In this article, a hierarchical classifier is proposed for classification of ground-cover types of a satellite image of Kangaroo Island, South Australia. The image contains seven ground-cover types, which are categorized into three groups using principal component analysis. The first group contains clouds only, the second consists of sea and cloud shadow over land, and the third contains land and three types of forest. The sea and shadow over land classes are classified with 99% accuracy using a network of threshold logic units. The land and forest classes are classified by multilayer perceptrons (MLPs) using texture features and intensity values. The average performance achieved by six trained MLPs is 91%. In order to improve the classification accuracy even further, the outputs of the six MLPs were combined using several committee machines. All committee machines achieved significant improvement in performance over the multilayer perceptron classifiers, with the best machine achieving over 92% correct classification.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Abdesselam BOUZERDOUM, "A Hierarchical Classifier for Multispectral Satellite Imagery" in IEICE TRANSACTIONS on Electronics,
vol. E84-C, no. 12, pp. 1952-1958, December 2001, doi: .
Abstract: In this article, a hierarchical classifier is proposed for classification of ground-cover types of a satellite image of Kangaroo Island, South Australia. The image contains seven ground-cover types, which are categorized into three groups using principal component analysis. The first group contains clouds only, the second consists of sea and cloud shadow over land, and the third contains land and three types of forest. The sea and shadow over land classes are classified with 99% accuracy using a network of threshold logic units. The land and forest classes are classified by multilayer perceptrons (MLPs) using texture features and intensity values. The average performance achieved by six trained MLPs is 91%. In order to improve the classification accuracy even further, the outputs of the six MLPs were combined using several committee machines. All committee machines achieved significant improvement in performance over the multilayer perceptron classifiers, with the best machine achieving over 92% correct classification.
URL: https://global.ieice.org/en_transactions/electronics/10.1587/e84-c_12_1952/_p
Copy
@ARTICLE{e84-c_12_1952,
author={Abdesselam BOUZERDOUM, },
journal={IEICE TRANSACTIONS on Electronics},
title={A Hierarchical Classifier for Multispectral Satellite Imagery},
year={2001},
volume={E84-C},
number={12},
pages={1952-1958},
abstract={In this article, a hierarchical classifier is proposed for classification of ground-cover types of a satellite image of Kangaroo Island, South Australia. The image contains seven ground-cover types, which are categorized into three groups using principal component analysis. The first group contains clouds only, the second consists of sea and cloud shadow over land, and the third contains land and three types of forest. The sea and shadow over land classes are classified with 99% accuracy using a network of threshold logic units. The land and forest classes are classified by multilayer perceptrons (MLPs) using texture features and intensity values. The average performance achieved by six trained MLPs is 91%. In order to improve the classification accuracy even further, the outputs of the six MLPs were combined using several committee machines. All committee machines achieved significant improvement in performance over the multilayer perceptron classifiers, with the best machine achieving over 92% correct classification.},
keywords={},
doi={},
ISSN={},
month={December},}
Copy
TY - JOUR
TI - A Hierarchical Classifier for Multispectral Satellite Imagery
T2 - IEICE TRANSACTIONS on Electronics
SP - 1952
EP - 1958
AU - Abdesselam BOUZERDOUM
PY - 2001
DO -
JO - IEICE TRANSACTIONS on Electronics
SN -
VL - E84-C
IS - 12
JA - IEICE TRANSACTIONS on Electronics
Y1 - December 2001
AB - In this article, a hierarchical classifier is proposed for classification of ground-cover types of a satellite image of Kangaroo Island, South Australia. The image contains seven ground-cover types, which are categorized into three groups using principal component analysis. The first group contains clouds only, the second consists of sea and cloud shadow over land, and the third contains land and three types of forest. The sea and shadow over land classes are classified with 99% accuracy using a network of threshold logic units. The land and forest classes are classified by multilayer perceptrons (MLPs) using texture features and intensity values. The average performance achieved by six trained MLPs is 91%. In order to improve the classification accuracy even further, the outputs of the six MLPs were combined using several committee machines. All committee machines achieved significant improvement in performance over the multilayer perceptron classifiers, with the best machine achieving over 92% correct classification.
ER -