【摘要】 针对传统的模糊C均值(FCM)算法在图像分割方面存在的缺点,提出一种基于空间信息及隶属度约束的FCM图像分割算法.该算法在传统FCM算法的目标函数中引入图像空间信息及对隶属度的约束,使得到的聚类中心更加合理,并且增强了算法对噪音的鲁棒性.实验结果表明,本算法可以有效地提高图像分割的质量.更多还原

【Abstract】 To overcome the disadvantages of traditional fuzzy C-means(FCM) algorithm in image segmentation,by integrating the local spatial information and membership constraints,an improved FCM algorithm was proposed.Compared with the existing fuzzy clustering algorithms,this method was robust to noises,and more sensible clustering centers could be obtained.Simulation results show that the proposed algorithm can effectively improve the segmentation quality.更多还原