Presentation 2005-10-28
Projection-based 3D Normalization for Face Recognition
Tatsuo KOZAKAYA, Osamu YAMAGUCHI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a new projection-based 3D normalization method for face recognition under variation in facial pose such as the rotation and the direction. Numerous normalization methods have been proposed, which deform or rotate a 3D model and adapt it to an input image. The proposed method fits an image to a generic 3D model according to the projective relationship between facial feature points on the image and the model. The normalization process can be done rapidly because it does not need personalized 3D models and iterative computation for fitting. Evaluation experiments are performed using several databases and the results show the effectiveness of our method under various facial poses.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face recognition / 3D / Normalization / Projective transformation
Paper # PRMU2005-101
Date of Issue

Conference Information
Committee PRMU
Conference Date 2005/10/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Projection-based 3D Normalization for Face Recognition
Sub Title (in English)
Keyword(1) Face recognition
Keyword(2) 3D
Keyword(3) Normalization
Keyword(4) Projective transformation
1st Author's Name Tatsuo KOZAKAYA
1st Author's Affiliation Corporate R&D Center, Toshiba Corporation()
2nd Author's Name Osamu YAMAGUCHI
2nd Author's Affiliation Corporate R&D Center, Toshiba Corporation
Date 2005-10-28
Paper # PRMU2005-101
Volume (vol) vol.105
Number (no) 375
Page pp.pp.-
#Pages 6
Date of Issue