Particle Swarm Optimization Algorithm and Its Application in Image Segmentation

Abstract

The complexity and scale of image data are growing due to the fast advancement of medical imaging technology. As a result, traditional image segmentation methods are finding it difficult to handle these data, as they typically perform poorly when faced with complex structures and noise. In order to greatly increase the segmentation accuracy and resilience, this study presents the Particle Swarm Optimization (PSO) technique, which optimizes the segmentation parameters through global search, and K-means in image segmentation for fatty liver level recognition and their optimization strategies. The paper concludes that heuristic optimization algorithms such as the PSO have gained considerable focus. This paper provides insight into the application of the PSO algorithm, Otsu’s Method, and the Watershed within the field of image segmentation for their global search capability and adaptability to complex problems. Meanwhile, classical segmentation methods such as OSTU, Watershed and K-means are also widely used in medical image processing due to their simplicity and effectiveness. The PSO simulates information sharing and collaboration between individuals in a population to optimize the process of image segmentation. This paper concludes that the PSO outperforms traditional methods such as OSTU, Watershed Algorithm and K-means clustering in image segmentation for liver fat level identification, especially in both complex images and lighting conditions, and shows strong accuracy and stability.