Assessment of matcha sensory quality using hyperspectral microscope imaging technology

Abstract Hyperspectral microscope imaging (HMI) technology coupled with chemometrics was attempted to mimic human panel test for estimating sensory quality of matcha in this study. The hypercubes from HMI system contained spatial and spectral information related with quality of samples. Models were established based on the spectral information and the sensory scores from human panel evaluation for sensory attributes. Characteristic spectra were first averaged and extracted from all the pixels in the optimized regions of interest. Then, key spectral variables were selected by competitive adaptive reweighted sampling and used for building artificial neural networks models (namely CARS-ANN models). Results demonstrated that the key spectral variables were only accounted for between 2% and 7% of the original spectral variables for each sensory attribute. The CARS-ANN models achieved superior performance, with 11 spectral variables and 0.7946 of Rp2 (coefficient of determination in prediction set) for appearance, 8 spectral variables and 0.7172 of Rp2 for infusion color, 21 spectral variables and 0.6747 of Rp2 for aroma, 6 spectral variables and 0.7788 of Rp2 for taste, 7 spectral variables and 0.7774 of Rp2 for overall quality. Overall, HMI technology as a rapid, objective and accurate tool has the potential for estimating quality of matcha.