Share Email Print
cover

Proceedings Paper

Kernel methods for HyMap imagery knowledge discovery
Author(s): Gustavo Camps-Valls; Luis Gomez-Chova; Javier Calpe-Maravilla; Emilio Soria-Olivas; Jose D. Martin-Guerrero; Jose Moreno
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

In this paper, we propose a kernel-based approach for hyperspectral knowledge discovery, which is defined as a process that involves three steps: pre-processing, modeling and analysis of the classifier. Firstly, we select the most representative bands analyzing the surrogate and main splits of a Classification And Regression Trees (CART) approach. This yields three datasets with different reduced input dimensionality (6, 3 and 2 bands, respectively) along with the original one (128 bands). Secondly, we develop several crop cover classifiers for each of them. We use Support Vector Machines (SVM) and analyze its performance in terms of efficiency and robustness, as compared to multilayer perceptrons (MLP) and radial basis functions (RBF) neural networks. Suitability to real-time working conditions, whenever a preprocessing stage is not possible, is evaluated by considering models with and without the CART-based feature selection stage. Finally, we analyze the support vectors distribution in the input space and through Principal Component Analysis (PCA) in order to gain knowledge about the problem. Several conclusions are drawn: (1) SVM yield better outcomes than neural networks; (2) training neural models is unfeasible when working with high dimensional spaces; (3) SVM perform similarly in the four classification scenarios, which indicates that noisy bands are successfully detected and (4) relevant bands for the classification are identified.

Paper Details

Date Published: 5 February 2004
PDF: 10 pages
Proc. SPIE 5238, Image and Signal Processing for Remote Sensing IX, (5 February 2004); doi: 10.1117/12.510719
Show Author Affiliations
Gustavo Camps-Valls, Univ. de Valencia (Spain)
Luis Gomez-Chova, Univ. de Valencia (Spain)
Javier Calpe-Maravilla, Univ. de Valencia (Spain)
Emilio Soria-Olivas, Univ. de Valencia (Spain)
Jose D. Martin-Guerrero, Univ. de Valencia (Spain)
Jose Moreno, Univ. de Valencia (Spain)


Published in SPIE Proceedings Vol. 5238:
Image and Signal Processing for Remote Sensing IX
Lorenzo Bruzzone, Editor(s)

© SPIE. Terms of Use
Back to Top