A generic face appearance model of shape and texture under very large pose variations from profile to profile views

Author

Romdhani, Sami ; Gong, Shaogang ; Psarrou, Alexandra

Author_Institution

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

Volume

1

fYear

2000

fDate

2000

Firstpage

1060

Abstract

Modelling the appearance of 3D objects under very large pose variations relies on recovering correspondence between local features and the texture variations across views. However, changes in object 3D pose introduce self-occlusions and cause nonlinear variations in both the shape and the texture of object appearance. In this paper we introduce a pose-invariant appearance model that utilises a generic-view shape template for alignment, Kernel PCA for modelling shape and texture nonlinearities across views of large pose variations, and a neural network for model fitting to new images

Keywords

computer vision; face recognition; feature extraction; image reconstruction; image texture; neural nets; principal component analysis; stereo image processing; 3D object reconstruction; face appearance model; feature extraction; image texture; model fitting; neural network; pose variations; pose-invariant appearance model; principal component analysis; shape change; view alignment; Active appearance model; Active shape model; Computer science; Educational institutions; Image motion analysis; Iterative algorithms; Kernel; Nonlinear optics; Optical computing; Principal component analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2000. Proceedings. 15th International Conference on

Conference_Location

Barcelona

ISSN

1051-4651

Print_ISBN

0-7695-0750-6

Type

conf

DOI

10.1109/ICPR.2000.905654

Filename

905654