Enhanced Chaos Game Optimization for Multilevel Image Thresholding through Fitness Distance Balance Mechanism

This study proposes a method to enhance the Chaos Game Optimization (CGO) algorithm for efficient multilevel image thresholding by incorporating a fitness distance balance mechanism. Multilevel thresholding is essential for detailed image segmentation in digital image processing, particularly in environments with complex image characteristics. This improved CGO algorithm adopts a hybrid metaheuristic framework that effectively addresses the challenges of premature convergence and the exploration-exploitation balance, typical of traditional thresholding methods. By integrating mechanisms that balance fitness and spatial diversity, the proposed algorithm achieves improved segmentation accuracy and computational efficiency. This approach was validated through extensive experiments on benchmark datasets, comparing favorably against existing state-of-the-art methods.