Comparative Analysis of Edge Detection Algorithms with Particle Swarm Optimization for Enhanced Image Processing

Edge detection plays an important role in various fields by identifying object boundaries and supporting advanced image analysis, such as segmentation, recognition, and tracking. Many edge detection algorithms, such as Canny, Laplacian, and Prewitt, have been developed to address issues such as noise sensitivity, computational complexity, and detection accuracy. This research compares the optimized algorithms using Particle Swarm Optimization (PSO). The results of this study show that the optimized algorithm provides better performance based on the evaluation conducted using entropy, Mean Squared Error (MSE), and computation time, and has practical implications. This research also determines the most effective edge detection technique in various image processing scenarios, thus contributing to the optimization of image analysis workflows in real-world contexts.