|CEN, HAIYAN - Michigan State University|
Submitted to: ASABE Annual International Meeting
Publication Type: Proceedings
Publication Acceptance Date: 8/22/2011
Publication Date: 8/22/2011
Citation: Mendoza, F., Lu, R., Cen, H. 2011. Data fusion of visible/near-infrared spectroscopy and spectral scattering for apple quality assessment. ASABE Annual International Meeting. Paper No. 1111244.
Interpretive Summary: Visible/near-infrared (VNIR) spectroscopy and spectral scattering are two promising sensing techniques for nondestructive assessment of fruit firmness and soluble solids content (SSC), two quality attributes that are critical to the consumer acceptance of fresh apples. Since each sensor is based on a different principle, combination of them could provide more complete and complementary information about the quality or condition of apples. This research was intended to develop and optimize mathematical models using the fused data acquired by the two sensing techniques, for prediction of apple firmness and SSC. VNIR spectroscopic and spectral scattering data were collected and analyzed for 6,631 apples of 'Delicious', 'Golden Delicious', 'Jonagold' cultivars harvested in 2009 and 2010. Statistical analyses showed that overall, spectral scattering technique performed better in predicting fruit firmness, whereas VNIR technique was superior for prediction of SSC. The fused-sensor approach, i.e., combination of the two sensors, significantly improved the firmness and SSC prediction of apples in most cases. The firmness and SSC prediction models for the pooled data of the two harvest seasons, however, did not perform as well as those for individual harvest seasons, even though the SSC models were less affected by harvest year. This research has showed that the sensor fusion approach can provide more robust and accurate assessment for the firmness and SSC of apples.
Technical Abstract: Visible/near-infrared (VNIR) spectroscopy and spectral scattering are based on different sensing principles, and they have shown different abilities for predicting apple fruit firmness and soluble solids content (SSC). Hence the two techniques could work synergistically to improve the quality prediction of apples. In this research, VNIR spectroscopic and spectral scattering data for the wavelength range of 460–1,100 nm were collected for 6,631 apples of ‘Delicious', 'Golden Delicious' and 'Jonagold' cultivars during the 2009 and 2010 harvest seasons and for three months after the refrigerated air storage. Partial least squares models were developed for each sensor and their combination to predict the fruit firmness and SSC for both single-year and cross-year data sets. The spectral scattering technique generally performed better in predicting firmness, whereas the VNIR technique was superior for prediction of SSC. Overall, the data fusion of the two sensors produced significant improvements (p<0.05) for prediction of the firmness and SSC than individual sensors. Cross-year prediction results for firmness and SSC were lower, compared with prediction results for each year. However, the cross-year prediction model for SSC was more robust and less sensitive to the harvest-year effect, compared to the firmness prediction model. Sensor fusion can provide more robust and accurate firmness and SSC assessment for apples.