Communications of the ACM
DHS' Biometric Rally Reveals Strong Capabilities Reliant on Camera Configuration
A key component of the 2022 challenge was to train these biometric systems to accurately select an individual face from groups of people, to mimic crowded public transportation stations.
Credit: metamorworks/Getty Images
The U.S. Department of Homeland Security's Science and Technology Directorate (DHS S&T) has released the results of its 2022 Biometric Technology Rally to assess the accuracy of facial recognition algorithms and technologies.
The goal of the rally, which involved 16 biometric systems, was to mitigate errors in facial recognition technologies.
DHS S&T's Arun Vemury said, "What we focus on is putting out a use case to industry describing an overall set of problems."
The researchers sought technology that could select an individual face in a large group of people while protecting the privacy of bystanders, and they identified more issues with accuracy readings for skin tone than other biometric data.
Said Vemury, "You get a better understanding of where the app errors happen in the overall system. And we have seen industry respond and provide better and better camera systems."
From Nextgov
View Full Article
Abstracts Copyright © 2023 SmithBucklin, Washington, DC, USA
No entries found