Potential use of synchronous pulse coupled neural network in partial occlusion

Abstract

The study of sperm motility especially in sperm tracking has received increasing attentions. In this paper, we proposed an automated system to help in solving partial occlusion between sperms. Synchronous Pulse Coupled Neural Network (SPCNN) is employed to extract the centroid of the sperm from the occluded sperms. By using an optimization algorithm called Particle Swarm Optimization (PSO), the five unknown parameters were optimized. The proposed method has been evaluated with 500 sperm images. The proposed SPCNN method solved the partial occlusion problem by providing more accurate results. In future, SPCNN is expected to be implemented in sperm tracking algorithm.