基于领域灰度的模糊C均值图像分割算法  

A new Fuzzy C-means algorithm based on gray value compensation and spatial information for aeral image segmengtation

作　　者：路彬彬[1] 贾振红[1] 杨杰[2] 胡英杰 

机构地区：[1]新疆大学信息科学与工程学院,新疆乌鲁木齐830046 [2]上海交通大学图像处理与模式识别研究所,上海200240 [3]新西兰奥克兰理工大学知识工程与开发研究所

出　　处：《光电子．激光》2011年第3期469-473,共5页Journal of Optoelectronics·Laser

基　　金：科技部国际科技合作资助项目(2009DFA12870);教育部促进与美大地区科研合作与高层次人才培养项目

摘　　要：模糊C均值(FCM)聚类算法对图像局部灰度值不均匀和噪声十分敏感,提出一种基于像素点灰度补偿校正和邻域信息的FCM新算法。通过预先假定像素点存在加性或乘性噪声,再将像素点的邻域信息引入到噪声模型,经反复迭代调整像素点的噪声值直至最优。在FCM反复迭代的过程中,对算法进行上下截集半模糊化处理,从而提高分类的速率和准确率。实验结果表明,本文算法对局部灰度值不均匀区域有较好的补偿作用,能有效地抑制噪声,分割质量明显提高,运算速度较标准FCM和MFCM算法更快。The fuzzy C-means（FCM） clustering algorithm has been proven to be effective for image segmentation.However,the standard FCM algorithm is sensitive to noise and gray inhomogeneity.An improved FCM-based algorithm is proposed in this paper,which firstly modeled the noise of an image as a slowly varying additive or multiplicative noise and iteratively approximate the gray inhomogeneity and noise areas by using the spatial neighborhood information.In this process,the threshold values of up and down cut-off were applied to adjust different memberships of pixel.The experimental results on the segmentation demonstrate that the algorithm performs more robust to noise than the standard FCM algorithm and MFCM algorithm.

关 键 词：模糊C均值(FCM) 灰度不均匀 聚类 空间信息 航拍图像 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]