Abstract | ||
---|---|---|
We propose a 3D Constrained Local Model framework for deformable face alignment in depth image. Our framework exploits the intrinsic 3D geometric information in depth data by utilizing robust histogram-based 3D geometric features that are based on normal vectors. In addition, we demonstrate the fusion of intensity data and 3D features that further improves the facial landmark localization accuracy. The experiments are conducted on publicly available FRGC database. The results show that our 3D features based CLM completely outperforms the raw depth features based CLM in term of fitting accuracy and robustness, and the fusion of intensity and 3D depth feature further improves the performance. Another benefit is that the proposed 3D features in our framework do not require any pre-processing procedure on the data. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/ICIP.2014.7025285 | ICIP |
Keywords | Field | DocType |
3d depth feature,3d constrained local model framework,image fusion,face recognition,deformable face alignment,3d facial geometry,visual databases,histogram-based 3d feature,raw depth features,constrained local model,publicly available frgc database,facial landmark localization accuracy,feature extraction,robust histogram-based 3d geometric features,3d facial geometric features,3d feature-intensity data fusion,depth image,geometry,intrinsic 3d geometric information,3d feature based clm | Histogram,Computer vision,Pattern recognition,Computer science,Fusion,Robustness (computer science),Artificial intelligence,Landmark | Conference |
ISSN | Citations | PageRank |
1522-4880 | 1 | 0.37 |
References | Authors | |
15 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shiyang Cheng | 1 | 478 | 17.26 |
Stefanos Zafeiriou | 2 | 3129 | 150.99 |
Akshay Asthana | 3 | 729 | 25.02 |
Maja Pantic | 4 | 10434 | 487.02 |