Filtering remote sensing data in the spatial and feature domains

We present a comparative study of the effects of applying pre-processing and post-processing to remote sensing data both in the spatial image domain and the feature domain. We use a neural network for classification since it is not biased by a priori assumptions about the distributions of the spectral values of the classes. Spatial smoothing was applied both as preand post-processing steps. Pre-processing involved smoothing the image spectral values by means of anisotropic diffusion, whereas iterative majority filtering was applied as a postprocessing step to improve spatial coherence by reclassifying pixels. While it is common practice to filter the image before classification (smoothing) or after classification (iterative majority filtering) it is less obvious what happens if pre-processing is applied to the training or image data in feature space. To minimise the effect of noisy training pixels we applied a k-nearest neighbour filtering algorithm to the training data. This involved reclassifying each training pixel by the majority class of the set of k closest training pixels (in terms of Euclidean distance) in feature space. The procedure eliminates isolated training pixels and tends to produce more compact class clusters. The effects of all spatial and spectral filtering methods were validated by applying them to three different testcases.