Abstract
This study attempted to identify authentic geographical indication tea using near infrared (NIR) spectroscopy with a combination of Fisher's discriminant classification and principal components analysis (PCA). This rapid and accurate NIR-based approach has shown an accuracy rate for identifying the geographical indication tea equal to 96.7% in a training set, 95.3% using cross-validation and 96.7% in a test set. The overall results suggest that the combination of NIR spectroscopy with Fisher's discriminant classification with PCA could be successfully applied as a rapid and reliable way to identify geographical indication tea.
© 2009 IM Publications LLP
PDF Article
More Like This
Cited By
You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.
Contact your librarian or system administrator
or
Login to access Optica Member Subscription