Distributed system for image segmentation based on parallel metaheuristics

Abstract

In recent years, the integration of distributed systems with parallel processing techniques has significantly advanced the field of image processing. Distributed systems enable the efficient handling of large datasets by dividing the computational tasks across multiple nodes, improving both speed and scalability. Parallelization in image processing enhances performance by executing multiple tasks simultaneously, making it possible to process high- resolution images and complex datasets in real time. Metaheuristic algorithms have been widely adopted for optimization tasks in image processing due to their ability to explore large search spaces effectively. These algorithms, when coupled with machine learning (ML) models, provide powerful solutions for feature selection in classification tasks. Metaheuristics help identify the most relevant features from large datasets, thereby enhancing the classification performance of ML models. Further, parallel metaheuristics, deployed in a distributed environment, can optimize image segmentation processes by splitting the task across multiple computational units, thereby speeding up the process while maintaining or improving segmentation accuracy. Bearing those in mind, we propose in this thesis, four hybrid methods focusing on feature selection, classification, and parallel image segmentation. The first method employs Grey Wolf Optimization (GWO) for selecting the most relevant features, followed by a Random Forest (RF) classifier to perform accurate classification. The second method integrates Correlation-based filtering with GWO to enhance the feature selection process, and applies various machine learning classifiers for comparative performance analysis. For parallel image segmentation, we designed two parallel approaches to improve efficiency and accuracy. The first is a Parallel Whale Optimization Algorithm (WOA) combined with K-Means clustering, implemented using multiprocessing to accelerate the segmentation process. The second method uses Grey Wolf Optimization in combination with Fuzzy C-Means (FCM), leveraging GPU acceleration for parallel execution. This approach significantly reduces computational time while maintaining high segmentation quality. All methods are evaluated using standard performance metrics. Our aim is to demonstrate the effectiveness of parallel metaheuristics and hybrid selection-classification strategies in medical image analysis. In conclusion, this thesis shows that combining parallel computing, metaheuristic optimization, and machine learning offers an effective, accurate, and scalable solution to challenges in medical image analysis, contributing to the development of next-generation diagnostic systems.