基于改进模糊核聚类的红外图像分割

Infrared Image Segmentation Based on Improved Fuzzy Kernel Clustering

针对传统模糊核聚类在红外图像分割方面存在的问题,提出了一种改进的模糊核聚类红外图像分割算法。在模糊核聚类的基础上引入了红外图像像素点的空间约束关系和邻域隶属度相关性,并定义了隶属度约束强度指数修正隶属度函数,可有效抑制红外图像分割结果中的噪声和野值。实验结果表明,与传统的分割结果相比,这种考虑邻域隶属度相关性的空间约束模糊核聚类算法可有效地对红外图像进行分割,准确完整地分割出了目标,达到了令人满意的结果。

Due to the problems to infrared image segmentation using fuzzy kernel clustering, an improved method for infrared image segmentation based on fuzzy kernel clustering was proposed. The pixel＇s spatial restriction and the membership relation of neighbor- hood were added in the base of fuzzy kernel clustering. And a intensity index of membership restriction was defined to revise the de- gree of membership. The experimental results show the infrared image can be segment well by the proposed method compared with the conventional method. The segmentation results were satisfied.