Selection/Extraction of Spectral Regions for Autofluorescence Spectra Measured in the Oral Cavity

Recently a number of successful algorithms to select/extract discriminative spectral regions was introduced. These methods may be more beneficial than the standard feature selection/extraction methods for spectral classification. In this paper, on the example of autofluorescence spectra measured in the oral cavity, we intend to get deeper understanding what might be the best way to select informative spectral regions and what factors may influence the success of this approach.