Medial axis generation in a model of perceptual organization

Axial skeletons are promising intermediate representations of shape which are used in machine vision and higher level theories of vision to provide a concise and intuitive description of the shape. More recently, physiological correlates of axial skeletons have been reported. We show that a stable approximation of the medial axis can be generated based on an existing neurally plausible model of perceptual organization.