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.

[1]  John L. Johnson,et al.  PCNN models and applications , 1999, IEEE Trans. Neural Networks.

[2]  Liu Qing,et al.  Automated image segmentation using improved PCNN model based on cross-entropy , 2004, Proceedings of 2004 International Symposium on Intelligent Multimedia, Video and Speech Processing, 2004..

[3]  Xiaopan Zhang,et al.  RS Image PCNN Automatical Segmentation Based on Information Entropy , 2010, 2010 Second International Conference on Multimedia and Information Technology.

[4]  Nor Ashidi Mat Isa,et al.  Segmentation and detection of human spermatozoa using modified Pulse Coupled Neural Network optimized by Particle Swarm Optimization with Mutual Information , 2015, 2015 IEEE 10th Conference on Industrial Electronics and Applications (ICIEA).

[5]  Xiu-juan Lei,et al.  Geese-Inspired Hybrid Particle Swarm Optimization Algorithm for Traveling Salesman Problem , 2009, 2009 International Conference on Artificial Intelligence and Computational Intelligence.

[6]  I. Mokris,et al.  Linking and Activation Potential Optimization in the Pulse Coupled Neural Network , 2008, 2008 IEEE International Conference on Computational Cybernetics.

[7]  Qi Chun-liang,et al.  Study of Automated PCNN System Based on Genetic Algorithm , 2006 .

[8]  Hong Zhou,et al.  Simplified parameters model of PCNN and its application to image segmentation , 2015, Pattern Analysis and Applications.

[9]  Jian Li,et al.  Non-local-based spatially constrained hierarchical fuzzy C-means method for brain magnetic resonance imaging segmentation , 2016, IET Image Process..

[10]  Li Xiao-gang.  Research on automated PCNN system based on cultural algorithm , 2008 .