势函数聚类自适应多阈值图像分割

ADAPTIVE MULTI THRESHOLDS IMAGE SEGMENTATION BASED ON POTENTIAL FUNCTION CLUSTERING

提出了一种新的有效的图像多阈值分割方法．该方法通过构造图像的势直方图，利用势函数聚类进行自适应多阈值分割．由于其划分函数是四次势基函数，因此该方法可等效为势基函数对直方图的最佳拟合．该方法是一种自动确定划分类数的非迭代方法，具有速度快、划分特性良好、鲁棒性强的优点．几个典型实验也证明了这一点．

A new effective multi thresholds image segmentation method based on potential function clustering is presented, which is characterized by its good partition peculiarity, low computing cost, strong robustness. The proposed method is equivalent to histogram optimal interpolation by four order basic potential function. Finally, four experiments have been given with satisfactory results.