Comparative analysis of two leading evolutionary intelligence approaches for multilevel thresholding

Abstract

The rapid advance of artificial intelligence has made complex image processing in real time possible. Multilevel thresholding has become a feasible way for image segmentation, even in the presence of poor contrast and external artefacts. Genetic algorithms (GAs) and particle swarm optimisation (PSO) are broadly recognised by far to be two dominating schemes which outperform classical ones on multilevel thresholding. Qualitative analysis can usually be applied to observe their superiority to all classical approaches. However, no convincing result is reached with respect to differences in performance between GAs and PSO. The existing segmentation practices are either examined by visual appeals exclusively, or evaluated quantitatively assuming perfect statistical distributions. To make thorough comparisons, comparative analysis of two leading multilevel thresholding approaches is conducted for true colour image segmentation. The information theory is also employed to analyse the outcomes of systematic approaches using diverse quantitative metrics from various aspects.