Particle Swarm Optimization with Time-Varying Acceleration Coefficients in Multilevel Image Thresholding

Multilevel image thresholding based on the exhaustive search for the optimal thresholds is computationally expensive. To overcome this drawback this paper investigates the use of the particle swarm optimization (PSO) algorithms with time-varying acceleration coefficients in multilevel image thresholding. Specifically, two multilevel image thresholding methods based on Kapur's entropy and PSO algorithm with time-varying acceleration coefficients are considered. The two methods use different strategies to vary cognitive and social acceleration coefficients within the PSO algorithm. The considered thresholding methods are assessed on five test images. The multilevel image thresholding performance is assessed for varying numbers of thresholds. The performance of the methods under consideration is compared to that of the thresholding method based on the PSO algorithm with constant acceleration coefficients. The experimental results show that the thresholding methods based on the PSO algorithm with time-varying acceleration coefficients can be successfully used to obtain image thresholds across different test images.