HYBRID CONSENSUS THEORETIC CLASSIFICATION

Hybrid classification methods based on consensus from several data sou rces are considered, Each data source is at first treated separately a nd modeled using statistical methods, Then weighting mechanisms are us ed to control the influence of each data source in the combined classi fication, The weights are optimized in order to improve the combined c lassification accuracies. Both linear and nonlinear optimization metho ds are considered and used in classification of two multisource remote sensing and geographic data sets. A nonlinear method which utilizes a neural network gives excellent experimental results, The hybrid stati stical/neural method outperforms all other methods in terms of test ac curacies in the experiments.