In this paper, we propose a pose robust multi-view face recognition system using plane of pose tolerance (PPT). The proposed system defines the PPT which represents the tendency of pose variation well presented in multiple images. Compared with the traditional multi-view face recognition system, the proposed system is more robust and accurate especially to the error caused by pose estimation since it uses the property of multiple images. We obtain 91% face recognition rate for the proposed system and accomplished 15% improvement when compared with the traditional one.
Published in:
Acoustics, Speech and Signal Processing, 2007. ICASSP 2007. IEEE International Conference on
(Volume:1
)
Date of Conference: 15-20 April 2007