Comparison and visualization of feature space behaviour of statistical and neural classifiers of satellite imagery

Comparison and visualization of feature space behaviour of statistical and neural classifiers of satellite imagery

Currently both statistical and neural classifiers are being used for the classification of multispectral satellite imagery. Because both classifier types are being used as 'black boxes' and because they are values based on different mathematical models the reasons for their different perfo...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings of IGARSS '94 - 1994 IEEE International Geoscience and Remote Sensing Symposium Vol. 4; pp. 1880 - 1882 vol.4
Main Authors: Fierens, F., Kanellopoulos, I., Wilkinson, G.G., Megier, J.
Format: Conference Proceeding
Language:English
Published: IEEE 1994
Subjects:
Data mining
Data visualization
Electronic mail
Expert systems
Mathematical model
Neural networks
Remote sensing
Satellites
Testing
Three dimensional displays
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Currently both statistical and neural classifiers are being used for the classification of multispectral satellite imagery. Because both classifier types are being used as 'black boxes' and because they are values based on different mathematical models the reasons for their different performance levels are not well understood. The authors have used visualization of class decision boundaries in feature space as a means to gain insight into the classification processes.< >
ISBN:0780314972
9780780314979
DOI:10.1109/IGARSS.1994.399600