A Comparison of Human and Automated Face Verification Accuracy on Unconstrained Image Sets

Austin Blanton, Kristen C. Allen, Timothy Miller, Nathan D. Kalka, Anil K. Jain; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2016, pp. 161-168

Abstract


Automatic face recognition technologies have seen significant improvements in performance due to a combination of advances in deep learning and availability of larger data sets for training deep networks. Since recognizing faces is a task that humans are believed to be very good at, it is only natural to compare the relative performance of automated face recognition and humans when processing fully unconstrained facial imagery. In this work, we expand on previous studies of the recognition accuracy of humans and automated systems by performing several novel analyses utilizing unconstrained face imagery. We examine the impact on performance when human recognizers are presented with varying amounts of imagery per subject, immutable attributes such as gender, and circumstantial attributes such as occlusion, illumination, and pose. Results indicate that humans greatly outperform state of the art automated face recognition algorithms on the challenging IJB-A dataset.

Related Material


[pdf]
[bibtex]
@InProceedings{Blanton_2016_CVPR_Workshops,
author = {Blanton, Austin and Allen, Kristen C. and Miller, Timothy and Kalka, Nathan D. and Jain, Anil K.},
title = {A Comparison of Human and Automated Face Verification Accuracy on Unconstrained Image Sets},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2016}
}