Learning a single active face shape model across views

Author

Romdhani, Sami ; Psarrou, Alexandra ; Gong, Shaogang

Author_Institution

Sch. of Comput. Sci., Westminster Univ., Harrow, UK

fYear

1999

fDate

1999

Firstpage

31

Lastpage

38

Abstract

An algorithm is described for modelling and recovering the shape of a face varying from the left to the right profile views. The method is based on a multi-view nonlinear model that utilises 2D view-dependent context without explicit reference to 3D structures. The model can cope with large nonlinear shape variations and inconsistent facial feature landmarks between wide varying views. For nonlinear model transformation, we adopt Kernel PCA based on the concept of support vector machines

Keywords

computer vision; face recognition; learning (artificial intelligence); principal component analysis; 2D view-dependent context; Kernel PCA; active face shape model; face shape recovery; facial feature landmarks; learning; multi-view nonlinear model; nonlinear model transformation; profile views; support vector machines; Active shape model; Computer science; Computer vision; Context modeling; Educational institutions; Humans; Image reconstruction; Kernel; Principal component analysis; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems, 1999. Proceedings. International Workshop on

Conference_Location

Corfu

Print_ISBN

0-7695-0378-0

Type

conf

DOI

10.1109/RATFG.1999.799220

Filename

799220