Take a sneak peek at the new NIST.gov and let us know what you think!
(Please note: some content may not be complete on the beta site.).

View the beta site
NIST logo

Publication Citation: Comparing Face Recognition Algorithms to Humans on Challenging Tasks

NIST Authors in Bold

Author(s): P J. Phillips; Alice O'Toole; Xiaobo An; Joseph Dunlop; Vaidehi Natu;
Title: Comparing Face Recognition Algorithms to Humans on Challenging Tasks
Published: October 17, 2012
Abstract: We compared face identifcation by humans and machines using images taken under a variety of uncontrolled illumination conditions in both indoor and outdoor settings. Natural variations in a person's day-to-day appearance (e.g., hair style, facial expression, hats, glasses, etc.) contributed to the difficulty of the task. Both humans and machines matched the identity of people (same or different?) in pairs of frontal view face images. The degree of diculty introduced by photometric and appearance-based variability was estimated using a face recognition algorithm created by fusing three top-performing algorithms from a recent international competition. The algorithm computed similarity scores for a constant set of same-identity and different-identity pairings from multiple images. Image pairs were assigned to good, moderate, and poor accuracy groups by ranking the similarity scores for each identity pairing, and dividing these rankings into three strata. This procedure isolated the role of photometric variables from the effects of the distinctiveness of particular identities. Algorithm performance for these constant identity pairings varied dramatically across the groups. In three experiments, humans matched image pairs from the good, moderate, and poor conditions, rating the likelihood that the images were of the same person (1: sure same - 5: sure different). Algorithms were more accurate than humans in the good and moderate conditions, but were comparable to humans in the poor accuracy condition. To date, these are the most variable illumination- and appearance-based recognition conditions on which humans and machines have been compared. The finding that machines were never less accurate than humans on these challenging frontal images suggests that face recognition systems may be ready for applications with comparable difficulty. We speculate that superiority of machines over humans in the less challenging conditions may be due to the machine use of view-sp
Citation: ACM Transactions on Applied Perception
Keywords: algorithms, human factors, Verification, Experimentation
Research Areas: Biometrics, Information Technology
PDF version: PDF Document Click here to retrieve PDF version of paper (6MB)