Application of neural network approach to classify multi-temporal Landsat images

The classification of remotely sensed multispectral data using classical statistical methods has been worked on for several decades. Recently there have been many new developments in neural network (NN) research, and many new applications have been studied. It is well known that NN approaches have the ability to classify without assuming a distribution. The authors have proposed an NN model to use the spectral and spatial information. In this paper, they apply the NN approach to the classification of multi-temporal LANDSAT TM images in order to investigate the robustness of a normalization method. From their experiments, they confirmed that the NN approach with the preprocessing is more effective for the classification than the original NN approach even if the test data, is taken at the different time