Many types of nonlinear classifiers have been proposed to automatically generate land-cover maps from satellite images. Some are based on the estimation of posterior class probabilities, whereas others estimate the decision boundary directly. In this paper, we propose a modular design
able to focus the learning process on the decision boundary by using posterior probability estimates. To do so, we use a self-configuring architecture that incorporates specialized modules to deal with conflicting classes, and we apply a learning algorithm that focuses learning on the posterior
probability regions that are critical for the performance of the decision problem stated by the user-defined misclassification costs. Moreover, we show that by filtering the posterior probability map, the impulsive noise, which is a common effect in automatic land-cover classification, can
be significantly reduced. Experimental results show the effectiveness of the proposed solutions on real multi- and hyperspectral images, versus other typical approaches, that are not based on probability estimates, such as Support Vector Machines.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
Document Type: Research Article
Dpto. de Teoria de la Senal y Comunicaciones, Campus de Fuenlabrada, Universidad Rey Juan Carlos, Fuenlabrada-Madrid, Spain
Dpto. de Ingenieria Electrica, Sistemas y Automatica, Campus de Vegazana, Universidad de Leon, Leon, Spain
Dpto. de Teoria de la Senal y Comunicaciones, EPS, Universidad Carlos III de Madrid, Leganes-Madrid, Spain
Publication date: 2009-01-01
More about this publication?