Abstract：To solve the problem that it is difficult to choose the number of segmentation regions for multi-threshold image segmentation, an adaptive multi-threshold image segmentation method based on Reversible Jump Markov Chain Monte Carlo (RJMCMC) method is proposed. Histogram-based image segmentation is essential to search the bottom between peaks. However, the multi-threshold segmentation number is difficult to determine and not all local peaks follow Gaussian distribution. Therefore, mixture of α-stable distributions is adopted to fit image gray level histogram. Firstly, a hierarchical Bayesian probability model is established with the number of local peaks and the various parameters for each component. Then, posterior probability reasoning based on RJMCMC is implemented to adaptively obtain the best number of α-stable distribution function and the parameters for each distribution. The experimental results on the single crystal pulling image, the simulated magnetic resonance imaging (MRI) image and international standard test images show that the image segmentation model is accurately constructed by the proposed method, and multi-threshold segmentation results of images are satisfactory.
[1] Huang Z J, Li X, Xu F J. An Adaptive Scale Segmentation for Remote Sensing Image Based on Visual Complexity. Journal of Electronics & Information Technology, 2013, 35(8): 1786-1792 (in Chinese) (黄志坚,黎 湘,徐帆江.基于视觉复杂度的自适应尺度遥感影像分割.电子与信息学报, 2013, 35(8): 1786-1792) [2] Liu D, Liang J L. A Bayesian Approach to Diameter Estimation in the Diameter Control System of Silicon Single Crystal Growth. IEEE Trans on Instrumentation and Measurement, 2011, 60(4): 1307-1315 [3] Lin K Y, Wu J H, Xu L H. A Survey on Color Image Segmentation Techniques. Journal of Image and Graphics, 2005, 10(1): 1-10 (in Chinese) (林开颜,吴军辉,徐立鸿.彩色图像分割方法综述.中国图象图形学报, 2005, 10(1): 1-10) [4] Lin Z C, Wang Z Y, Zhang Y Q. Optimal Evolution Algorithm for Image Thresholding. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(7): 1201-1206 (in Chinese) (林正春,王知衍,张艳青.最优进化图像阈值分割算法.计算机辅助设计与图形学学报, 2010, 22(7): 1201-1206) [5] Long J W, Shen X J, Chen H P. Adaptive Minimum Error Thre-sholding Algorithm. Acta Automatica Sinica, 2012, 38(7): 1134-1144 (in Chinese) (龙建武,申铉京,陈海鹏.自适应最小误差阈值分割算法.自动化学报, 2012, 38(7): 1134-1144) [6] Tian J W, Huang Y X, Yu Y L. A Fast FCM Cluster Multi-threshold Image Segmentation Algorithm Based on Entropy Constraint. Pattern Recognition and Artificial Intelligence, 2008, 21(2): 221-226 (in Chinese) (田军委,黄永宣,于亚琳.基于熵约束的快速FCM聚类多阈值图像分割算法.模式识别与人工智能, 2008, 21(2): 221-226) [7] Gao Y W, Xiong Y, Pan J J, et al. Multilevel Thresholding Method Based on Immune Genetic Algorithm and Gaussian Mixture Model for Image Segmentation. Application Research of Computers, 2012, 29(3): 1130-1134 (in Chinese) (高业文,熊 鹰,潘晶晶,等.基于IGA与GMM的图像多阈值分割方法.计算机应用研究, 2012, 29(3): 1130-1134) [8] Huang Z K, Chau K W. A New Image Thresholding Method Based on Gaussian Mixture Model. Applied Mathematics and Computation, 2008, 205(2): 899-907 [9] Huang D Y, Wang C H. Optimal Multi-level Thresholding Using a Two-Stage Otsu Optimization Approach. Pattern Recognition Letters, 2009, 30(3): 275-284 [10] Hammouche K, Diar M, Siarry P. A Multilevel Automatic Thre-sholding Method Based on a Genetic Algorithm for a Fast Image Segmentation. Computer Vision and Image Understanding, 2008, 109(2): 163-175 [11] Kato Z. Segmentation of Color Images via Reversible Jump MCMC Sampling. Image and Vision Computing, 2008, 26(3): 361-371 [12] Akay B. A Study on Particle Swarm Optimization and Artificial Bee Colony Algorithms for Multilevel Thresholding. Applied Soft Computing, 2013, 13(6): 3066-3091 [13] Horng M H. Multilevel Thresholding Selection Based on the Artificial Bee Colony Algorithm for Image Segmentation. Expert Systems with Applications, 2011, 38(11): 13785-13791 [14] Dirami A, Hammouche K, Diaf M, et al. Fast Multilevel Thre-sholding for Image Segmentation through a Multiphase Level Set Method. Signal Processing, 2013, 93(1): 139-153 [15] Li Y, Li J, Chapman M A. Segmentation of SAR Intensity Imagery with a Voronoi Tessellation, Bayesian Inference, and Reversible Jump MCMC Algorithm. IEEE Trans on Geoscience and Remote Sensing, 2010, 48(4): 1872-1881 [16] Salas-Gonzalez D, Kuruoglu E E, Ruiz D P. Finite Mixture of α-Stable Distributions. Digital Signal Processing, 2009, 19(2): 250-264 [17] Nolan J P. Numerical Calculation of Stable Densities and Distribution Functions. Communications in Statistics－Stochastic Models, 1997, 13(4): 759-774 [18] Lombardi M J. Bayesian Inference for α-Stable Distributions: A Random Walk MCMC Approach. Computational Statistics & Data Analysis, 2007, 51(5): 2688-2700 [19] Hao Y L, Shan Z M, Shen F. Parameter Estimation of α-Stable Distributions Based on Adaptive Metropolis Algorithm. Journal of Systems Engineering and Electronics, 2012, 34(2): 236-242 (in Chinese) (郝燕玲,单志明,沈 锋.基于自适应Metropolis算法的α稳定分布参数估计.系统工程与电子技术, 2012, 34(2): 236-242) [20] Fiche A, Cexus J C, Martin A, et al. Features Modeling with an α-Stable Distribution: Application to Pattern Recognition Based on Continuous Belief Functions. Information Fusion, 2013, 14(4): 504-520 [21] Chen Y J, Liu D, Liang J L. Bayesian Inference on Parameters for Mixtures of α-Stable Distributions Based on Markov Chain Monte Carlo. Journal of Xi′an University of Technology, 2012, 28(4): 385-391 (in Chinese) (陈亚军,刘 丁,梁军利.基于MCMC的混合α稳定分布参数贝叶斯推理.西安理工大学学报, 2012, 28(4): 385-391) [22] Richardson S, Green P J. On Bayesian Analysis of Mixtures with an Unknown Number of Components. Journal of the Royal Statistical Society: Series B, 1997, 59(4): 731-792 [23] Andrieu C, de Freitas N, Doucet A. Robust Full Bayesian Learning for Radial Basis Networks. Neural Computation, 2001, 13(10): 2359-2407 [24] Jin M N, Zhao Y J, Ge J W. DOA Estimation of Wideband Signals Based on Hybrid RJMCMC Method. Journal of Electronics & Information Technology, 2010, 32(2): 504-508 (in Chinese) (金美娜,赵拥军,盖江伟.一种基于混合RJMCMC方法的宽带信号DOA估计方法.电子与信息学报, 2010, 32(2): 504-508) [25] Elguebaly T, Bouguila N. Simultaneous Bayesian Clustering and Feature Selection Using RJMCMC-Based Learning of Finite Generalized Dirichlet Mixture Models. Signal Processing, 2013, 93(6): 1531-1546 [26] Gong M G, Liang Y, Shi J, et al. Fuzzy C-Means Clustering with Local Information and Kernel Metric for Image Segmentation. IEEE Trans on Image Processing, 2013, 22(2): 573-584
2014, Vol. 27 
