Support Vector classifiers for Land Cover Classification
Neural and Evolutionary Computing
2009-11-13 v1 Computer Vision and Pattern Recognition
Abstract
Support vector machines represent a promising development in machine learning research that is not widely used within the remote sensing community. This paper reports the results of Multispectral(Landsat-7 ETM+) and Hyperspectral DAIS)data in which multi-class SVMs are compared with maximum likelihood and artificial neural network methods in terms of classification accuracy. Our results show that the SVM achieves a higher level of classification accuracy than either the maximum likelihood or the neural classifier, and that the support vector machine can be used with small training datasets and high-dimensional data.
Cite
@article{arxiv.0802.2138,
title = {Support Vector classifiers for Land Cover Classification},
author = {Mahesh Pal and Paul M. Mather},
journal= {arXiv preprint arXiv:0802.2138},
year = {2009}
}
Comments
11 pages, 1 figure, Published in MapIndia Conference 2003