利用分维向量改进神经网络在遥感模式识别中的分类精度

章杨清; 刘政凯

doi:10.11834/jrs.1994010

浏览量 : 0 下载量: 506 CSCD: 98

PDF
导出
分享
收藏
专辑

利用分维向量改进神经网络在遥感模式识别中的分类精度
Accuracy Improving of Neural Network Classification for Remotely-sensed Data by Using of Fractal Dimension
1994年第1期
纸质出版：1994
DOI： 10.11834/jrs.1994010
稿件说明：

移动端阅览

[1]章杨清,刘政凯.利用分维向量改进神经网络在遥感模式识别中的分类精度[J].环境遥感,1994(01):68-72. DOI： 10.11834/jrs.1994010.

Accuracy Improving of Neural Network Classification for Remotely-sensed Data by Using of Fractal Dimension[J]. Journal of Remote Sensing, 1994, (1). DOI： 10.11834/jrs.1994010.

摘要

本文介绍了基于ＢＰ神经网络的遥感模式识别方法的特点，同时引入分形维数的概念及其在图像中的计算和应用，并将分维作为反映各类别数据纹理特征的附加波段分量，加到网络的输入层，明显地提高了分类精度。

Abstract

This paper has presented a classification method of remotely-sensed Ima-ge data based on BP neural network

and introduced the concept of fractal dimensionwhich describes image texture suitably;The approach is also given for calculatingfractal dimension applied in image field.Finally

fractal dimension is adopted astbe additional sector of input vectors in neural network

which has greatly improvedclassification accuracy.