An Unsupervised Color Image Segmentation Algorithm Based on Context Information
GUO Lei1, HOU YiMin1, LUN XiangMin2
1.School of Automation, Northwestern Polytechnical University, Xi'an 7100722. Space Optical Technology Research Center, Xi'an Institute of Optics and Precision Mechanics, Chinese Academy of Sciences, Xi'an 710068
Abstract An unsupervised color image segmentation method based on image context information is proposed. According to the traditional markov random field (MRF) potential function, the method involves intensity Euclidean distance and spatial position information of pixels in the neighborhood of the image. Therefore, the traditional potential function of MRF segmentation method is improved. The segmentation is transformed into the problem of maximum a posteriori (MAP) which is solved by the iterative conditional model. And Kmeans is used to initialize the classification in the range of the specified classification numbers. The optimal class number is chosen according to the minimum message length (MML) criterion to complete an unsupervised segmentation. In the experiments, synthetic and real images are employed in segmentation procedure. Compared with other methods, the proposed algorithm is proved to be more effective.
[1] Mirmehdi M, Petrou M. Segmentation of Color Textures. IEEE Trans on Pattern Analysis and Machine Intelligence, 2000, 22(2): 142159 [2] Ohlander R, Price K, Reddy D R. Picture Segmentation Using a Recursive Region Splitting Method. Computer Graphics and Image Processing, 1978, 8(3): 313333 [3] Luo Xiping, Tian Jie, Zhuge Ying, et al. A Survey for Image Segmentation Methods. Pattern Recognition and Artificial Intelligence, 1999, 12(3): 300312 (in Chinese) (罗希平,田 捷,诸葛婴,等.图像分割方法综述.模式识别与人工智能, 1999, 12(3): 300312) [4] Tseng D C, Lai C C. A Genetic Algorithm for MRF Based Segmentation of MultiSpectral Textured Images. Pattern Recognition Letters, 1999, 20(14): 14991510 [5] Tu Zhuowen, Zhu Songchun. Image Segmentation by DataDriven Markov Chain Monte Carlo. IEEE Trans on Pattern Analysis and Machine Intelligence, 2002, 24(5): 657673 [6] Barker S A. Image Segmentation Using Markov Random Field Models. Ph.D Dissertation. Cambridge, UK: University of Cambridge. Department of Engineering, 1998 [7] Hurn M A, Mardia K V, Hainsworth T J, et al. Bayesian Fused Classification of Medical Images. IEEE Trans on Medical Imaging, 1996, 15(6): 850858 [8] Melas D E, Wilson S P. Double Markov Random Fields and Bayesian Image Segmentation. IEEE Trans on Signal Processing, 2002, 50(2): 357365 [9] Lei T H, Udupa J K. Performance Evaluation of Finite Normal Mixture ModelBased Image Segmentation Techniques. IEEE Trans on Image Processing, 2003, 12(10): 11531169 [10] Lei T H. Gibbs Ringing Artifact Spatial Correlation and Spatial Correlation in MRI. Proc of the SPIE, 2004, 5368: 837847
2008, Vol. 21 
