<i>Nitzschia closterium</i> and <i>Nitzschia longissima</i> are two species of diatom that are extremely difficult to differentiate using light microscopy. This paper details an investigation into the use of FT-IR microscopy combined with discriminant analysis to differentiate between these species. Spectra were taken from unidentified samples and classified against a training set using either Mahalanobis distances or principal component analysis combined with canonical discriminant analysis. Unidentified samples were classified with a 100% accuracy using both mathematical techniques.
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.
Contact your librarian or system administrator
Login to access OSA Member Subscription