A Darwinian Whale Optimization Approach to Image Thresholding

This work presents a new multilevel thresholding algorithm for image segmentation, addressing the limitations of metaheuristic algorithms. Multilevel thresholding provides a fast and effective approach. A major challenge for metaheuristic algorithms like Whale Optimization Algorithm (WOA) is stagnation, leading to suboptimal solutions and premature convergence. This research introduces the Darwinian Whale Optimization Algorithm (DWOA), which incorporates the principles of natural selection to address this issue. DWOA enhances diversity and improves the quality of individuals within the population while maintaining the convergence speed of WOA.The proposed DWOA employs an encouragement-punishment strategy to guide search agents effectively through the search space. This strategy is implemented by dividing the population into groups, where each group collaborates to locate optimal threshold values. The effectiveness of DWOA is evaluated on 12 test images using the energy curve method, a well-established approach for performance assessment. Additionally, Kapur entropy is employed to further assess DWOA's capability. To conduct a thorough analysis, seven additional search algorithms have been developed and assessed alongside the DWOA. The segmented results indicate that the proposed mthod has the best performance on 32 out of 36 cases in terms of Kapur fitness. Results prove that DWOA consistently outperforms the standard WOA and other heuristic search methods, establishing itself as a powerful tool for image segmentation tasks.