Share Email Print

Optical Engineering

Feature extraction and pattern classification of remote sensing data by a modular neural system
Author(s): Palma N. Blonda; Vincenza la Forgia; Guido Pasquariello; Giuseppe Satalino
Format Member Price Non-Member Price
PDF $20.00 $25.00

Paper Abstract

A modular neural network architecture has been used for the classification of remote sensed data in two experiments carried out to study two different but rather usual situations in real remote sensing applications. Such situations concern the availability of high-dimensional data in the first setting and an imperfect data set with a limited number of features in the second. The learning task of the supervised multilayer perceptron classifier has been made more efficient by preprocessing the input with unsupervised neural modules for feature discovery. The linear propagation network is introduced in the first experiment to evaluate the effectiveness of the neural data compression stage before classification, whereas in the second experiment data clustering before labeling is evaluated by the Kohonen self–organizing feature map network. The results of the two experiments confirm that modular learning performs better than nonmodular learning with respect to both learning quality and speed.

Paper Details

Date Published: 1 February 1996
PDF: 7 pages
Opt. Eng. 35(2) doi: 10.1117/1.600898
Published in: Optical Engineering Volume 35, Issue 2
Show Author Affiliations
Palma N. Blonda, Istituto Elaborazione Segnali ed Immagini (Italy)
Vincenza la Forgia, Istituto Elaborazione Segnali ed Immagini (Italy)
Guido Pasquariello, Istituto Elaborazione Segnali ed Immagini (Italy)
Giuseppe Satalino, Istituto Elaborazione Segnali ed Immagini (Italy)

© SPIE. Terms of Use
Back to Top