Pooling Faces: Template based Face Recognition with Pooled Face Images

Autor:	Hassner, Tal, Masi, Iacopo, Kim, Jungyeon, Choi, Jongmoo, Harel, Shai, Natarajan, Prem, Medioni, Gerard
Rok vydání:	2016
Předmět:	Computer Science - Computer Vision and Pattern Recognition
Druh dokumentu:	Working Paper
Popis:	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. Comment: Appeared in the IEEE Computer Society Workshop on Biometrics, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), June, 2016
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1607.01450 Zobrazit plný text záznamu View this record from Arxiv