基于K-L变换的BP神经网络遥感图像分类  

BP neural network based on principle component analysis in multi-spectral remote sensing images classification

作　　者：胡剑策[1] 吴国平[1] 

机构地区：[1]中国地质大学机械与电子信息学院,武汉430074

出　　处：《测绘科学》2009年第3期137-139,共3页Science of Surveying and Mapping

摘　　要：为了提高多光谱遥感图像的分类正确,提出了一种基于主成分分析(K-L变换)的分类方法。该方法先应用K-L变换对多波段遥感图像进行降维,提取最主要的三个成分合成假彩色图,然后利用BP神经网络对假彩色图进行监督分类。由于主成分之间是不相关的,增强了图象信息,降低了神经网络的计算量,提高了分类精度。实验结果证明,该算法分类精度优于传统分类方法,总正确率为88.5%,Kappa系数为0.862,因而具有实用价值。In order to improve the classification accuracy of multi-spectral remote sensing image, this paper puts forward a new classification method based on principal component analysis. The method is consisted of two steps： reducing the dimensions of multispectral remote sensing image with principle component analysis and generating a new image by the three main components of the remote sensing image; performing supervised classification on the new image with BP neural network. The result indicates that this method is superior to traditional algorithms, and its overall accuracy and Kappa coefficient reach 88.5% and 0. 862.

关 键 词：K—L变换 BP神经网络 遥感图像 监督分类 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]