Human Recognition of Familiar and Unfamiliar People in Naturalistic Video

Authors:
D. A. Roark;A. J. O'Toole;H. Abdi
Affiliations:
-;-;-
Venue:
AMFG '03 Proceedings of the IEEE International Workshop on Analysis and Modeling of Faces and Gestures
Year:
2003

Citing 2
Cited 5

The FERET Evaluation Methodology for Face-Recognition Algorithms

IEEE Transactions on Pattern Analysis and Machine Intelligence
Introduction to the Special Section on Video Surveillance

IEEE Transactions on Pattern Analysis and Machine Intelligence

Identity Management in Face Recognition Systems

Biometrics and Identity Management
Can local avatars satisfy a global audience? A case study of high-fidelity 3D facial avatar animation in subject identification and emotion perception by US and international groups

Computers in Entertainment (CIE) - SPECIAL ISSUE: Media Arts and Games (Part II)
VideoTicket: detecting identity fraud attempts via audiovisual certificates and signatures

NSPW '07 Proceedings of the 2007 Workshop on New Security Paradigms
Hand-drawn face sketch recognition by humans and a PCA-based algorithm for forensic applications

IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans - Special issue on recent advances in biometrics
Application of an incremental SVM algorithm for on-line human recognition from video surveillance using texture and color features

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Understanding the human performance factors that mediatesuccessful person identification can be helpful in the developmentof automatic face recognition algorithms. Facefamiliarity and facial motion are two factors that seem especiallyuseful when subjects make recognition decisionsfrom challenging viewing formats. We tested the effects ofthese two factors on person recognition from naturalistic,surveillance-like video. Subjects learned faces from eitherstatic photographs or facial speech videos and were askedto recognize people from whole body gait videos. We foundthat the more experience participants had with a face duringlearning (i.e., 1-view, 2-view, and 4-view conditions),the better their recognition performance for people in thewhole body video gait clips. Thus, familiarizing subjectswith high-resolution images or videos of faces was sufficientto improve recognition from low-resolution, whole-body images.Moreover, participants who learned faces from dynamicvideo clips were more accurate than participants wholearned the faces from static images, but only when theywere familiar with the faces. Facial motion and face familiaritymay therefore play a role in understanding recognitionwhen there are photometric inconsistencies betweenlearning and test stimuli.