Name
Abstract | ||
|---|---|---|
Facial fiducial point localization is a crucial step for most facial analysis applications, e.g., face recognition, expression recognition and facial aging simulation. Although state-of-art methods have the ability to provide good salient point location on frontal faces, finding a global solution under large variations caused by off-plane rotations and exaggerated expression changes is still a challenge. In this paper, we present a system with a two-level shape model to facilitate accurate facial fiducial point localization. In the first level, two local component models interact with each other in order to offer novel shape constraints. At the same time, the clamped local shape model provides constrained non-linear shape initialization for better convergence performance of the shape model as a whole. The experimental results confirm that the proposed method is capable of dealing with the face alignment under large shape variations. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/ICIP.2013.6738725 | ICIP |
Keywords | Field | DocType |
face alignment,shape recognition,face recognition,discriminate texture models,global shape model,facial fiducial point localization,expression recognition,active shape models,two-level shape model,salient point location,clamped local shape model,constrained nonlinear shape initialization,facial aging simulation,facial analysis,shape constraint,frontal faces,off-plane rotation | Active shape model,Computer vision,Facial recognition system,Face hallucination,Fiducial marker,Point location,Pattern recognition,Computer science,Topological skeleton,Artificial intelligence,Initialization,Shape analysis (digital geometry) | Conference |
ISSN | Citations | PageRank |
1522-4880 | 3 | 0.38 |
References | Authors | |
8 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hui Fang | 1 | 918 | 63.03 |
| Jingjing Deng | 2 | 16 | 5.83 |
| Xianghua Xie | 3 | 383 | 37.13 |
| Philip W. Grant | 4 | 101 | 6.47 |