TY - GEN
T1 - Pose-robust face signature for multi-view face recognition
AU - Dou, Pengfei
AU - Zhang, Lingfeng
AU - Wu, Yuhang
AU - Shah, Shishir K.
AU - Kakadiaris, Ioannis A.
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/12/16
Y1 - 2015/12/16
N2 - Despite the great progress achieved in unconstrained face recognition, pose variations still remain a challenging and unsolved practical issue. We propose a novel framework for multi-view face recognition based on extracting and matching pose-robust face signatures from 2D images. Specifically, we propose an efficient method for monocular 3D face reconstruction, which is used to lift the 2D facial appearance to a canonical texture space and estimate the self-occlusion. On the lifted facial texture we then extract various local features, which are further enhanced by the occlusion encodings computed on the self-occlusion mask, resulting in a pose-robust face signature, a novel feature representation of the original 2D facial image. Extensive experiments on two public datasets demonstrate that our method not only simplifies the matching of multi-view 2D facial images by circumventing the requirement for pose-adaptive classifiers, but also achieves superior performance.
AB - Despite the great progress achieved in unconstrained face recognition, pose variations still remain a challenging and unsolved practical issue. We propose a novel framework for multi-view face recognition based on extracting and matching pose-robust face signatures from 2D images. Specifically, we propose an efficient method for monocular 3D face reconstruction, which is used to lift the 2D facial appearance to a canonical texture space and estimate the self-occlusion. On the lifted facial texture we then extract various local features, which are further enhanced by the occlusion encodings computed on the self-occlusion mask, resulting in a pose-robust face signature, a novel feature representation of the original 2D facial image. Extensive experiments on two public datasets demonstrate that our method not only simplifies the matching of multi-view 2D facial images by circumventing the requirement for pose-adaptive classifiers, but also achieves superior performance.
UR - http://www.scopus.com/inward/record.url?scp=84962900920&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84962900920&partnerID=8YFLogxK
U2 - 10.1109/BTAS.2015.7358788
DO - 10.1109/BTAS.2015.7358788
M3 - Conference contribution
AN - SCOPUS:84962900920
T3 - 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015
BT - 2015 IEEE 7th International Conference on Biometrics Theory, Applications and Systems, BTAS 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th IEEE International Conference on Biometrics Theory, Applications and Systems, BTAS 2015
Y2 - 8 September 2015 through 11 September 2015
ER -