Grayscale image edge detection based on pulse-coupled neural network and particle swarm optimization

Pulse coupled neural network (PCNN) was originally presented to explain the synchronous burst of the neurons in the cat visual cortex by Eckhorn. Because the parameters greatly affect the performance of PCNN, finding the optimal parameters becomes an onerous task. Particle swarm optimization (PSO) is a global stochastic evolutionary algorithm. It tries to find optimal regions of complex searching space through the interaction of particles in the population. A self-tuning optimized method for PCNN parameters based on PSO algorithm and it was used to detect edges in a gray image automatically and successfully. The effective of the proposed method is verified by simulation results, that is to say, the quality of the image edge detection is much better and parameters are set automatically.