Multilevel minimum cross entropy threshold selection with shuffled frog-leaping algorithm

Multilevel thresholding algorithms are important techniques for image segmentation, among them; the minimum cross entropy thresholding (MCET) has been widely applied. In this paper, a new multilevel MCET algorithm using the shuffled frog-leaping optimization (SFLO) algorithm is proposed. The proposed image thresholding algorithm is called SFLO-based MCET algorithm. Five different methods including the exhaustive search, the honey bee mating optimization (HBMO), the firefly (FF) algorithm, the particle swarm optimization (PSO) and artificial bee colony (ABC) algorithm are also implemented for comparison. The experimental results demonstrate that the proposed SFLO-based MCET algorithm can efficiently search for multiple thresholds that are very close to the optimal ones examined by the exhaustive search method. Compared with the other four thresholding methods, the needs of computation time using the SFLO-based MCET algorithm is the smallest. And further, the performance of segmentation is better than the one of PSO-based MCET algorithm, while the result of SFLO-based MCET algorithm is insignificant with respect to the other three algorithms.