An experimental comparison of neural networks for the classification of multisensor remote-sensing images

Reports the results of an investigation into the use of different neural models for the supervised classification of a multisensor (optical and radar) data set. The authors evaluated the performances of two well-known types of neural classifiers (i.e., MLPs, and probabilistic neural networks (PNNs)) and compared them with the performances of the structured neural networks (SNNs) proposed earlier. Further comparisons with the k-nearest neighbour classifier were also made in order to evaluate the validity of the considered neural networks as alternative classifiers to classical statistical ones.