Nondestructive Discrimination of Grape Seed Varieties Using UV-VIS-NIR Spectroscopy and Chemometrics
Classification of grape seed species is a useful tool to obtain seeds with desired quality traits. This study aimed at rapidly and nondestructively discriminating four varieties of grape seeds using ultra violet, visible and near infrared (UV-VIS-NIR) spectroscopy with wavelength range of 2101100 nm. A hundred twenty grape seed samples were divided for calibration (n=80) and validation (n=40). The spectra were subjected to a principal component analysis (PCA) with the leading 10 principal components (PCs) used to build calibration models. The obtained PCs were treated by linear discriminant analysis (LDA), artificial neural network (ANN) and support vector machine (SVM) to build various discrimination models. Validation results showed that the PC-LDA model developed for the full range of UV-VIS-NIR achieved better performance than those developed for partial wavelengths, i.e. UV, VIS, NIR, UV-VIS, and VIS-NIR. The PC-LDA model with 8 PCs achieved best performance with 100% discrimination accuracy. This experiment suggests that the UV-VIS-NIR spectroscopy coupled with PC-LDA calibration method is promising for the nondestructive discrimination of grape seed varieties.