Robust representations for face recognition: The power of averages

A. Mike Burton*, Rob Jenkins, Peter J.B. Hancock, David White

*Corresponding author for this work

Research output: Contribution to journalArticleResearchpeer-review

217 Citations (Scopus)

Abstract

We are able to recognise familiar faces easily across large variations in image quality, though our ability to match unfamiliar faces is strikingly poor. Here we ask how the representation of a face changes as we become familiar with it. We use a simple image-averaging technique to derive abstract representations of known faces. Using Principal Components Analysis, we show that computational systems based on these averages consistently outperform systems based on collections of instances. Furthermore, the quality of the average improves as more images are used to derive it. These simulations are carried out with famous faces, over which we had no control of superficial image characteristics. We then present data from three experiments demonstrating that image averaging can also improve recognition by human observers. Finally, we describe how PCA on image averages appears to preserve identity-specific face information, while eliminating non-diagnostic pictorial information. We therefore suggest that this is a good candidate for a robust face representation.

Original languageEnglish
Pages (from-to)256-284
Number of pages29
JournalCognitive Psychology
Volume51
Issue number3
DOIs
Publication statusPublished - Nov 2005
Externally publishedYes

Fingerprint

Dive into the research topics of 'Robust representations for face recognition: The power of averages'. Together they form a unique fingerprint.

Cite this