Abstract | ||
---|---|---|
We present a 3D matching framework based on a many-to-many matching algorithm that works with skeletal representations of 3D volumetric objects. We demonstrate the performance of this approach on a large database of3D objects containing more than 1000 exemplars. The method is especially suited to matching objects with distinct part structure and is invariant to part articulation. Skeletal matching has an intuitive quality that helps in defining the search and visualizing the results. In particular, the matching algorithm produces a direct correspondence between two skeletons and their parts, which can be used for registration and juxtaposition. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1109/SMI.2005.1 | SMI |
Keywords | Field | DocType |
skeletal matching,direct correspondence,object retrieval,skeletal representation,distinct part structure,intuitive quality,curve skeletons,of3d object,many-to-many matching,large database,matching algorithm,part articulation,many-to-many matching algorithm,object recognition,robustness,scientific visualization,skeleton,computer vision,image registration,topology,curve fitting,computer graphics,data visualisation,visualization | Computer vision,Optimal matching,Visualization,Computer science,Artificial intelligence,Invariant (mathematics),3-dimensional matching,Computer graphics,Image registration,Blossom algorithm,Cognitive neuroscience of visual object recognition | Conference |
ISBN | Citations | PageRank |
0-7695-2379-X | 52 | 1.55 |
References | Authors | |
17 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Nicu D. Cornea | 1 | 426 | 15.45 |
M. Fatih Demirci | 2 | 333 | 21.73 |
Deborah Silver | 3 | 566 | 23.48 |
A. Shokoufandeh | 4 | 1356 | 88.63 |
Sven J. Dickinson | 5 | 2836 | 185.12 |
Paul B. Kantor | 6 | 716 | 115.67 |