A new approach to pattern recognition of remote sensing image using artificial neural network

Author

Li, Houqiaug ; Liu, Zhengkai ; Sun, Weidong

Author_Institution

Dept. of Radio & Electron., Univ. of Sci. & Technol. of China, Hefei, China

fYear

1993

fDate

18-21 Aug 1993

Firstpage

713

Abstract

The performance is analyzed of Multilayered Neural Networks (MLNs) and its training rule-back propagation (BP) algorithm. Some new methods are used to improve its training speed and to avoid local minima. Spatial information is introduced into pattern recognition of remote sensing image using MLNs. The authors use three-layer modified MLNs as classifiers in pattern recognition of remote sensing images (Landsat-4 TM Data). The experimental results verify the usefulness of the approach

Keywords

geophysical techniques; geophysics computing; image recognition; neural nets; remote sensing; Landsat-4; MLN; Multilayered Neural Network; artificial neural network; classifier; geophysical measurement technique; image classification; land surface imaging; local minima; multispectral optical; pattern recognition; remote sensing; training rule back propagation algorithm; training speed; Artificial neural networks; Image analysis; Image recognition; Neural networks; Paper technology; Pattern analysis; Pattern recognition; Remote sensing; Shape; Sun;

fLanguage

English

Publisher

ieee

Conference_Titel

Geoscience and Remote Sensing Symposium, 1993. IGARSS '93. Better Understanding of Earth Environment., International

Conference_Location

Tokyo

Print_ISBN

0-7803-1240-6

Type

conf

DOI

10.1109/IGARSS.1993.322236

Filename

322236