Face pose estimation and its application in video shot selection

Author

Yang, Zhiguang ; Ai, Haizhou ; Wu, Bo ; Lao, Shihong ; Cai, Lianhong

Author_Institution

Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China

Volume

1

fYear

2004

fDate

23-26 Aug. 2004

Firstpage

322

Abstract

In this paper, a face pose estimation method and its application in video shot selection for face image preprocessing is introduced. The pose estimator is learned by a boosting regression algorithm called SquareLev.R that learns poses from simple Haar-type features. It consists of two tree structured subsystems for the left-right angle and up-down angle respectively. As a specific application in video based face recognition, the best shot selection problem is discussed, which results in a real-time system that can automatically select the most frontal face from a video sequence.

Keywords

estimation theory; face recognition; feature extraction; image sequences; learning (artificial intelligence); real-time systems; regression analysis; trees (mathematics); video signal processing; Haar type features; boosting regression algorithm; face image preprocessing; face pose estimation; face recognition; real time system; training set; tree structured subsystems; video sequence; video shot selection; Application software; Artificial intelligence; Boosting; Computer aided instruction; Computer science; Face detection; Face recognition; Real time systems; Regression tree analysis; Video sequences;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on

ISSN

1051-4651

Print_ISBN

0-7695-2128-2

Type

conf

DOI

10.1109/ICPR.2004.1334117

Filename

1334117