%0 Conference Proceedings
%T Pose-Invariant Face Recognition in Videos for Human-Machine Interaction
%A Bogdan Raducanu
%A Fadi Dornaika
%B 12th European Conference on Computer Vision
%D 2012
%V 7584
%I Springer Berlin Heidelberg
%@ 0302-9743
%@ 978-3-642-33867-0
%F Bogdan Raducanu2012
%O OR;MV
%O exported from refbase (http://refbase.cvc.uab.es/show.php?record=2182), last updated on Tue, 18 Oct 2016 12:03:25 +0200
%X Human-machine interaction is a hot topic nowadays in the communities of computer vision and robotics. In this context, face recognition algorithms (used as primary cue for a person’s identity assessment) work well under controlled conditions but degrade significantly when tested in real-world environments. This is mostly due to the difficulty of simultaneously handling variations in illumination, pose, and occlusions. In this paper, we propose a novel approach for robust pose-invariant face recognition for human-robot interaction based on the real-time fitting of a 3D deformable model to input images taken from video sequences. More concrete, our approach generates a rectified face image irrespective with the actual head-pose orientation. Experimental results performed on Honda video database, using several manifold learning techniques, show a distinct advantage of the proposed method over the standard 2D appearance-based snapshot approach.
%U http://refbase.cvc.uab.es/files/RaD2012e.pdf
%U http://dx.doi.org/10.1007/978-3-642-33868-7_56
%P 566.575