CSEye: A Proposed Solution for Accurate and Accessible One-to-Many Face Verification

Authors

  • Ameer Dharamshi University of Waterloo
  • Rosie Yuyan Zou University of Waterloo

DOI:

https://doi.org/10.1609/aaai.v33i01.33019933

Abstract

Facial verification is a core problem studied by researchers in computer vision. Recently published one-to-one comparison models have successfully achieved accuracy results that surpass the abilities of humans. A natural extension to the one-to-one facial verification problem is a one-to-many classification. In this abstract, we present our exploration of different methods of performing one-to-many facial verification using low-resolution images. The CSEye model introduces a direct comparison between the features extracted from each of the candidate images and the suspect before performing the classification task. Initial experiments using 10-to-1 comparisons of faces from the Labelled Faces of the Wild dataset yield promising results.

Downloads

Published

2019-07-17

How to Cite

Dharamshi, A., & Zou, R. Y. (2019). CSEye: A Proposed Solution for Accurate and Accessible One-to-Many Face Verification. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 9933-9934. https://doi.org/10.1609/aaai.v33i01.33019933

Issue

Section

Student Abstract Track