An approach to feature selection and classification of remote sensing images based on the Bayes rule for minimum cost

Classification of remote-sensing images icr usually carried out by using ap proaches aimed at minimizing the overall error affecting land-cover maps. H owever, in several remote-sensing problems, it could be useful to perform c lassification by taking into account the different consequences (and hence the different costs) associated with each kind of error. This allows one to obtain land-cover maps in which the total classification cost involved by errors is minimized, instead of the overall classification error. To this e nd, in this paper, an approach to feature selection and classification of r emote-sensing images based on the Bayes rule for minimum cost (BRMC) is pro posed. In particular, a feature-selection criterion function is presented t hat permits one to select the features to be given as input to a classifier by taking into account the different cost associated with each confused pa ir of land-cover classes. Moreover, a classification technique based on the BRMC and implemented by using a neural network is described. The results o f experiments carried out on a multisource data set concerning the Island o f Elba (Italy) point out the ability of the proposed minimum cost approach to produce land-cover maps in which the consequences of each kind of error are considered.