This paper describes a method for segmenting digital images using pulse coupled neural networks (PCNN's). The pulse coupled neuron (PCN) model used in PCNN is a modification of Eckhorn's cortical neuron model. A single layered laterally connected PCNN is capable of perfectly segmenting digital images even when there is a considerable overlap in the intensity ranges of adjacent regions. Conditions for perfect image segmentation are derived. It is also shown that addition of an inhibition receptive field to the neuron model increases the possibility of perfect segmentation. The inhibition input reduces the overlap of intensity ranges of adjacent regions by effectively compressing the intensity range of each region.

No abstract

This paper describes an object detection system based on pulse coupled neural networks. The system is designed and implemented to illustrate the power, flexibility and potential the pulse coupled neural networks have in real-time image processing. In the preprocessing stage, a pulse coupled neural network suppresses noise by smoothing the input image. In the segmentation stage, a second pulse coupled neural-network iteratively segments the input image. During each iteration, with the help of a control module, the segmentation network deletes regions that do not satisfy the retention criteria from further processing and produces an improved segmentation of the retained image. In the final stage each group of connected regions that satisfies the detection criteria is identified as an instance of the object of interest.

It is shown that if the parameters of a pulse coupled neural network are properly adjusted neurons corresponding to the pixels of each region can be forced to pulse together. Each synchronous burst identifies an image region. 0-7803-1901-X/94 $4.00 01994 IEEE

No abstract