A NEURAL-NET CLASSIFIER FOR MULTITEMPORAL LANDSAT TM IMAGES

The classification of remotely sensed multispectral data using classic al statistical methods has been worked an for several decades. Recentl y there have been many new developments in neural network (NN) researc h, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribu tion. We have proposed an NN model to combine the spectral and spacial information of a LANDSAT TM image. In this paper, we apply the NN app roach with a normalization method to classify multi-temporal LANDSAT T M images in order to investigate the robustness of our approach. From our experiments, we have confirmed that our approach is more effective for the classification of multi-temporal data than the original NN ap proach and maximum likelihood approach.