Learning from uncertain image data using granular fuzzy sets and bio-mimetic applicability functions

In this paper we present a new method for machine learning from images using uncertain information granules which has been inspired by bio-mimetic study of human perceptual processing. We present a method for generating labelled image data using the rapid application of rough labelled regions to the image under study. Over each region is defined an applicability function which acts as a centre of focus for the uncertain information contained within the region. We present a number of alternative applicability functions inspired by the human visual system and particularly by the centre-weighted effect of the fovea within the retina. We also show how this uncertain data can be used to directly train a granular fuzzy machine learner.