A neural architecture for the classification of remote sensing imagery with advanced learning algorithms

This work presents an artificial neural networks based architecture for the classification of remote sensing (RS) multispectral imagery. The architecture consists of two processing modules: an image feature extraction module using Kohonen self-organizing map and a classification module using multilayer perceptron network. The architecture was developed aiming at two specific goals: to exploit the advantages of unsupervised learning for feature extraction, and the testing of techniques to increase the learning algorithm´s performance concerning training time. To test the applicability of this work, the architecture was applied to the classification of a LANDSAT/TM image segment from a pre-selected testing area and its performance was compared with that of a maximum likelihood classifier, conventionally used for RS multispectral images classification