【作者】 万永菁； 杨大毛；

【Author】 WAN Yong-jing YANG Da-mao College of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, P.R.China

【机构】 华东理工大学信息科学与工程学院；

【摘要】 提出了一种基于邻域空间信息的模糊c均值聚类图像分割算法,算法基于像点邻域空间信息修正模糊隶属度函数,从而获得合理聚类中心。对一组含有不同类型噪声的pepper图像应用FCM算法和改进的FCM算法进行了仿真实验,比较和分析不同算法的聚类有效性。针对纤维增强复合材料微观结构图像应用不同算法进行图像分割实验,实验结果证明改进的基于空间信息的FCM具有对噪声不敏感的特点,能获得更好的图像分割结果。更多还原

【Abstract】 A Fuzzy c means clustering (FCM) image segmentation algorithm based on neighborhood spatial information is proposed in the paper. The fuzzy membership degree function is modified based on spatial information and the reasonable clustering centers are acquired accordingly. A group of simulation experiments about pepper image with different kinds of noise are performed using FCM algorithm and the improved algorithm. The clustering validity is compared and analyzed in the paper. Aiming at the image segmentation of fiber-reinforced composite microstructure image, FCM algorithm and the proposed algorithm are used to compare the segmentation results in the paper. According to the results, it can be proved that the proposed algorithm has the advantage of not sensitivity to noise and can get better segmentation results.更多还原