A Comparative Analysis of Different Natural Exponent Inertia Weight Strategies for Particle Swarm Optimization in Multilevel Image Thresholding

This paper presents a comparative analysis of two different natural exponent inertia weight strategies for particle swarm optimization in multilevel image thresholding. The considered multilevel image thresholding methods are based on Otsu’s between class variance. The multilevel thresholding methods are evaluated on different test images and for varying numbers of thresholds. The experimental results have demonstrated that the particle swarm optimization algorithm with the natural exponent inertia weight can be successfully employed to obtain threshold levels for different test images.