TY - GEN
T1 - Pooling Faces
T2 - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
AU - Hassner, Tal
AU - Masi, Iacopo
AU - Kim, Jungyeon
AU - Choi, Jongmoo
AU - Harel, Shai
AU - Natarajan, Prem
AU - Medioni, Gerard
N1 - Publisher Copyright:
© 2016 IEEE.
Copyright:
Copyright 2017 Elsevier B.V., All rights reserved.
PY - 2016/12/16
Y1 - 2016/12/16
N2 - We propose a novel approach to template based face recognition. Our dual goal is to both increase recognition accuracy and reduce the computational and storage costs of template matching. To do this, we leverage on an approach which was proven effective in many other domains, but, to our knowledge, never fully explored for face images: average pooling of face photos. We show how (and why!) the space of a template's images can be partitioned and then pooled based on image quality and head pose and the effect this has on accuracy and template size. We perform extensive tests on the IJB-A and Janus CS2 template based face identification and verification benchmarks. These show that not only does our approach outperform published state of the art despite requiring far fewer cross template comparisons, but also, surprisingly, that image pooling performs on par with deep feature pooling.
AB - We propose a novel approach to template based face recognition. Our dual goal is to both increase recognition accuracy and reduce the computational and storage costs of template matching. To do this, we leverage on an approach which was proven effective in many other domains, but, to our knowledge, never fully explored for face images: average pooling of face photos. We show how (and why!) the space of a template's images can be partitioned and then pooled based on image quality and head pose and the effect this has on accuracy and template size. We perform extensive tests on the IJB-A and Janus CS2 template based face identification and verification benchmarks. These show that not only does our approach outperform published state of the art despite requiring far fewer cross template comparisons, but also, surprisingly, that image pooling performs on par with deep feature pooling.
UR - http://www.scopus.com/inward/record.url?scp=85010189140&partnerID=8YFLogxK
U2 - 10.1109/CVPRW.2016.23
DO - 10.1109/CVPRW.2016.23
M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???
AN - SCOPUS:85010189140
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 127
EP - 135
BT - Proceedings - 29th IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2016
PB - IEEE Computer Society
Y2 - 26 June 2016 through 1 July 2016
ER -