摘要
针对传统的模糊C均值聚类算法未考虑图像的空间信息,对噪声图像分割不理想,提出了一种结合空间信息的模糊C均值聚类的图像分割算法。此算法充分考虑像素的邻域特性,对隶属度函数做一定的修改,并将局部信息和非局部信息引入到数据和聚类中心的相异性测度中。实验结果表明,该算法能有效地分割图像,并具有较好的抗噪能力。
The conventional fuzzy C means clustering algorithm couldn＇t consider any spatial information,and it is no good to noise image segmentation.In order to overcome this shortcoming,a fuzzy C-means clustering algorithm using spatial information for image segmentation was proposed.The new algorithm could make full use of pixel＇s neighborhood feature by improving the membership function,furthermore local information and non local information were introduced in dissimilarity of data and clustering center.Experimental results show that this method is effective in image segmentation,and has better performance of resisting noise.
出处
《辽宁石油化工大学学报》
CAS
2010年第4期51-53,共3页
Journal of Liaoning Petrochemical University
基金
辽宁省教育厅资助项目(2008380)
关键词
模糊C均值
聚类
图像分割
Fuzzy C-means
Clustering
Image segmentation
