Skeleton path based approach for nonrigid 3D shape analysis and retrieval

Authors:
Chunyuan Li;A. Ben Hamza
Affiliations:
Concordia Institute for Information Systems Engineering, Concordia University, Montréal, QC, Canada;Concordia Institute for Information Systems Engineering, Concordia University, Montréal, QC, Canada
Venue:
IWCIA'11 Proceedings of the 14th international conference on Combinatorial image analysis
Year:
2011

Citing 14
Cited 0

Shock Graphs and Shape Matching

International Journal of Computer Vision
Surface Coding Based on Morse Theory

IEEE Computer Graphics and Applications
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Reflective Symmetry Descriptor

ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Skeleton Based Shape Matching and Retrieval

SMI '03 Proceedings of the Shape Modeling International 2003
The Princeton Shape Benchmark

SMI '04 Proceedings of the Shape Modeling International 2004
3D Object Retrieval using Many-to-many Matching of Curve Skeletons

SMI '05 Proceedings of the International Conference on Shape Modeling and Applications 2005
Curve-Skeleton Properties, Applications, and Algorithms

IEEE Transactions on Visualization and Computer Graphics
Skeleton extraction by mesh contraction

ACM SIGGRAPH 2008 papers
Curve-Skeleton Extraction Using Iterative Least Squares Optimization

IEEE Transactions on Visualization and Computer Graphics
Path Similarity Skeleton Graph Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Retrieving articulated 3-D models using medial surfaces

Machine Vision and Applications
3D articulated object retrieval using a graph-based representation

The Visual Computer: International Journal of Computer Graphics - Special Issue on 3D Object Retrieval 2009
SHREC'10 track: non-rigid 3D shape retrieval

EG 3DOR'10 Proceedings of the 3rd Eurographics conference on 3D Object Retrieval

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a skeleton path based approach to analyze and retrieve nonrigid 3D shapes. The main idea is to match skeleton graphs by comparing the geodesic paths between skeleton endpoints. Our approach is motivated by the fact that the path feature is stable in the presence of articulation of components. The experimental results demonstrate the performance of our proposed method in terms of robustness to symmetry, discrimination against different graph structures, and high efficiency in nonrigid shape retrieval.