A Modified Particle Swarm Optimization Algorithm for Automatic Image Clustering

Abstract

In this paper, we present a new automatic image clustering algorithm based on a modified version of particle swarm optimization algorithm. ACMPSO clustering algorithm can partition image into compact and well separated clusters without any knowledge on the real number of clusters. It uses a swarm of particles with variable number of length, which evolve dynamically using mutation operators. Experimental results on real images demonstrate that the proposed algorithm is able to extract the correct number of clusters with denser and more compactness clusters. The results demonstrate that ACMPSOoutperforms other optimization algorithms.