Preferred Spatial Frequencies for Human Face Processing Are Associated with Optimal Class Discrimination in the Machine

Autor: David Masip, Matthias S. Keil, Jordi Vitrià, Agata Lapedriza
Přispěvatelé: Universitat de Barcelona, Universitat Oberta de Catalunya (UOC)
Rok vydání: 2008
Předmět:
Male
Computer science
lcsh:Medicine
Computational Biology/Computational Neuroscience
Artificial face recognition systems
Processament digital d'imatges
Computer Science/Numerical Analysis and Theoretical Computing
Computer Science/Applications
Facial recognition system
Pattern Recognition
Automated
Human face recognition (Computer science)
Image processing
Image Interpretation
Computer-Assisted
Humans
Reconeixement de formes (Informàtica)
lcsh:Science
Image resolution
Reconeixement facial (Informàtica)
Multidisciplinary
business.industry
lcsh:R
Visió per ordinador
Pattern recognition
Pattern recognition systems
Processament d'imatges
Mutual information
Class discrimination
Linear discriminant analysis
Computer Science/Information Technology
Pattern Recognition
Visual
Reconocimiento de formas (Informática)
Face (geometry)
Face
Pattern recognition (psychology)
Visual Perception
Psychophysical studies
lcsh:Q
Female
Reconocimiento facial (Informática)
Computer vision
Spatial frequency
Artificial intelligence
business
Digital image processing
Research Article
Zdroj: Dipòsit Digital de la UB
Universidad de Barcelona
O2, repositorio institucional de la UOC
Universitat Oberta de Catalunya (UOC)
Recercat. Dipósit de la Recerca de Catalunya
instname
PLoS ONE
PLoS ONE, Vol 3, Iss 7, p e2590 (2008)
Popis: 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.
Databáze: OpenAIRE
Externí odkaz: