一种改进的FCM图像分割算法

提出了一种基于高维特征矢量与金字塔结构的模糊聚类图像分割方法。该方法考虑了图像像点的灰度信息和其邻域空间相关信息，给出了三维特征及多分辨率分析的聚类分割方法。实验结果表明，在图像受高斯噪声干扰的情况下，该方法不仅运行速度较快，而且分割效果更好。

An Improved FCM Algorithm For Image Segmentation

In this paper, a fuzzy clustering method based on high-dimensional feature vector and the pyramid is presented for image segmentation. The three-dimensional features and Multi-resolution Analysis of the clustering segmentation method is given by considering gray-scale information of the image pixel and its neighborhood space-related information. Experimental resuhs show that the method not only run faster, but also has better segmentation results in the case of the image with Gaussian noise.