A Low-dimensional Illumination Space Representation of Human Faces for Arbitrary Lighting Conditions

Author

Hu, Yuankui ; Wang, Zengfu

Author_Institution

Univ. of Sci. & Technol., Hefei

Volume

3

fYear

0

fDate

0-0 0

Firstpage

1147

Lastpage

1150

Abstract

In this paper, a method for low-dimensional illumination space representation (LDISR) of human faces is proposed. The method can not only synthesize a virtual face image when given lighting condition but also estimate lighting conditions when given a face image. The LDISR is based on the observation that 9 basis point light resources can represent almost arbitrary lighting conditions for face recognition application and different human faces have the similar LDISR. The advantage of LDISR is that it can be trained on images of one human face and can be used for all human faces. The experiments on image reconstruction indicated the efficiency of LDISR

Keywords

face recognition; image reconstruction; image representation; arbitrary lighting conditions; face recognition; human face representation; image reconstruction; low-dimensional illumination space representation; virtual face image synthesis; Face recognition; Humans; Image reconstruction; Light sources; Lighting; Pattern recognition; Principal component analysis; Shape; Space technology;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.92

Filename

1699729