Multi-Threshold Image Segmentation Based on Improved Grey Wolf Optimization Algorithm

Abstract

Threshold selection is the key to image threshold segmentation. The threshold determines the good or bad of the image segmentation results. As the number of thresholds increases, the computational process of image segmentation becomes more and more complicated. In order to select a better threshold for image segmentation, an improved Grey Wolf Optimization (IGWO) algorithm is proposed in this paper. The good point set method is applied to the GWO to generate the initial population, the weight is introduced in the position update of gray wolf hunting process, and the algorithm is used to solve the global optimization problem with the Kapur partition function as the objective function. The IGWO algorithm has good global convergence and computational robustness, can effectively avoid falling into local optimum, and is especially suitable for solving high-dimensional and multi-peak complex function problems, and can be well integrated into the image segmentation process. The results of theoretical analysis and simulation experiments show that compared with the image segmentation results of particle swarm optimization (PSO), the algorithm has better segmentation effect when multiple segmentation thresholds are selected. The segmentation efficiency, the threshold range obtained by optimization is more stable, and the segmentation quality is higher.