Automatic Image Segmentation Using PCNN and Quantum Geese Swarm Optimization

Image segmentation is a very important aspect in the fields of computer vision and pattern recognition. Although Pulse-coupled Neural Network (PCNN) is an effective method for image segmentation, the optimal parameters of PCNN are difficult to be decided. In order to effectively find the optimal parameters of the PCNN, Quantum Geese Swarm Optimization (QGSO) is proposed to evolve parameters of PCNN. The proposed QGSO applies quantum computing theory to Geese Swarm Optimization (GSO) for continuous optimization problems. Minimal combined weighting entropy which considers of Shannon-entropy and Cross-entropy is used as the fitness function of QGSO. Experiment results show that the proposed method can obtain better segmented image and has an excellent performance.