Robust representations for face recognition: the power of averages



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.;

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.

Face recognition; PCA; Face perception; Visual perception; Recognition (Psychology); Principal components analysis

Cognitive Psychology: Volume 51, Issue 3

Publication date30/11/2005
Publication date online28/09/2005
Publisher URL

People (1)


Professor Peter Hancock

Professor Peter Hancock

Professor, Psychology