Face Pose Estimation and its Application in Video Shot Selection

Authors:
Zhiguang Yang;Haizhou Ai;Bo Wu;Shihong Lao;Lianhong Cai
Affiliations:
Tsinghua University, Beijing, China;Tsinghua University, Beijing, China;Tsinghua University, Beijing, China;Sensing Technology Laboratory, Omron Corporation;Tsinghua University, Beijing, China
Venue:
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 1 - Volume 01
Year:
2004

Citing 0
Cited 3

Physiology-Based Face Recognition in the Thermal Infrared Spectrum

IEEE Transactions on Pattern Analysis and Machine Intelligence
Best-Shot Selection for Video Face Recognition Using FPGA

CIARP '08 Proceedings of the 13th Iberoamerican congress on Pattern Recognition: Progress in Pattern Recognition, Image Analysis and Applications
Horizontal human face pose determination using pupils and skin region positions

PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology

Quantified Score

Hi-index	0.00

Visualization

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 [Boosting Methods for Regression] 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.