Image Segmentation using Different Optimization Technique

In image segmentation field Multilevel thresholding is an important technique. However, in standard methods, the complexity of this method increases with the variation of number of thresholds value. To avoid this disadvantages, nature inspired meta-heuristic techniques are used. These metaheuristic algorithms give near exact results in a reasonable time, which catches the attention of recent researchers for optimization. No matter what kind of optimization method , the solution set must be represented via some way. For example, GWO (Grey Wolf Optimizer) this method follows the grouping and hunting behavior of wolves, PSO (Particle Swarm Optimizer) inspired from foraging behavior of swarm of particles (assuming birds as particles). Above optimizer are applied on some standard images collected from USC SIPI, BSD 500 database. At end part, a comparison was made based on threshold values, image quality measures, and computational time .In this analysis, GWO based results and PSO based results are compared with the standard results .The results are compared in terms of thresholded images, image quality .Time complexity and plotting convergence plots, which shows the goodness of Grey Wolf Optimizer in terms of global search