Analysis of multispectral urban images using adaptive resonance theory

Multispectral images of an urban environment are analyzed and interpreted by means of a neural network approach. In particular, the advantages found by using an adaptive resonance theory network of the data are shown and commented on. The author uses the ART2 structure which accepts floating-point data, so that each input can be for each pixel gray level values at each band. This choice is an attempt to simplify the algorithm as much as possible. Experiments carried out with JERS-1 images are given.