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.

Open PDF

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

Tags

Communities of Interest

  • Air Platforms
  • Autonomy

DTIC Thesaurus Topics

  • Artificial Intelligence Software
  • Computer Vision
  • Convolutional Neural Networks
  • Data Science
  • Databases
  • Dimensionality Reduction
  • Feature Extraction
  • Identification
  • Image Recognition
  • Information Processing
  • Information Science
  • Intelligence Community (United States)
  • Machine Learning
  • Neural Networks
  • Order Statistics
  • Recognition
  • Statistics
  • Supervised Machine Learning

Fields of Study

  • Computer science

Readers

  • Computer Vision.

Technology Areas

  • AI & ML
  • AI & ML - Neural Networks
  • Space
  • Space - Space Objects