A similarity-based method for the generalization of face recognition over pose and expression

Sharon Duvdevani-Bar, Shimon Edelman, A. Jonathan Howell, Hilary Buxton

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

19 Scopus citations

Abstract

Human observers are capable of recognizing a face seen only once before when confronted with it subsequently under different viewing conditions. We constructed a working computational model of such generalization from a single view, and tested it on a homogeneous database of face images obtained under tightly controlled viewing conditions. The model effectively constructs a view space for novel faces by interpolating view spaces of familiar ones. Its performance /spl sim/30% error rate in one out of 18 recognition, and 8% in one out of three discrimination-is encouraging, given that it reflects generalization from a single view/expression to a range of /spl plusmn/34/spl deg/ rotation in depth and to two additional expressions. For comparison, human subjects in the one out of three task involving only viewpoint changes exhibit a 3% error rate.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
PublisherIEEE Computer Society
Pages118-123
Number of pages6
ISBN (Print)0818683449, 9780818683442
DOIs
StatePublished - 1998
Externally publishedYes
Event3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 - Nara, Japan
Duration: 14 Apr 199816 Apr 1998

Publication series

NameProceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998

Conference

Conference3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
Country/TerritoryJapan
CityNara
Period14/04/9816/04/98

Fingerprint

Dive into the research topics of 'A similarity-based method for the generalization of face recognition over pose and expression'. Together they form a unique fingerprint.

Cite this