Grading of apples based on firmness and soluble solids content using Vis/SWNIR spectroscopy and spectral scattering techniques

摘要: Abstract Sorting of apple fruit based on internal quality can enhance the industry’s competiveness and profitability assure consumer satisfaction. In this research, visible shortwave near-infrared (Vis/SWNIR) spectroscopy (460–1100 nm) spectral scattering (450–1050 nm) were used for sorting three varieties (i.e., ‘Delicious’, ‘Golden Delicious’ ‘Jonagold’) into two grades firmness, soluble solids content (SSC), or both firmness SSC. Vis/SWNIR spectra obtained in interactance mode under stationery condition, whereas images acquired online at a conveyor speed 82 mm/s. A total 8491 apples harvested from same orchard 2009, 2010 2011 analysis. First derivative data, while first preprocessed by computing mean reflectance then performing continuous wavelet transform decompositions. algorithms developed using sequential forward selection linear discriminant analysis, classification models compared terms their overall performance local confusion matrices. sensitivity analysis was also performed to assess effect different threshold criteria performance. Overall, consistent relatively good results (ranging between 77.9% 98.2%) moderate SSC 62.0% 91.7%) technique. technique showed slightly better 87.3% 97.6%) 77.1% 92.3%). When SSC, accuracies generally decreased 75.7% 90.1% 69.7% 91.5% scattering. techniques have potential grading