Hyperspectral Imaging to Characterize Table Grapes

Table grape quality is of importance for consumers and thus producers. Its objective usually determined by destructive methods mainly based on sugar content. This study proposed to evaluate the possibility hyperspectral imaging characterize table grapes through its (TSS), total flavonoid (TF), anthocyanin (TA) contents. Different data pre-treatments (WD, SNV, 1st 2nd derivative) different were tested get best prediction models: PLS with full spectra then Multiple Linear Regression (MLR) realized after selecting optimal wavelengths thanks regression coefficients (β-coefficients) Variable Importance in Projection (VIP) scores. All models good at showing that a relevant method predict sugar, flavonoid, The predictions obtained from wavelength selection β-coefficients TSS VIPs windows using SNV pre-treatment Thus, order while reducing sets limit storage enable an industrial use.