Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 02015 | |
Number of page(s) | 7 | |
Section | Machine Learning in Healthcare and Finance | |
DOI | https://doi.org/10.1051/itmconf/20257002015 | |
Published online | 23 January 2025 |
Particle Swarm Optimization Algorithm and Its Application in Image Segmentation
School of Information Science and Technology, Northwest University, Xi’an, Shaanxi, 710127, China
Corresponding author: 2023117473@stumail.nwu.edu.cn
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.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.