Matlab自组织神经网络在遥感图像分类中的应用
he Application of Self-organizing neural network in Remote sensing image Classification based on Matlab
以Matlab5.3平台为基础，利用神经网络工具箱构建了自组织神经网络，对一幅TM432假彩色遥感图象，通过500次训练后，仿真输出能真实的反映原始图像的特征。其分类总精度为87.14%，Kappa系数为0.85，分类精度能够满足遥感图象分类的需要。
self-organization aritifical neural net was created based on the neural net tools box of Matlab5.3 in this study. applied this net, a LandSat TM432 false color composition image was trained 300 times and got a satisfactory result when simulate it. the total precision of classification is 87.14% and Kappa coefficient is 0.85, it show that the precision of classification can meet the demand of remote sensing image classification.
杜华强
遥感技术
Matlab自组织神经网络分类Kappa系数
MatlabSelf-organization aritifical neural netClassificationKappa coefficient
杜华强.Matlab自组织神经网络在遥感图像分类中的应用[EB/OL].(2004-02-02)[2025-08-10].http://www.paper.edu.cn/releasepaper/content/200401-104.点此复制
评论