, UZ Gasthuisberg, Leuven, Belgium
Venue:
AMDO'10 Proceedings of the 6th international conference on Articulated motion and deformable objects
Year:
2010

Citing 9
Cited 0

A Multilinear Singular Value Decomposition

SIAM Journal on Matrix Analysis and Applications
Three-Dimensional Face Recognition

International Journal of Computer Vision
Laplace-Beltrami Eigenfunctions Towards an Algorithm That "Understands" Geometry

SMI '06 Proceedings of the IEEE International Conference on Shape Modeling and Applications 2006
Retrieving articulated 3-D models using medial surfaces

Machine Vision and Applications
Numerical Geometry of Non-Rigid Shapes

Numerical Geometry of Non-Rigid Shapes
Isometric Deformation Modelling for Object Recognition

CAIP '09 Proceedings of the 13th International Conference on Computer Analysis of Images and Patterns
A Gromov-Hausdorff Framework with Diffusion Geometry for Topologically-Robust Non-rigid Shape Matching

International Journal of Computer Vision
Robust expression-invariant face recognition from partially missing data

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III
On bending invariant signatures for surfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Intra-shape deformations complicate 3D object recognition and retrieval and need therefore proper modeling. A method for inelastic deformation invariant object recognition is proposed, representing 3D objects by diffusion distance tensors (DDT), i.e. third order tensors containing the average diffusion distance for different diffusion times between each pair of points on the surface. In addition to the DDT, also geodesic distance matrices (GDM) are used to represent the objects independent of the reference frame. Transforming these distance tensors into modal representations provides a sampling order invariant shape descriptor. Different dissimilarity measures can be used for comparing these shape descriptors. The final object pair dissimilarity is the sum or product of the dissimilarities obtained by modal representations of the GDM and DDT. The method is validated on the TOSCA non-rigid world database and the SHREC 2010 dataset of non-rigid 3D models indicating that our method combining these two representations provides a more noise robust but still inter-subject shape variation sensitive method for the identification and the verification scenario in object retrieval.