Theoretical and Experimental Evaluation of Hybrid ACO-k-means Image Segmentation Algorithm for MRI Images Using Drift-analysis

摘要

The hybrid Ant Colony Optimization (ACO) – k-means image segmentation algorithm for MRI images segmentation is considered. The proposed algorithm and sub-system for the medical image segmentation have been implemented. The time complexity of proposed algorithm is investigated using consequences from Drift theorem. It is established that the proposed algorithm has a polynomial estimation of complexity. Images from the Ossirix image dataset and real medical images were used for testing. Comparison of segmentation accuracy have been performed between proposed algorithm and competing algorithms C-means and Magic Wand.