Image denoising using neural network based Accelerated Particle Swarm Optimization

This paper proposes a new type of filter called neural network filter for image denoising. The noisy images are fed as input to the network and the weights are updated with LMS algorithm. Further the weights are updated by using a recently developed novel optimization technique called Accelerated Particle Swarm Optimization (APSO) for gray level image denoising application. Implementation of APSO is easier than the PSO(Particle Swarm Optimization) and GA(Genetic Algorithm) in terms of computational time. The results of comparison of the optimization has been presented.