Optimal Multilevel Thresholding for Image Segmentation Using Contrast-Limited Adaptive Histogram Equalization and Enhanced Convergence Particle Swarm Optimization

This paper proposes a Tsallis entropy based multilevel thresholding method for image segmentation, using Contrast-Limited Adaptive Histogram Equalization(CLAHE) and a novel algorithm called Enhanced Convergence Particle Swarm Optimization(ECPSO). This is done to optimize the thresholds so that better image segmentation is obtained. Ten test images have been used to obtain the results, which are then compared with those obtained from Genetic Algorithm(GA), Particle Swarm Optimization(PSO) and Bacterial Foraging(BF) algorithms. The results obtained by the proposed method have been found to be significantly better than those obtained by the above mentioned algorithms.