Invariant Object Material Identification via Discriminant Learning on Absorption Features

In this paper, we propose a novel approach to object material identification in spectral imaging by combining the use of absorption features and statistical machine learning techniques. We depart from the significance of spectral absorption features for material identification and cast the problem into a classification setting which can be tackled using support vector machines. Hence, we commence by proposing a novel method for the robust detection of absorption bands in the spectra. With these bands at hand, we show how those absorptions which are most relevant to the classification task in hand may be selected via discriminant learning. We then train a support vector machine for purposes of classification making use of an absorption feature representation scheme which is robust to varying photometric conditions. We perform experiments on real world data and compare the results yield by our approach with those recovered using an alternative. We also illustrate the invariance of the absorption features recovered by our method to different photometric effects.