Multi-Strategy Improved Love Evolutionary Algorithm for Global Optimization and Art Image Segmentation

Although the Love Evolution Algorithm (LEA) has achieved encouraging results in optimization tasks, several shortcomings still limit its effectiveness when solving high-dimensional multimodal problems. In particular, the fixed interaction threshold, stochastic reflection mechanism, and convergence-biased role evolution process may weaken population diversity and reduce the coordination between exploration and exploitation during evolution. To overcome these issues, this paper develops a Multi-Strategy Improved Love Evolution Algorithm (MILEA) under a phase-oriented cooperative evolutionary framework. First, a diversity-enhanced reflection mechanism is incorporated to enlarge the search region and dynamically regulate evolutionary dispersion during the early search stage. Second, an adaptive acceptance threshold strategy is introduced to adjust pairwise interaction behaviors according to the evolutionary state, thereby improving search flexibility and adaptability. Third, an elite-guided role evolution mechanism is designed to strengthen local exploitation and guide the population toward promising regions more efficiently. Furthermore, a probability-based collaborative update scheme is employed to coordinate multiple search behaviors adaptively while preserving the same computational complexity order as the original LEA framework. To evaluate the effectiveness of the proposed algorithm, extensive experiments are conducted on the CEC2017 and CEC2022 benchmark suites. The experimental results indicate that MILEA exhibits competitive optimization performance with respect to convergence behavior, solution accuracy, and optimization stability when compared with several advanced metaheuristic algorithms. Relative to the original LEA, the proposed method obtains improved average fitness values on most benchmark functions and significantly suppresses result fluctuations on several multimodal and hybrid optimization problems, indicating enhanced robustness during repeated independent runs. In addition, statistical evaluations based on the Wilcoxon signed-rank test and Friedman ranking analysis further support the reliability of the proposed optimization framework. To verify its practical applicability, MILEA is also applied to Otsu-based multi-threshold image segmentation tasks. Experimental results evaluated by PSNR, SSIM, and FSIM demonstrate that the proposed algorithm can generate high-quality segmentation results and preserve important structural image information. Overall, the proposed MILEA provides an effective optimization framework for both benchmark optimization and practical image segmentation applications.