结合mRMR选择和IFCM聚类的遥感影像分类算法

为解决高分影像特征间相关性大冗余度高、FCM聚类稳健性差带来的分类精度不佳问题，提出一种基于mRMR选择和改进FCM聚类的影像分类算法。首先基于对象置信度指标（OC）进行影像分割，然后利用mRMR算法实现特征选择，解决特征冗余问题，最后将提取的特征输入分类器通过IFCM聚类，得到最终分类结果。试验结果表明，本文算法能减少特征间相关性，降低冗余，并有效提高影像分类精度。

Remote sensing image classification algorithm based on mRMR selection and IFCM clustering

In order to solve the problem of poor classification precision caused by high correlation redundancy between features of high-resolution image and poor robustness of FCM clustering, an image classification algorithm based on mRMR selection and IFCM clustering is proposed. First, the image segmentation is carried out based on the object confidence index (OC), then the feature selection is realized by mRMR algorithm to solve the feature redundancy problem. The extracted feature is put in classifier and final classification result is clustered by IFCM algorithm. Comparison of experimental results show that the proposed algorithm can reduce feature correlation and redundancy and effectively improve image classification accuracy.