Multilevel Minimum Cross Entropy Threshold Selection Based on Quantum Particle Swarm Optimization

The minimum cross entropy thresholding (MCET) has been proven as an efficient method in image segmentation for bilevel thresholding. However, this method is computationally intensive when extended to multilevel thresholding. This paper first employs a recursive programming technique which can reduce an order of magnitude for computing the MCET fitness function. Then, a quantum particle swarm optimization (QPSO) algorithm is proposed for searching the near- optimal MCET thresholds. The experimental results show that the proposed QPSO-based algorithm can get ideal segmentation result with less computation cost.