Name
Abstract | ||
|---|---|---|
In this paper, an effective gender classification based on 3D face model is proposed based on 3D principal components analysis (3D Eigenmodels) and 3D independent components analysis (3D ICmodels). In our work, the 3D face model is represented by 3D landmarks. The proposed gender classification method consists of three steps: 1) Align the 3D models to get 3D aligned shapes; 2) Perform 3D PCA/ICA transformation on the aligned 3D shapes; 3) Do gender classification on the 3D Eigenmodels/ICmodels features using SVM. The experimental results on BU_3DFE database demonstrate that the proposed method can achieve good performance. |
Year | DOI | Venue |
|---|---|---|
2017 | 10.1007/s11042-016-3446-7 | Multimedia Tools Appl. |
Keywords | Field | DocType |
Procrustes transformation, Point alignment, 3D gender classification | Data mining,Pattern recognition,3d shapes,Computer science,Support vector machine,Statistical model,Independent component analysis,Artificial intelligence,Procrustes transformation,Principal component analysis | Journal |
Volume | Issue | ISSN |
76 | 3 | 1573-7721 |
Citations | PageRank | References |
2 | 0.36 | 27 |
Authors | ||
4 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Wankou Yang | 1 | 199 | 26.33 |
| Changyin Sun | 2 | 2002 | 157.17 |
| Wenming Zheng | 3 | 1240 | 80.70 |
| Karl Ricanek | 4 | 165 | 18.65 |