[1]程显毅,巩向普.改进的模糊C-均值算法在医学图像分割中的应用[J].智能系统学报,2010,5(1):80-84.
CHENG Xian-yi,GONG Xiang-pu.An improved fuzzy Cmeans algorithm for segmentation of medical images[J].CAAI Transactions on Intelligent Systems,2010,5(1):80-84.
点击复制
《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷:
5
期数:
2010年第1期
页码:
80-84
栏目:
学术论文—机器学习
出版日期:
2010-02-25
- Title:
-
An improved fuzzy Cmeans algorithm for segmentation of medical images
- 文章编号:
-
1673-4785(2010)01-0080-05
- 作者:
-
程显毅,巩向普
-
南通大学 计算机科学与技术学院,江苏 南通 226019
- Author(s):
-
CHENG Xian-yi, GONG Xiang-pu
-
School of Computer Science and Technology, Nantong University, Nantong 226019, China
-
- 关键词:
-
蚁群算法; 医学图像分割; 模糊C均值聚类; 遗传算法
- Keywords:
-
ant colony algorithm; medical image segmentation; fuzzy Cmeans clustering; genetic algorithm
- 分类号:
-
TP391
- 文献标志码:
-
A
- 摘要:
-
针对随机选取聚类中心易使得迭代过程陷入局部最优解的缺点,提出了一种混合优化蚁群和动态模糊C均值的图像分割方法,该方法利用蚁群算法较强处理局部极值的能力,并能动态确定聚类中心和数目.针对传统的分阶段结合遗传算法和蚁群算法的策略存在收敛速度慢,聚类精度差的问题,提出在整个优化过程综合遗传算法和蚁群算法,并在蚁群算法中引入拥挤度函数,利用遗传算法的快速性、全局收敛性提高了蚁群算法的收敛速度,同时利用蚁群算法的并行性和正反馈性提高了聚类的精确度.最后将该算法应用到医学图像分割,对比实验表明,混合算法具有很强的模糊边缘和微细边缘分割能力.
- Abstract:
-
Stochastic selection of a clustering center would cause the iterative process to become trapped in a local extremum. To overcome this image segmentation problem, a hybrid method was proposed. It combined an ant colony algorithm with dynamic fuzzy clustering analysis. Thus the superior ability of the ant colony algorithm became available for dealing with local extrema. The resulting algorithm dynamically determined the number of clusters as well as clustering centers. Within the optimization procedure, we introduced a crowd degree function to improve the convergence rate. In addition, the parallelism and positive feedback effect of ant colony algorithm were employed to increase clustering precision. The proposed algorithm was used in the segmentation of medical images. A series of comparative experiments showed that the algorithm has improved ability to detect fuzzy or thin edges.
更新日期/Last Update:
2010-03-31