摘要
提出一种基于Markov随机场图像分割方法。在K-Means图像分割的基础上,建立标记场和特征场,构造Markov随机场模型,再利用条件迭代模型(ICM)算法逐点更新图像标记,实现图像的最大后验概率(MAP)估计,从而实现图像的有效分割。实验结果表明,该方法比直接采用Markov方法有着更好的分割效果。
An image segmentation method based on Markov radom field was discussed.On the basis of K-Means image segmentation,the labeling field and the feature field were built,Markov radon field model was constructed.With the iterated conditional model（ICM） algorithm the labels of the image were updated,the maximum posteriori（MAP） was estimated.Experimental results show that the segmentation effect of the proposed method is better than that of the Markov method.
出处
《安徽工业大学学报（自然科学版）》
CAS
2012年第3期252-255,共4页
Journal of Anhui University of Technology（Natural Science）
基金
国家自然科学基金项目(61003311)
关键词
图像分割
MARKOV随机场
条件迭代模型
最大后验概率
image segmentation
Markov random field
iterated conditional model
maximum posteriori probability
