Perfect image segmentation using pulse coupled neural networks

This paper describes a method for segmenting digital images using pulse cou pled neural networks (PCNN's), The pulse coupled neuron (PCN) model used in PCNN is a modification of Eckhorn's cortical neuron model. A single layere d laterally connected PCNN is capable of perfectly segmenting digital image s even when there is a considerable overlap in the intensity ranges of adja cent regions. Conditions for perfect image segmentation are derived. It is also shown that addition of an inhibition receptive held to the neuron mode l increases the possibility of perfect segmentation, The inhibition input r educes the overlap of intensity ranges of adjacent regions by effectively c ompressing the intensity range of each region.