U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Search Publications by: P. Jonathon Phillips (Fed)

Search Title, Abstract, Conference, Citation, Keyword or Author
Displaying 1 - 25 of 129

Who Is That? Perceptual Expertise on Other-Race Face Comparisons, Disguised Face Comparisons, and Face Memory

April 20, 2023
Author(s)
Amy Yates, Jacqueline Cavazos, Geraldine Jeckeln, Ying Hu, Eilidh Noyes, Carina Hahn, Alice O'Toole, P. Jonathon Phillips
Forensic facial specialists identify faces more accurately than untrained participants on tests using high quality images of faces. Whether this superiority holds in more challenging conditions is not known. Here, we measured performance for forensic

NIST Explainable AI Workshop Summary

August 25, 2022
Author(s)
P. Jonathon Phillips, Carina Hahn, Peter Fontana, Amy Yates, Matthew Smith
This report represents a summary of the National Institute of Standards and Technology (NIST) Explainable Artificial Intelligence (AI) Workshop, which NIST held virtually on January 26-28, 2021.

Forensic facial examiners vs. super-recognizers: Evaluating behavior beyond accuracy

August 24, 2021
Author(s)
Carina Hahn, Liansheng Larry Tang, Amy Yates, P. Jonathon Phillips
We evaluated the detailed, behavioral properties of face matching performance in two specialist groups: forensic facial examiners and super-recognizers. Both groups compare faces to determine identity with high accuracy and outperform the general

Four Principles of Explainable Artificial Intelligence (Draft)

August 18, 2020
Author(s)
P J. Phillips, Amanda C. Hahn, Peter C. Fontana, David A. Broniatowski, Mark A. Przybocki
We introduce four principles for explainable artificial intelligence (AI) that comprise the fundamental properties for explainable AI systems. They were developed to encompass the multidisciplinary nature of explainable AI, including the fields of computer

Dictionary-based Face and Person Recognition from Unconstrained Video

September 9, 2015
Author(s)
P J. Phillips, Yi-Chen Chen, Vishal M. Patel, Rama Chellappa
The main challenge in recognizing people in uncon- strained video is exploiting the identity information in multiple frames and the accompanying dynamic signature. These identity cues include face, body, and motion. Our approach is based on video

Perceptual expertise in forensic facial image comparison

September 1, 2015
Author(s)
P. Jonathon Phillips, David White, Alice O'Toole, Carina A. Hahn, Matthew Hill
Forensic facial identification examiners are required to match the identity of faces in images that vary substantially, owing to changes in viewing conditions and in a person's appearance. These identifications affect the course and out- come of criminal

Evaluating automatic face recognition systems with human benchmarks

April 9, 2015
Author(s)
P. Jonathon Phillips, Alice O'Toole
Human face recognition skills are often considered the gold standard against which machines must compete. Over the last two decades, however, international tests of computer-based face recognition algorithms have shown steady improvements in accuracy with