Prediction of polyphenol content in tea leaves using NIR spectroscopy

Abstract

Total polyphenol contents in tea leaves estimation have been presented by the near infrared reflectance (NIR) spectroscopy. In order to calibrate the regression model on NIR tea spectra partial least squares (PLS) algorithm was used. The number of PLS factors and the choice of preprocessing methods were optimized simultaneously by leave-one-sample out cross-validation during the model calibration. The efficacy of the model developed was evaluated by the root mean square error of prediction (RMSEP), root mean square error of cross-validation (RMSECV) and correlation coefficient (R). The correlation coefficients (R) in the prediction set is 0.95. Results showed that NIR spectroscopy with PLS algorithm can be used to analyze the content of polyphenol in tea leaves.