Using irreducible group representations for invariant 3d shape description

Authors:
Marco Reisert;Hans Burkhardt
Affiliations:
Computer Science Department, University of Freiburg, Freiburg i.Br., Germany;Computer Science Department, University of Freiburg, Freiburg i.Br., Germany
Venue:
DAGM'06 Proceedings of the 28th conference on Pattern Recognition
Year:
2006

Citing 5
Cited 3

Rotation invariant spherical harmonic representation of 3D shape descriptors

Proceedings of the 2003 Eurographics/ACM SIGGRAPH symposium on Geometry processing
Matching 3D Models with Shape Distributions

SMI '01 Proceedings of the International Conference on Shape Modeling & Applications
Margin based feature selection - theory and algorithms

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Invariant Features for 3D-Data based on Group Integration using Directional Information and Spherical Harmonic Expansion

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04
Technical section: Second order 3D shape features: An exhaustive study

Computers and Graphics

Invariant features for searching in protein fold databases

International Journal of Computer Mathematics - Bioinformatics
A Bag of Features Approach for 3D Shape Retrieval

ISVC '09 Proceedings of the 5th International Symposium on Advances in Visual Computing: Part I
Holomorphic filters for object detection

Proceedings of the 29th DAGM conference on Pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

Invariant feature representations for 3D objects are one of the basic needs in 3D object retrieval and classification. One tool to obtain rotation invariance are Spherical Harmonics, which are an orthogonal basis for the functions defined on the 2-sphere. We show that the irreducible representations of the 3D rotation group, which acts on the Spherical Harmonic representation, can give more information about the considered object than the Spherical Harmonic expansion itself. We embed our new feature extraction methods in the group integration framework and show experiments for 3D-surface data (Princeton Shape Benchmark).