Material analysis on noisy multispectral images using classifier combination

Abstract

Methods for material analysis on images are essential in many applications. We present a set of experiments with classifier combiners in order to recognize materials in multispectral images with applications in soil science. These images were obtained by the transmission of different energies with a computerized tomography scanner. The use of the linear attenuation coefficients as classification features is studied. The multispectral images are classified, and combining techniques for the classifiers are investigated. A comparison of the combiners with the individual classifiers is also performed.