基于Wishart分类器和图谱聚类的极化SAR图像分类

Polarimetric SAR Images Based on Spectral Clustering and Wishart Classifier

针对极化SAR的Wishart分类器存在的问题和具有的特点,本文提出一种基于Wishart分类器的图谱聚类的极化SAR图像分类方法.该方法充分考虑了极化SAR数据的统计特征和图像上的复杂几何结构特征,在采用Wishart分类器进行初始分类的基础上,运用图谱聚类进行极化SAR图像的分类.实验结果表明,与仅用Wishart分类器和图谱聚类对极化SAR数据进行分类相比,该方法具有更好的分类效果.

Aiming at the existent problems and characteristics of the wishart classifier of the polarimetricc SAR, a classification method of polarimetric SAR images based on the spectrial clustering of wishart classifier is presented in this paper. The statistical characteristics and structure characteristics of complex geometry in image of the polarimetric SAR are fully considered in this method. Based on the imitial classification of the wishart classifier, the classification of the polarimetric SAR images using spectrical clustering are used.