Research accepted for publication!

Ok, ok…with minor revisions, but still: ACCEPTED.

I am super proud to be able to work with the fantastic minds at the University of Texas at Dallas Face Perception Research Lab and Oakridge National Laboratory. We are currently knee-deep in ongoing research about maintaining privacy in videos that contain faces.

In the upcoming paper, we examine how well humans and a neural network recognize faces covered by different virtual “masks”. The end game is to find the best technique for tracking and covering only the face(s) in a video without losing information about what the face is doing - information that can be very valuable in a number of contexts (e.g., research, body cam review, etc…). Stay tuned for the publication announcement!

Title:
Evaluating Automated Face Identity Masking Methods with Human Perception and a Deep Convolutional Neural Network

To be published in:
The Association for Computing Machinery’s Transactions on Applied Perception.

Related pre-print:
The article is based on a previous, open-access piece that has since been revised, restructured, peer-reviewed, and revised again for publication.