Unsupervised retraining of a maximum likelihood classifier for the analysis of multitemporal remote sensing images

An unsupervised retraining technique for a maximum likelihood (ML) classifi er is presented. The proposed technique allows the classifier's parameters, obtained by supervised learning on a specific image, to be updated in a to tally unsupervised way on the basis of the distribution of a new image to b e classified. This enables the classifier to provide a high accuracy for th e new image even when the corresponding training set is not available.