Particle Swarm Optimizer Guided Active Contour Model for Lung Image Segmentation

Snakes, also known as active contour models, are widely used in a variety of applications, including Detecting object boundaries, segmenting images, tracking objects, and classification based on energy minimization. While standard optimization techniques can be used to achieve energy minimization, more recently, techniques based on evolutionary algorithms inspired by nature have been created. Particle swarm optimization (PSO) is one such evolutionary method that has been widely applied in active contours. Conventional PSO provides accurate curve recognition in the object border because it converges quickly and is readily took in a local minimum. The suggested PSOGACM has each control point in the snake and also has a swarm to assign in it. Subsequently, the swarms exchange information with one another to jointly seek for their optimal spots. The active contour model considerably improves the PSO-based search process's performance. The outcomes of the experiments show that the suggested strategy is more effective than traditional methods. The proposed system has accuracy of 91.15%, sensitivity of 89.20%, and precision of 88.23% is more effective and more accurate.