New two-dimensional fuzzy C-means clustering algorithm for image segmentation

Abstract

To solve the problem of poor anti-noise performance of the traditional fuzzy C-means (FCM) algorithm in image segmentation, a novel two-dimensional FCM clustering algorithm for image segmentation was proposed. In this method, the image segmentation was converted into an optimization problem. The fitness function containing neighbor information was set up based on the gray information and the neighbor relations between the pixels described by the improved two-dimensional histogram. By making use of the global searching ability of the predator-prey particle swarm optimization, the optimal cluster center could be obtained by iterative optimization, and the image segmentation could be accomplished. The simulation results show that the segmentation accuracy ratio of the proposed method is above 99%. The proposed algorithm has strong anti-noise capability, high clustering accuracy and good segment effect, indicating that it is an effective algorithm for image segmentation.

Keywords

image segmentation / fuzzy C-means clustering / particle swarm optimization / two-dimensional histogram

References

[1] LiewA. W., YanH., LawN. F.. Image segmentation based on adaptive cluster prototype estimation [J]. IEEE Transactions on Fuzzy Systems, 2005, 13(4): 444-449

[2] LiuY. T.. A genetic clustering algorithm for data with non-spherical shape cluster [J]. Pattern Recognition Letter, 2000, 33(1): 1251-1259

[3] PhamD. L.. Fuzzy clustering with spatial constraints [C]. Proceedings of the IEEE International Conference on Image Processing, 2002, New York, IEEE Computer Society: 65-68

[4] DengH., WuY.-h., DuanJ.-an.. Adaptive learning with guaranteed stability for discrete-time recurrent neural networks [J]. Journal of Central South University of Technology, 2007, 14(3): 685-690

[5] WangX.-j., ShiH.-bo.. Clustering and fuzzy neural network for fuzzy rule sets modeling [J]. Journal of Central South University of Technology, 2003, 34(4): 360-362

[6] ChenS.-c., ZhangD.-qing.. Robust image segmentation using FCM with spatial constraints based on new kernel-induced distance measure [J]. IEEE Transactions on Systems, Man, and Cybernetics, 2004, 34(4): 1907-1916

[7] YuJ.-h., WangY.-y., ShiX.-ling.. Image segmentation with two-dimension fuzzy cluster method based on spatial information [J]. Opto-Electronic Engineering, 2007, 34(4): 114-119

[8] WangX., WangY., WangL.. Improving fuzzy C-means clustering based on feature-weight learning [J]. Pattern Recognition Letter, 2004, 25(10): 1123-1132

[9] AhmedM. N., YamanyS. M., MohamedN.. A modified fuzzy C-means algorithm for bias field estimation and segmentation of MRI data [J]. IEEE Trans on Medical Imaging, 2002, 21(3): 193-199

[10] LiX.-h., ZhangT.-y., QuZhan.. Image segmentation using fuzzy clustering with spatial constraints based on Markov random field via Bayesian theory [J]. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, 2008, 91(3): 723-729

[11] GaoX.-bo.Fuzzy cluster analysis and its applications [M], 2004, Xi’an, Xidian University Press: 50-54

[12] ClercM., KennedyJ.. The particle swarm: Explosion, stability, and convergence in a multi-dimensional complex space [J]. IEEE Transaction on Evolutionary Computation, 2004, 6(11): 58-73

[13] van Den BerghF.An analysis of particle swarm optimizaters [D], 2001, Pretoria, South Africa, University of Pretoria

[14] SilvaA., NevesA., CostaE.. An empirical comparison of particle swarm and predator prey optimization [C]. Proceeding of the Artificial Intelligence and Cognitive Science: 13th Irish International Conference, 2002, Berlin, Springer-Verlag: 103-110

[15] HigashitaniM., IshigameA., YasudaK.. Particles swarm optimization considering the concept of predator-prey behavior [C]. Proceedings of 2006 IEEE Congress on Evolutionary Computation, 2006, New York, IEEE Computer Society: 434-437