Skip to main content
ARS Home » Midwest Area » East Lansing, Michigan » Sugarbeet and Bean Research » Research » Publications at this Location » Publication #287346
Title: Grading of apples based on firmness and soluble solids content using VIS-SWNIR spectroscopy and spectral scattering techniques

Author
item Mendoza, Fernando
item Lu, Renfu
item CEN, HAIYAN - Michigan State University

Submitted to: Journal of Food Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 10/17/2013
Publication Date: 3/1/2014
Citation: Mendoza, F., Lu, R., Cen, H. 2014. Grading of apples based on firmness and soluble solids content using VIS-SWNIR spectroscopy and spectral scattering techniques. Journal of Food Engineering. 125(3):59-68.

Interpretive Summary: Currently, apples are sorted by color, shape and size or weight, but not for internal quality. But consumers demand for the good eating quality of apples that is primarily characterized by firmness and soluble solids content (SSC). Sorting apples for firmness and SSC can thus assure consumer satisfaction and enhance the industry’s profitability. In this research, two nondestructive optical sensing systems, including a visible and shortwave near-infrared (Vis-SWNIR) spectroscopic sensor and a spectral scattering prototype developed inhouse, were used to grade apples into two quality grades, based on their firmness and/or SSC values as measured by standard destructive methods. Vis-SWNIR measurements were conducted in stationary condition, while spectral scattering measurements were carried out online at a conveyor speed of 82 mm/s. A total of 8491 apples for ‘Delicious’, ‘Golden Delicious’ and ‘Jonagold’ varieties harvested in 2009, 2010 and 2011 were used in the study. Spectral features were extracted from the Vis-SWNIR spectra data and the spectral scattering data, respectively, using appropriate mathematical methods, from which classification models were developed to sort apples into two quality grades based on firmness, SSC or their combined values. Results showed that Vis-SWNIR and spectral scattering gave good classification results for the three apple varieties with the accuracies of 87.3%-97.6% and 77.9-98.2% respectively, and both techniques, however, yielded lower classification accuracies of 77.1%-92.3% and 62.0%-91.7% for SSC. Varietal and seasonal effects on the classification results were observed. The research demonstrated that Vis-SWNIR and spectral scattering techniques are potentially useful for sorting apples based on firmness and/or SSC. Implementation of these techniques could greatly enhance the industry’s capability for delivering better quality and more consistent fruit to the consumer.

Technical Abstract: Sorting apple fruit based on internal quality will enhance the industry’s competiveness and profitability and assure consumer satisfaction. In this research, visible and shortwave near-infrared (Vis-SWNIR) spectroscopy (460–1,100 nm) and spectral scattering (450–1,050 nm) were used for sorting apples into two quality grades (i.e., ‘Premium’ and ‘Regular’) based on firmness, soluble solids content (SSC), or their combination. Vis-SWNIR spectra were obtained in an interactance mode under stationary condition, whereas spectral scattering images were acquired online at a conveyor speed of 82 mm/s. A total of 8,491 ‘Jonagold’, ‘Golden Delicious’, and ‘Delicious’ apples harvested in 2009, 2010 and 2011 were measured and used for analysis. First derivative was applied in the preprocessing of the Vis-SWNIR data, while the scattering images were first preprocessed by computing mean reflectance spectra and then performing continuous wavelet transform decompositions. Sorting algorithms were developed using sequential forward selection method and linear discriminant analysis. Relatively good sorting results for firmness (ranging between 77.9%-98.2%) and moderate results for SSC (ranging between 62.0%-91.7%) were obtained using scattering technique. The Vis-SWNIR technique showed slightly better sorting results for firmness (ranging between 87.3%-97.6%) and SSC (ranging between 77.1%-92.3%). When the classification involved both quality attributes, the sorting error increased. Vis-SWNIR and spectral scattering techniques have potential for online sorting and grading of apples by firmness and SSC.