A Parallel Gannet Optimization Algorithm for Image Segmentation

Gannet optimization algorithm (GOA) is a meta-heuristic algorithm based on habits of gannet proposed by Zhang et al. In this paper, we propose a Gannet optimization algorithm using parallel strategy (PGOA). Since the GOA algorithm has the risk of easily falling into local optimality, the use of the parallel strategy can largely avoid falling into local optimality. Therefore, we use the parallel strategy to improve the GOA algorithm, which greatly improves the performance and efficiency of the algorithm. The improved algorithm is applied to image segmentation, and the processed images are evaluated using PSNR, SSIM, and FSIM as evaluation metrics. The experimental results show that the improved GOA algorithm can achieve higher quality image segmentation compared to other algorithms on image segmentation.