Title: Multilevel thresholding for image segmentation through Bayesian particle swarm optimisation

Authors: Yunzhi Jiang; Zhifeng Hao; Ganzhao Yuan; Zhenlun Yang

Addresses: School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, Guangdong, China. ' Faculty of Computer, Guangdong University of Technology, Guangzhou 510006, Guangdong, China; School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, Guangdong, China. ' School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, Guangdong, China. ' School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, Guangdong, China

Abstract: A simpler and efficient PSO algorithm based on Bayesian theorem and the characters of intensity images is proposed, called as Bayesian particle swarm optimisation algorithm (BPSO). In BPSO, a new method is designed to assign the constriction coefficient of the 'social influence' term for each particle automatically and separately based on Bayesian theorem, so that they can have different levels of exploration and exploitation capabilities. A new population initialisation strategy is adopted to make the search more efficient according to the characters of multilevel thresholding in an image arranged from a low grey level to a high one. The experimental results indicate that BPSO can produce effective, efficient and smoother segmentation results in comparison with three existing methods on Berkeley datasets.

Keywords: image segmentation; multilevel thresholding; Bayesian theorem; particle swarm optimisation; Bayesian PSO.

DOI: 10.1504/IJMIC.2012.046405

International Journal of Modelling, Identification and Control, 2012 Vol.15 No.4, pp.267 - 276

Published online: 29 Nov 2014 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article