Pooling Faces: Template based Face Recognition with Pooled Face Images
Abstract
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 templates 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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jun 26, 2016
- Accession Number
- AD1155351
Entities
People
- Gerard Medioni
- Iacopo Masi
- Jongmoo Choi
- Jungyeon Kim
- Prem Natarajan
- Shai Harel
- Tal Hassner
Organizations
- Open University of Israel
- University of Southern California