Image Segmentation through Particle Swarm Optimization based on Simulated Annealing

H. Zhang, T. Liao, and Y. Cen (PRC)

Keywords

Simulated annealing, particle swarm optimization, Otsu, threshold segmentation, and pattern recognition

Abstract

A rapid Otsu’s method based on simulated annealing particle swarm optimization algorithm was proposed for image segmentation. Otsu’s method required much computation. Particle Swarm Optimization (PSO) algorithm was used to search threshold vectors. Each particle represented a feasible threshold vector. Thus, the optimal threshold could be acquired by the cooperation of particle swarm. For better convergence, simulated annealing idea was applied in PSO algorithm, and a random method based on simulated annealing was used to obtain the inertia weight used in PSO algorithm. Simulation experiment results demonstrated that this method retained the uncomplicated principle, simple operation and coevolutionary search of standard PSO, and also solved the slow convergence problem, could acquire ideal results with less computation.

Important Links:

Go Back