A Novel Hybrid Bat Algorithm for the Multilevel Thresholding Medical Image Segmentation

摘要

In this paper, a novel hybrid bat algorithm using Otsu's method for multilevel thresholding medical image segmentation optimization is proposed. We use the modified random localization strategy to improve the bats' exploratory abilities and increase search efficiency and convergence speed. The proposed algorithm is used to find the optimal thresholds by maximizing Otsu's objective function, and its performance was tested two medical images. The experimental results show that the proposed algorithm provides better solutions and higher computation accuracy.