Face Recognition in the Machine Reveals Properties of Human Face Recognition

Abstract

Psychophysical 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.