A control-driven transition strategy for enhanced multi-level threshold image segmentation optimization

This work proposes an image segmentation approach based on a multi-threshold segmentation method and the enhanced Flood Algorithm combined with the Non-Monopolize search (named Improved IFLANO). The introduced approach, depending on IFLANO, offers much better segmentation quality for various images. Based on the existing structure, two different types of optimization techniques are added within IFLANO to enhance the update dynamics during optimization. The random strategy used in the Aquila optimization procedure enhances the performance of FLA, and a self-transition adaptation enhances the exploration ability of the image analysis. IFLANO framework is implemented for multi-level threshold image segmentation wherein the evaluation metric is Kapur’s entropy-based between-class variance. Benchmarking studies against standard test images show that IFLANO works not only faster but also yields better, more stable outcomes in image segmentations within similar time frames. IFLANO is shown to put any solution a step forward in its search for more accurate alternatives than any of the considered techniques by getting 96% improvement. We also find that the proposed method got better results in solving large medical clustering applications.