Visual Hyperacuity: Representation and computation of high precision position information

Abstract

Visual hyperacuity, acuity an order of magnitude finer than the optical resolution of a diffraction-limited visual system, is described and analyzed in the terms of information theory. It is shown that in principle, the computation and representation of both luminance and edge features can be performed with a precision commensurate with hyperacuity thresholds and human abilities. Luminance features are represented as the centroid of the intensity distribution. Edge features are represented as zero-crossings in the difference of two filtered intensity distributions; this method is shown to be very economical. Algorithms are formulated in accord with the different representations, and tested with vernier acuity tasks. The results indicate that both methods can extract relative position with an accuracy better than 1 s arc.