【摘要】 提出了一种新的基于二型模糊可能性聚类的红外图像分割算法。针对受概率约束的模糊聚类算法和不受概率约束的可能性聚类算法在红外图像分割时存在的问题,采用二型模糊系统融合两种分割算法的隶属度函数,将隶属度函数看作一个区间型分布,而不是单独采用两种算法输出的确定模糊值。这种处理方式不但能有效抑制噪声及野值,而且能有效防止红外图像的过分割。实验仿真结果表明,该算法较传统聚类算法能获得更好的分割效果,可有效抑制噪声对目标区域分割的干扰。更多还原

【Abstract】 A new algorithm for infrared image segmentation using type-2 fuzzy possibilistic clustering is proposed.Due to the problems of fuzzy clustering and possibilistic clustering in infrared image segmentation,the type-2 fuzzy is used to fuse the membership function of the two segmentation algorithms.The membership function is an interval distribution.The determined fuzzy values which are the output of the two algorithms are not adopted now.This processing method not only can suppress the noise and the outliers,but also can prevent the over segmentation of infrared image.The experimental results show the infrared image can be segment well by the proposed method compared with the conventional clustering method,and the noise and outliers are prevented to influence the segmentation of targets region.更多还原