Face Recognition in the Machine Reveals Properties of Human Face Recognition

Simple item page
dc.creatorKeil, Matthias S.
dc.creatorLapedriza, Agata
dc.creatorMasip, David
dc.creatorVitria, Jordi
dc.date2006-12-01
dc.date.accessioned2026-07-07T07:35:02Z
dc.date.available2026-07-07T07:35:02Z
dc.descriptionPsychophysical studies suggest that face recognition takes place in a narrow band of low spatial frequencies (``critical band''). Here, we examined the recognition performance of an artificial face recognition system as a function of the size of the input images. Recognition performance was quantified with three discriminability measures: Fisher Linear Discriminant Analysis, non Parametric Discriminant Analysis, and mutual information. All of the three measures revealed a maximum at the same image sizes. Since spatial frequency content is a function of image size, our data consistently predict the range of psychophysical found frequencies. Our results therefore support the notion that the critical band of spatial frequencies for face recognition in humans and machines follows from inherent properties of face images.
dc.description10 pages
dc.identifierhttps://arxiv.org/abs/q-bio/0612001
dc.identifierhttp://arxiv.org/abs/q-bio/0612001
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/119972
dc.subjectNeurons and Cognition
dc.titleFace Recognition in the Machine Reveals Properties of Human Face Recognition
dc.typetext

Files

Collections

arXiv