A New Methodology for Efficient Classification of MultispectralSatellite Images Using Neural Network Techniques

Authors:
Nikolaos Vassilas;Eleni Charou
Affiliations:
National Research Center ’Demokritos‘, Institute of Informatics and Telecommunications, 153 10 Agia Paraskevi, Attiki, Greece. E-mail: nvas@iit.nrcps.ariadne-t.gr;National Research Center ’Demokritos‘, Institute of Informatics and Telecommunications, 153 10 Agia Paraskevi, Attiki, Greece. E-mail: nvas@iit.nrcps.ariadne-t.gr
Venue:
Neural Processing Letters
Year:
1999

Citing 3
Cited 2

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Modified self-organizing feature map algorithms for efficient digital hardware implementation

IEEE Transactions on Neural Networks

Content-Based coin retrieval using invariant features and self-organizing maps

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II
An application of neural and probabilistic unsupervised methods to environmental factor analysis of multi-spectral images

ICIAP'05 Proceedings of the 13th international conference on Image Analysis and Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A methodology based on self-organizing feature maps and indexing techniquesfor time and memory efficient neural network training and classification oflarge volumes of remotely sensed data is presented. Results on land-coverclassification of multispectral satellite images using two popular neuralmodels show orders of magnitude of speedup with respect to both trainingand classification times. The generality of the proposed methodology isdemonstrated with a dramatic improvement of the classification time ofthe k-nearest neighbors statistical classifier.