摘要
近年来,随着人工神经网络系统理论的发展,神经网络技术日益成为遥感数字图像分类处理的有效手段。但是该方法不能降低维数、时间开销大,针对这些不足提出一种基于粗糙集约简的神经网络方法。本文对RapidEye影像进行分析并提取纹理特征,利用粗糙集理论对纹理特征与光谱特征属性进行约简,得到的约简属性作为输入属性,利用神经网络法对影像分类。结果表明该方法具有较好的分类精度。
In the last few years,the artificial neural network technology has increasingly become an effective tool in remote sensing image classification.However,this method can not reduce the dimension and waste of time.In response to these deficiencies a neural network based on rough sets reduction and its application to remote sensing image classification are proposed.This paper analyzes the satellite image of Rapideye：the texture feature extraction,rough set theory attribute reduction according to texture feature and spectral characteristics,and using it as input attribute,and using the neural network method to classify the remote sensing image.According to the experiment results,this method has fairly classification precision.
出处
《遥感信息》
CSCD
2012年第4期86-90,74,共6页
Remote Sensing Information
关键词
神经网络
粗糙集
约简
分类
neural network
rough sets
reduction
classification
