Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

15

WACV
2007
IEEE

favoriteEmaildiscussreport

149views Computer Vision» more WACV 2007»

Probabilistic Hierarchical Face Model for Feature Localization

13 years 10 months ago

Probabilistic Hierarchical Face Model for Feature Localization

Download users.soe.ucsc.edu

Facial feature localization is an important research area in both computer vision and pattern analysis. We present in this paper a hierarchical face model. It uniﬁes both the global and local face appearance together with geometric information for precise feature localization. Face detection is used to obtain the face rough position and scale in the image. A coarse global AAM (Active Appearnce Model) is then applied to obtain the initial position of each part. Local detailed part-level AAM models (like the eyes, mouth) are used to reﬁne the localization. This coarseto-ﬁne scheme constraints the search in the correct space which makes the localization more accurate. In the partlevel localization, we consider the geometric relationship of the local parts and the global face model. The whole procedure is formulated into a Maximum-A-Posteriori(MAP) framework. Experiments demonstrate the effectiveness of our approach.

Feng Tang, Jin Wang, Hai Tao, Qunsheng Peng

Real-time Traffic

Face Model | Facial Feature Localization | Feature Localization | WACV 2007 |

claim paper

Related Content

» Face Localization via Hierarchical CONDENSATION with Fisher Boosting Feature Selection

» Hierarchical Shape Modeling for Automatic Face Localization

» Robust facial feature tracking under varying face pose and facial expression

» Learning Probabilistic Distribution Model for MultiView Face Detection

» Robust face alignment based on local texture classifiers

» A Hierarchical Compositional Model for Face Representation and Sketching

» Probabilistic Contour Extraction Using Hierarchical Shape Representation

» Hierarchical Wavelet Networks for Facial Feature Localization

» Hierarchical Ensemble of Global and Local Classifiers for Face Recognition

Post Info
More Details (n/a)

Added	04 Jun 2010
Updated	04 Jun 2010
Type	Conference
Year	2007
Where	WACV
Authors	Feng Tang, Jin Wang, Hai Tao, Qunsheng Peng

Comments (0)