journal article Mar 30, 2015

Identity From Variation: Representations of Faces Derived From Multiple Instances

Cognitive Science Vol. 40 No. 1 pp. 202-223 · Wiley
View at Publisher Save 10.1111/cogs.12231
Abstract
AbstractResearch in face recognition has tended to focus on discriminating between individuals, or “telling people apart.” It has recently become clear that it is also necessary to understand how images of the same person can vary, or “telling people together.” Learning a new face, and tracking its representation as it changes from unfamiliar to familiar, involves an abstraction of the variability in different images of that person's face. Here, we present an application of principal components analysis computed across different photos of the same person. We demonstrate that people vary in systematic ways, and that this variability is idiosyncratic—the dimensions of variability in one face do not generalize well to another. Learning a new face therefore entails learning how that face varies. We present evidence for this proposal and suggest that it provides an explanation for various effects in face recognition. We conclude by making a number of testable predictions derived from this framework.
Topics

No keywords indexed for this article. Browse by subject →

References
53
[1]
Aishwarya P. "Face recognition using multiple eigenface subspaces" Journal of Engineering and Technology Research (2010)
[5]
Beymer D. (1995)
[10]
Understanding face recognition

Vicki Bruce, Andy Young

British Journal of Psychology 10.1111/j.2044-8295.1986.tb02199.x
[18]
Edelman S. (2001)
[20]
Geng X. (2007)
[21]
Recognition of unfamiliar faces

Peter J.B. Hancock, Vicki Bruce, A.Mike Burton

Trends in Cognitive Sciences 10.1016/s1364-6613(00)01519-9
[30]
Prototype-referenced shape encoding revealed by high-level aftereffects

David A. Leopold, Alice J. O'Toole, Thomas Vetter et al.

Nature Neuroscience 10.1038/82947
[35]
O'Toole A. J. "Comparing face recognition algorithms to humans on challenging tasks" ACM Transactions on Applied Perception (2012) 10.1145/2355598.2355599
[47]
Eigenfaces for Recognition

Matthew Turk, Alex Pentland

Journal of Cognitive Neuroscience 10.1162/jocn.1991.3.1.71
[48]
A Unified Account of the Effects of Distinctiveness, Inversion, and Race in Face Recognition

Tim Valentine

The Quarterly Journal of Experimental Psychology S... 10.1080/14640749108400966

Showing 50 of 53 references

Cited By
192
The neural dynamics of familiar face recognition

Holger Wiese, Stefan R. Schweinberger · 2024

Neuroscience & Biobehavioral Re...
A Robust Neural Index of High Face Familiarity

Holger Wiese, Simone C. Tüttenberg · 2018

Psychological Science
Understanding face familiarity

Robin S.S. Kramer, Andrew W. Young · 2018

Cognition
Recognizing Faces

Andrew W. Young, A. Mike Burton · 2017

Current Directions in Psychological...
Quarterly Journal of Experimental P...
Metrics
192
Citations
53
References
Details
Published
Mar 30, 2015
Vol/Issue
40(1)
Pages
202-223
License
View
Funding
European Research Council Award: 323262
Economic and Social Research Council Award: ES/J022950/1
Cite This Article
A. Mike Burton, Robin S. S. Kramer, Kay L. Ritchie, et al. (2015). Identity From Variation: Representations of Faces Derived From Multiple Instances. Cognitive Science, 40(1), 202-223. https://doi.org/10.1111/cogs.12231
Related

You May Also Like

Finding Structure in Time

Jeffrey L. Elman · 1990

7,851 citations

Why a Diagram is (Sometimes) Worth Ten Thousand Words

Jill H. Larkin, HERBERT A. SIMON · 1987

2,229 citations

A Learning Algorithm for Boltzmann Machines*

David H. Ackley, Geoffrey E. Hinton · 1985

2,067 citations