Name
Abstract | ||
|---|---|---|
Nowadays, 3D scanning, 3D modeling and 3D printing technologies are more and more popular, the number and size of 3D model dataset is growing dramatically. Since shape distribution based methods are easy to compute and invariant to geometric transformation, finding more useful features to refine the retrieval accuracy of shape distribution based methods is a meaningful work. In this paper, a novel feature extraction method for retrieving 3D models by using curvature-based shape distribution is proposed. The 3D model's surface is divided into fine region, flat region, and steep region based on its curvature, then the shape distribution between the same and different regions are extracted respectively. Experimental results demonstrate that the searching accuracy could be highly refined by using the curvature-based shape distribution. |
Year | Venue | Keywords |
|---|---|---|
2015 | 2015 12TH INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (FSKD) | 3D model retrieval, mean curvature, shape distribution, feature extraction, similarity matching |
Field | DocType | Citations |
Active shape model,Curvature,Pattern recognition,Computer science,Mean curvature,Geometric transformation,Feature extraction,Artificial intelligence,Invariant (mathematics),3D modeling,Heat kernel signature | Conference | 1 |
PageRank | References | Authors |
0.35 | 10 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kuan-Sheng Zou | 1 | 15 | 2.28 |
| Zhaojun Zhang | 2 | 7 | 1.44 |
| Jianhua Zhang | 3 | 3 | 1.05 |
| Qian Zhang | 4 | 1 | 0.35 |