Image segmentation using minimum cross entropy and bacterial foraging optimization algorithm

Image segmentation is a fundamental step for many image analysis and preprocessing tasks. In segmentation, minimum cross entropy (MCE) based multilevel thresholding is regarded as an effective improvement over the bi-level method. However, it is very time consuming for real-time applications. In this paper, a fast threshold selection method based on bacterial foraging optimization (BFO) algorithm is proposed to speed up the original MCE threshold method in image segmentation. BFO algorithm is a newly developed memetic meta-heuristic evolutionary algorithm with good global search ability. Experimental results compared with particle swarm optimization (PSO) and genetic algorithm (GA) show that the BFO based thresholding can exactly obtain the global optimal threshold values with significant decrease in the computational time and provide better peak to signal noise ratio (PSNR) value and stability.