Residual Error based Approach to Classification of Multisource Remote Sensing Images

Classification of multisource remote sensing images has been studied for decades, and many methods have been proposed. Most of these studies focus on how to improve the classifiers in order to obtain higher classification accuracy. However, as we know, even if the most promising neural network method, its good performance not only depends on the classifier itself, but also has relation to the training pattern (i.e. features). On consideration of this aspect, we propose an approach to feature selection and classification of multisource remote sensing image based on residual error in this paper. In particular, a feature-selection scheme approach is proposed, which is to select effective subsets of features as inputs of a classifier by taking into account the residual error associated with each land-cover class. In addition, a classification technique base on selected features by using a feedforward neural network is investigated. The results of experiments carried out on a multisource data set confirm the validity of the proposed approach