Fisher和神经网络相融合的遥感图像分类  

Classification of Emote Sensing Image Based on Fisher-BP

作　　者：邓江洪[1] 赵领[1] 

机构地区：[1]黄淮学院,河南驻马店463000

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2016年第1期46-49,共4页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：2013河南省科技攻关项目(132102210423);2012河南省科技攻关项目(122102210549)

摘　　要：针对遥感图像分类方法存在的不足,提出一种基于Fisher-BP的遥感图像分类方法.把收集到的遥感图像数据进行相应的处理,从中提取遥感图像特征,用Fisher方法对图像特征进行选择,然后用BP神经网络构建遥感图像分类器,并用遗传算法优化BP神经网络的参数.应用实例表明,相对其他遥感图像分类方法,Fisher-BP提高了遥感图像的分类效率和分类正确率,而且分类速度更快.In order to solve the problems existing in the current remote sensing image classification method,this paper put forward a remote sensing image classification method based on Fisher-BP.Remote sensing images are collected and treated corresponding;and then the features of remote sensing images are extracted and selected by using Fisher＇s method,the BP neural network is used to build remote sensing image classifier,and genetic algorithm is used to optimize the parameters of BP neural network.Experimental results show that compared with other remote sensing image classification methods,Fisher-BP improves the classification efficiency and classification accuracy of remote sensing images,and the classification speed is faster.

关 键 词：遥感图像 图像特征 分类器 分类精度 神经网络参数 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]