直方图模糊约束FCM聚类自适应多阈值图像分割

Adaptive Multi Thresholds Image Segmentation Based on Fuzzy Restrainted Histogram FCM Clustering

本文提出了一种新的有效的图像多阈值分割方法．该方法通过对模糊约束直方图目标函数的优化．获得一个最佳模糊约束Ｃ划分，根据最大隶属度原则进行图像多阈值化．文中对得到的模糊划分函数进行了分析，同时还讨论了直方图划分类数的自适应确定问题．最后给出了几个典型的实验．理论分析和实验表明了本文方法具有速度快、划分特性良好。

A new effective multi thresholds image segmentation method based on Fuzzy Restrainted Histogram FCM Clustering is presented,which is characterized by its good partition peculiarity,low computing cost and strong robustness.The analysis of its optimal partition function is given,and how to adaptively detemine segmentation class number is discussed.Finally,four experiments have been given with satisfactory results.