Multilevel minimum cross entropy thresholding using artificial bee colony algorithm

The minimum cross entropy thresholding (MCET) has been widely applied in image processing. In this paper, a new multilevel MCET algorithm based on the artificial bee colony (ABC) algorithm is proposed. The proposed thresholding algorithm is called ABC-based MCET algorithm. Four different methods including the exhaustive search, the honey bee mating optimization (HBMO), the particle swarm optimization (PSO) and the quantum particle swarm optimization (QPSO) methods are also implemented for comparison with the results of the proposed method. The experimental results demonstrate that the proposed ABC-based MCET algorithm can efficiently search for multiple thresholds that are very close to the optimal ones selected by using the exhaustive search method. Compared with the other three thresholding methods, the segmentation results using the ABC-based MCET algorithm is the best. It is promising to encourage further research for applying the HBMO algorithm to complex problems of image processing and pattern recognition. © 2013 Universitas Ahmad Dahlan.