Click on “Download PDF” for the PDF version or on the title for the HTML version.

If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Application of Time Series Hyperspectral Imaging (TS-HSI) for Determining Water Content within Tea Leaves during Drying

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan

Citation:  Transactions of the ASABE. 56(6): 1431-1440. (doi: 10.13031/trans.56.10243) @2013
Authors:   Chuanqi Xie, Xiaoli Li, Pengcheng Nie, Yong He
Keywords:   Drying, Tea leaves, Time series hyperspectral imaging, Variable selection, Water content.

This research investigated the feasibility of using time series hyperspectral imaging (TS-HSI) for rapid and nondestructive determination of water content in tea leaves. Hyperspectral images of tea leaves were obtained at different periods of drying across the wavelength region of 380 to 1030 nm. The reflectance value of the region of interest (ROI) was extracted with ENVI 4.7 software. Different preprocessing methods were applied to determine the best method based on the root mean square error of calibration (RMSEC), root mean square error of prediction (RMSEP), residual predictive deviation (RPD), and coefficient of determination (R2) of the partial least squares regression (PLSR) model. The successive projections algorithm (SPA) was then used to identify the most important wavelengths and reduce the high dimensionality of the spectral data. On the basis of the four effective wavelengths (542, 709, 752, and 971 nm), an SPA-PLSR model was established. Among the different PLSR models, the multiplicative scatter correction-PLSR (MSC-PLSR) model performed best with the highest values of R2cal, R2val, R2pre, and RPD (0.979, 0.961, 0.968, and 5.616, respectively) and the lowest values of RMSEC, RMSEV, and RMSEP (0.033, 0.045, and 0.040, respectively). However, the SPA-PLSR mode, with only four input variables, was considered to be preferable for determining water content in tea leaves. The SPA-PLSR model obtained R2cal, R2val, R2pre, and RPD values of 0.938, 0.935, 0.946, and 4.292, respectively, and RMSEC, RMSEV, and RMSEP values of 0.055, 0.057, and 0.052, respectively. The results showed that the TS-HSI technique has potential to be a rapid and nondestructive method to detect water content in tea leaves at different drying periods.

(Download PDF)    (Export to EndNotes)