With rapid advancement of artificial intelligence via evolutionary optimization, multilevel thresholding has become a feasible and critical way for image segmentation. Genetic Algorithms (GAs) and Particle Swarm Optimization (PSO) are two dominating schemes for multilevel thresholding, which group image pixels into multiple classes in terms of the intensity level of each pixel. However, majority segmentation practices of GAs and PSO are judged by visual appeals exclusively. To make convincing comparisons between two primary approaches of GAs and PSO, systematic quantitative analysis is proposed and conducted with respect to diverse performance metrics.