模糊马尔可夫场模型与图像分割新算法

被引:7
作者
冯前进
陈武凡
机构
[1] 南方医科大学生物医学工程学院医学图像处理重点实验室
关键词
模糊随机变量; 模糊马尔可夫场; 图像分割; 最大伪似然;
D O I
暂无
中图分类号
TP391.41 [];
学科分类号
080203 ;
摘要
本文建立模糊马尔可夫场模型,并提出基于模糊马尔可夫场的图像分割新算法。该算法同时处理模糊性和随机性,因此能有效获取图像的先验知识。在模糊马尔可夫场与待分割图像之间用经典的马尔可夫场关联。模糊马尔可夫场是经典马尔可夫场的推广,当模糊马尔可夫场失去模糊性时,它将退化为经典的马尔可夫场。给定图像,随即进行模糊化处理;以最大后验概率作为优化准则修正模糊马尔可夫场的隶属度;最后按照最大隶属度原则消除模糊性,从而得到图像的分割。该算法可以有效地虑除噪和消除部分容积效应,得到更为准确的分割结果。
引用
收藏
页码:579 / 583
页数:5
相关论文
共 10 条
[1]  
Soft image segmentation by weighted linked pyramid. Prewer D,Kitchen LJ. Pattern Recognition . 2001
[2]  
PATTERN RECOGNITION[P]. RINGLAND SIMON PATRICK ALEXAND;TALINTYRE JOHN EDWARD.EP0917708B1,2002-03-27
[3]  
Markov random field modeling in image analysis. Li SZ. . 2001
[4]  
Knowledge-based segmentation and labeling of brain structures from MRI images. Xue JH,Ruan S,Moretti B,et al. Pattern Recognition . 2001
[5]  
Fuzzy random variables-I,definition and theorems. Kwakernaak H. Journal of Information Science . 1978
[6]  
Segmentation of brain images through a hidden Markov random field model and the expectation-ma-ximization algorithm. Zhang Y,Brady M,Smith S. IEEE Transactions on Medical Imaging . 2001
[7]  
Unsupervised multistage image classification using hierarchical clustering with a bayesian similarity measure. Lee S,Crowford MM. IEEE Transactions on Image Processing . 2005
[8]  
A Modified fuzzy c-means algorithms for bias field estimation and segmentation of MRI data. Ahmed MN,Yamany SM. IEEE Transactions on Medical Imaging . 2002
[9]  
SLIDE:A simple adaptive defuzzification method. Yager R,Filev D. IEEE Transactions on Fuzzy Systems . 1993
[10]  
SLIDE:A simple adaptive defuzzification method. Yager R,Filev D. IEEE Transactions on Fuzzy Systems . 1993