Image segmentation based on improved PSO

Abstract

The multilevel thresholds image segmentation method based on maximum entropy and improved particle swarm optimization (PSO) is presented in this paper. The proposed algorithm takes advantage of the characteristics of particle swarm optimization, and improves the parameter and evolutional process of basic PSO. Compared with the basic PSO method, the proposed method can get the better optimal thresholds and more ideal segmentation result with less computation cost and has good search stability in the experiments. The experimental results indicate that the proposed method is an promising and efficient segmentation method with fast convergence and high computational efficiency.