Share Email Print
cover

Proceedings Paper

A comparative study of several supervised classifiers for coconut palm tree fields' type mapping on 80cm RGB pansharpened Ikonos images
Author(s): R. Teina; D. Béréziat; B. Stoll; S. Chabrier
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The purpose of this study is to classify the types of coconut plantation. To this end, we compare several classifiers such as Maximum Likelihood, Minimum Distance, Parallelepiped, Mahalanobis and Support Vector Machines (SVM). The contribution of textural informations and spectral informations increases the separability of different classes and then increases the performance of classification algorithms. Before comparing these algorithms, the optimal windows size, on which the textural information are computed, as well as the SVM parameters are first estimated. Following this study, we conclude that SVM gives very satisfactory results for coconut field type mapping.

Paper Details

Date Published: 3 February 2009
PDF: 9 pages
Proc. SPIE 7251, Image Processing: Machine Vision Applications II, 72510X (3 February 2009); doi: 10.1117/12.805736
Show Author Affiliations
R. Teina, Univ. Pierre et Marie Curie (France)
D. Béréziat, Univ. Pierre et Marie Curie (France)
B. Stoll, Univ. de la Polynésie Française (French Polynesia)
S. Chabrier, Univ. de la Polynésie Française (French Polynesia)


Published in SPIE Proceedings Vol. 7251:
Image Processing: Machine Vision Applications II
Kurt S. Niel; David Fofi, Editor(s)

© SPIE. Terms of Use
Back to Top