Please use this identifier to cite or link to this item:
Appears in Collections:Psychology Journal Articles
Peer Review Status: Refereed
Title: Robust representations for face recognition: the power of averages
Author(s): Burton, A Mike
Jenkins, Rob
Hancock, Peter J B
White, David
Keywords: Face recognition
Face perception
Visual perception
Recognition (Psychology)
Principal components analysis
Issue Date: Nov-2005
Date Deposited: 31-Mar-2008
Citation: Burton AM, Jenkins R, Hancock PJB & White D (2005) Robust representations for face recognition: the power of averages. Cognitive Psychology, 51 (3), pp. 256-284.;
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.
DOI Link: 10.1016/j.cogpsych.2005.06.003
Rights: Published in Cognitive Psychology by Elsevier.

Files in This Item:
File Description SizeFormat 
BJHW_inline.pdfFulltext - Accepted Version1.69 MBAdobe PDFView/Open

This item is protected by original copyright

Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved

If you believe that any material held in STORRE infringes copyright, please contact providing details and we will remove the Work from public display in STORRE and investigate your claim.