Active (Mueller matrix) remote sensing is an under-utilized technique for material discrimination and classification. A full Mueller matrix instrument returns more information than a passive (Stokes) polarimeter; Mueller polarimeters measure depolarization and other linear transformations that materials impart on incident Stokes vectors, which passive polarimeters cannot measure. This increase in information therefore allows for better classification of materials (in general). Ideally, material classification over the entire polarized BRDF is desired, but sets of Mueller matrices for different materials are generally not separable by a linear classifier over elevation and azimuthal target angles. We apply non-linear support vector machines (SVM) to classify materials over BRDF (all relevant angles) and show variations in receiver operator characteristic curves with scene composition and number of Mueller matrix channels in the observation.