Classification and authentication of tea according to their geographical origin based on FT-IR fingerprinting using pattern recognition methods

The potential of FT-IR spectra was examined to classify tea samples based on the geographical origins. Principal component analysis (PCA), principal analysis-linear discriminant (PCA-LDA) and partial least square-discriminant (PLS-DA) were investigated in order achieve discrimination samples. Several spectral pre-processing methods, such as mean centering (MC), auto-scaling, multiplicative scatter correction (MSC), standard normal variate (SNV) their combinations, employed improve quality spectra. results showed that from five regions can be identified using fingerprints. demonstrated fingerprinting combined with pattern recognition methods an effective feasible method for classification Iranian