全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

FasART模糊神经网络用于遥感图象监督分类的研究

DOI: 10.11834/jig.2002012365

Keywords: 遥感图象,监督分类,隶属度函数,模糊神经网络,FasART,图象处理

Full-Text   Cite this paper   Add to My Lib

Abstract:

说明了遥感图象数据的非线性性质,目视的图象分类实践是一个模糊推理的过程,模糊神经网络遥感图象分类符合其事物的内在规律,具有理论优势,分析了模糊ART,模糊ARTMAP和FasART模型的结构和原理,详细地阐述了FasART是一种基于模糊逻辑系统的神经网络,提出了一种简化的FasART模型,改变了一般遥感数据的模糊化方法,采用中巴资源一号卫星数据进行测试实验,结果表明,该简化的FasART模型能用于遥感图象的监督分类,其分类精度高于模糊ARTMAP神经网络和K均值算法,且性能稳定,有较好的抗干扰能力,尤其具有良好的处理两组相似程度比较接近的,和同组数据模式变化较大的非线性数据的能力。

References

[1]  [2]Andrea Baraldi, Elisabetta Binaghi. Comparison of themultilayer perceptron with neuro-fuzzy techniques in the estimation of cover class mixture in remotely sensed data [J]. IEEE Trans. on Geosci. and Remote sensing, 2001, 39(5): 994~1005.
[2]  [4]Carpenter Gail A, Gjaja Marin N. ART neural networks for remote sensing: Vegetation classification from landsat TM and terrain data[J]. IEEE Trans. on Geosci. and Remote sensing, 1997,35(2) :308~325.
[3]  [6]José Manuel Cano Izquierdo, Dimitriadis Yannis A. Learning from noisy information in FasART and fasBack neuro-fuzzy systems[J]. Neural Networks, 2001,14 (5): 407~425.
[4]  [1]WANG FANGJU. Fuzzy supervised classification of remote sensing images [J]. IEEE Trans. on Geosci. and Remotesensing, 1990,28(2) :194~201.
[5]  [3]Bruzzone L, Prieto D F. A technique for the selection of kernel function parameters in RBF neural networks for classification of remote sensing images[J]. IEEE Trans. on Geosci. and Remote sensing, 1999,37(2 I ):1179~1184.
[6]  [5]Innocent P R, Barnes M, John R. Application of fuzzy ART (MAP) and MinMax (MAP) neural network to radiographic image classification [J ]. Artificial Intelligence in Medicine, 1997, (11):241~263.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133