Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/33684
Title: Preferred Spatial Frequencies for Human Face Processing Are Associated with Optimal Class Discrimination in the Machine
Author: Keil, Matthias S.
Lapedriza i Garcia, Àgata
Masip, David
Vitrià i Marca, Jordi
Keywords: Processament d'imatges
Visió per ordinador
Processament digital d'imatges
Image processing
Computer vision
Digital image processing
Issue Date: 2008
Publisher: Public Library of Science (PLoS)
Abstract: Psychophysical studies suggest that humans preferentially use a narrow band of low spatial frequencies for face recognition. Here we asked whether artificial face recognition systems have an improved recognition performance at the same spatial frequencies as humans. To this end, we estimated recognition performance over a large database of face images by computing three discriminability measures: Fisher Linear Discriminant Analysis, Non-Parametric Discriminant Analysis, and Mutual Information. In order to address frequency dependence, discriminabilities were measured as a function of (filtered) image size. All three measures revealed a maximum at the same image sizes, where the spatial frequency content corresponds to the 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, and that the use of these frequencies is associated with optimal face recognition performance.
Note: Reproducció del document publicat a: http://dx.doi.org/10.1371/journal.pone.0002590
It is part of: PLoS One, 2008, vol. 3, num. 7
Related resource: http://dx.doi.org/10.1371/journal.pone.0002590
URI: http://hdl.handle.net/2445/33684
ISSN: 1932-6203
Appears in Collections:Articles publicats en revistes (Matemàtiques i Informàtica)

Files in This Item:
File Description SizeFormat 
568082.pdf278.79 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons