Fuzzy ARTMAP — A Neural Classifier for Multispectral Image Classification

This chapter shifts attention to fuzzy ARTMAP classification which synthesises fuzzy logic and Adaptive Resonance Theory (ART) by exploiting the formal similarity between the computations of fuzzy subsets and the dynamics of category choice, search and learning. The contribution describes design features, system dynamics and simulation algorithms of this learning system, which is trained and tested for classification (with eight classes a priori given) of a Landsat-5 Thematic Mapper scene from the city of Vienna on a pixel-by-pixel basis. The performance of the fuzzy ARTMAP is compared with that of an error-based learning system based upon a single hidden layer feedforward network, and the Gaussian maximum likelihood classifier as conventional statistical benchmark on the same database. Both neural classifiers outperform the conventional classifier in terms of classification accuracy. Fuzzy ARTMAP leads to out-of-sample classification accuracies which are very close to maximum performance, while the backpropagation network — like the conventional classifier — has difficulty in distinguishing between some land use categories.