Short communication: Identification of geographical indication tea with Fisher's discriminant classification and principal components analysis

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.