Identity masking effectiveness and gesture recognition: Effects of eye enhancement in seeing through the mask

TL;DR

This study evaluates simple Canny filter-based face masking algorithms with eye enhancement for privacy protection, finding they effectively hinder identification while preserving facial action perception in low-quality videos.

Contribution

It demonstrates that basic filter-based masks with eye enhancement can protect privacy without affecting the perception of facial actions.

Findings

Masking impairs identification accuracy.

Eye enhancement does not reduce mask effectiveness.

Facial action perception remains intact.

Abstract

Face identity masking algorithms developed in recent years aim to protect the privacy of people in video recordings. These algorithms are designed to interfere with identification, while preserving information about facial actions. An important challenge is to preserve subtle actions in the eye region, while obscuring the salient identity cues from the eyes. We evaluated the effectiveness of identity-masking algorithms based on Canny filters, applied with and without eye enhancement, for interfering with identification and preserving facial actions. In Experiments 1 and 2, we tested human participants' ability to match the facial identity of a driver in a low resolution video to a high resolution facial image. Results showed that both masking methods impaired identification, and that eye enhancement did not alter the effectiveness of the Canny filter mask. In Experiment 3, we tested action preservation and found that neither method interfered significantly with driver action perception. We conclude that relatively simple, filter-based masking algorithms, which are suitable for application to low quality video, can be used in privacy protection without compromising action perception.