Publication Type
Conference Proceeding Article
Publication Date
8-2004
Abstract
In this paper, we present a novel method for efficient 3D model comparison. The method matches highly deformed models by comparing topological and geometric features. First, we propose “Bi-directional LSD analysis” to locate reliable topological points and rings. Second, based on these points and rings, a set of bounded regions are extracted as topological features. Third, for each bounded region, we capture additional spatial location, curvature and area distribution as geometric data. Fourth, to model the topological importance of each bounded region, we capture its effective area as weight. By using “Earth Mover Distance” as a distance measure between two models, our method can achieve a high accuracy in our retrieval experiment, with precision of 0.53 even at recall rate of 1.0.
Discipline
Computer Sciences | Graphics and Human Computer Interfaces
Research Areas
Intelligent Systems and Optimization
Publication
Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, UK, 2004 August 23-26
Volume
3
First Page
910
Last Page
913
ISBN
0769521282
Identifier
10.1109/ICPR.2004.1334676
Publisher
IEEE
City or Country
Cambridge
Citation
TAM, Kwok-Leung; LAW, Rynson W.H.; and NGO, Chong-wah.
Deformable geometry model matching by topological and geometric signatures. (2004). Proceedings of the 17th International Conference on Pattern Recognition, ICPR 2004, Cambridge, UK, 2004 August 23-26. 3, 910-913.
Available at: https://ink.library.smu.edu.sg/sis_research/6565
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.