Nondestructive identification of tea (Camellia sinensis L.) varieties using FT-NIR spectroscopy and pattern recognition

Abstract

Due to more and more tea varieties in the current tea market, rapid and accurate identification of tea (<I>Camellia sinensis</I> L.) varieties is crucial to the tea quality control. Fourier Transform Near-Infrared (FT-NIR) spectroscopy coupled with the pattern recognition was used to identify individual tea varieties as a rapid and non-invasive analytical tool in this work. Seven varieties of Chinese tea were studied in the experiment. Linear Discriminant Analysis (LDA) and Artificial Neural Network (ANN) were compared to construct the identification models based on Principal Component Analysis (PCA). The number of principal components factors (PCs) was optimised in the constructing model. The experimental results showed that the performance of ANN model was better than LDA models. The optimal ANN model was achieved when four PCs were used, identification rates being all 100% in the training and prediction sets. The overall results demonstrated that FT-NIR spectroscopy technology with ANN pattern recognition method can be successfully applied as a rapid method to identify tea varieties.