Unsupervised image segmentation based on multidimensional particle swarm optimization

Abstract

An unsupervised image segmentation method based on multidimensional (MD) particle swarm optimization (PSO) is proposed in this paper. Firstly, a clustering-based nonlinear objective function of unsupervised image segmentation is established according to Turi's validity index. Secondly, MD PSO algorithm is adopted to minimize the objective function to seek the optimal number and cluster centers of segmented regions simultaneously. Finally, global best (GB) position of swam in each dimension is modified to avoid being trapped in local optima. Experimental results valid the performance of the proposed image segmentation algorithm.