基于欧氏空间距离的加强模糊C均值聚类方法

Enhanced fuzzy C-means clustering method based on Euclidean space distance

针对利用加强的模糊C均值(En FCM)聚类算法进行图像分割时未利用图像空间信息,造成算法对椒盐噪声敏感、分割结果不准确的问题,提出了一种基于欧氏空间距离的聚类方法。将图像中邻域像素到中心像素欧氏空间距离的倒数作为权重与邻域像素加权,引入图像的邻域和空间信息;将所得结果与中心像素求和,对原始图像滤波;在图像的灰度直方图上进行聚类运算,得到分割结果。引入了欧氏空间距离的滤波函数,同时考虑了图像的邻域信息和空间信息,有效抑制了聚类过程中噪声的影响。实验结果表明:与En FCM算法相比,提出的方法对椒盐噪声鲁棒性更好,可获得更为理想的分割结果。

Using the enhanced fuzzy C-means（ En FCM） clustering algorithm for image segmentation can greatly improve the efficiency of the algorithm. However,due to lack of using spatial information of the image,results in En FCM algorithm is more sensitive to the salt and pepper noise,and the segmentation results are not accurate. So an En FCM clustering method based on Euclidean space distance is proposed. The reciprocal of the Euclidean space distance of neighbor pixels and to central pixel in image acts as weight for weighing with neighbor pixel,to introduce spatial and neighbor information. Result is summed with the central pixel to filter the original image.Clustering operation is carried out on gray histogram of image,get the segmentation result. Filtering function of Euclidean space distance is introduced,not only consider neighborhood information,but also spatial information at the same time,and effectively suppress the influence of noise in the clustering process. The experimental results show that,comparing with En FCM algorithm,the proposed method is more robust to the salt and pepper noise and more ideal segmentation result can be obtained.