ENHANCED EDGE DETECTION USING PSO ALGORITHM FOR COMPUTER VISION

Edge detection is a fundamental task in image processing with numerous applications in fields such as medical imaging, autonomous driving, and surveillance. This abstract proposes a novel approach to edge detection leveraging Particle Swarm Optimization (PSO) algorithm. The proposed method integrates PSO's ability to search and optimize a large solution space efficiently with the objective of accurately detecting edges in digital images. The algorithm operates by iteratively adjusting particle positions in the search space to minimize an objective function, which is tailored to capture edge information effectively. Unlike traditional edge detection methods, which often rely on handcrafted features or predefined filters, the proposed PSO-based approach adapts dynamically to the characteristics of the input image, leading to improved edge detection performance. Experimental results on standard benchmark datasets demonstrate the effectiveness of the proposed method in accurately localizing edges while maintaining robustness to noise and variations in image content. Furthermore, comparative analyses against state-of-the-art edge detection techniques validate the superiority of the proposed PSO-based algorithm in terms of both accuracy and computational efficiency, showcasing its potential for real-world applications.

Keywords: Edge Detection, Particle Swarm Optimization (PSO), Image Processing, Optimization, Computational Efficiency.