基于Fuzzy c-means算法聚类有效性函数的纹理分割

Texture Segmentation Based on Clustering Validity Function for Fuzzy c-means Algorithm

Fuzzyc means(FCM)算法用于图像分割是一种非监督模糊聚类后再标定的过程.本文利用聚类有效性函数对Fuzzyc means算法的聚类结果进行评价,从而获得最优的聚类结果,较好地解决了Fuzzyc means算法的一些不足,如聚类数目无法自动确定、其聚类结果是否最优.最后,利用纹理图像分割实验验证了该算法的有效性.

It is a procedure of the label following an unsupervised fuzzy clustering that Fuzzy c-means (FCM) algorithm is applied to image segmentation. In this paper, cluster validity function is used to evaluate the goodness of clustering so that optimal segmentation result is obtained, which conquers some deficiencies encountered in the algorithm, for example, the number of clustering can not be determined automatically and whether its clustering is optimal. This algorithm is evaluated by texture segmentation experiments.