Supervised Classification of Remotely Sensed Imagery Using a Modified k-NN Technique

Nearest neighbor (NN) techniques are commonly used in remote sensing, pattern recognition and statistics to classify objects into a predefined number of categories based on a given set of predictors. These techniques are especially useful in those cases exhibiting highly nonlinear relationship between variables. In most studies the distance measure is adopted a priori. In contrast, we propose a general procedure to find Euclidean metrics in a low dimensional space (i.e. one in which the number of dimensions is less than the number of predictor variables) whose main characteristic is to minimize the variance of a given class label of all those pairs of points whose distance is less than a predefined value. k-nearest neighbor (k-NN) is used in each embedded space to determine the possibility that a query belongs to a given class label. The class estimation is carried out by an ensemble of predictions. To illustrate the application of this technique, a typical land cover classification using a Landsat 5-TM scene is presented. Experimental results indicate substantial improvement with regard to the classification accuracy compared with approaches such as maximum likelihood (ML), linear discriminant analysis (LDA), standard k-NN, and adaptive quasiconformal kernel k-nearest neighbor (AQK). Index Terms Land cover classification, k-nearest neighbors, simulated annealing, dimensionality reduction, ensemble prediction.