Multilevel Thresholding for Satellite Image Segmentation with Moth-flame Based Optimization

In this paper, an improved version of the moth-flame optimization (MFO) algorithm for image segmentation is proposed to effectively enhance the optimal multilevel thresholding of satellite images. Multilevel thresholding is one of the most widely used methods for image segmentation, as it has efficient processing ability and easy implementation. However, as the number of threshold values increase, it consequently becomes computationally expensive. To overcome this problem, the nature-inspired meta-heuristic named multilevel thresholding moth-flame optimization algorithm (MTMFO) for multilevel thresholding was developed. The improved method proposed herein was tested on various satellite images tested against five different existing methods: the genetic algorithm (GA), the differential evolution (DE) algorithm, the artificial bee colony (ABC) algorithm, the particle swarm optimization (PSO) algorithm, and the moth-flame optimization (MFO) algorithm for solving multilevel satellite image thresholding problems. Experimental results indicate that the MTMFO more effectively and accurately identifies the optimal threshold values with respect to the other state-of-the-art optimization algorithms.