NIR laser-based imaging techniques to monitor quality attributes of apple slices during the drying process: Laser-light backscattering & biospeckle imaging techniques

Abstract

This paper seeks to investigate the potential use of laser-based imaging techniques in non-invasive quality inspection of apple slices during drying. For this purpose, Laser-light Backscattering (LLBI) and Biospeckle (BSI) Imaging techniques were investigated. Images at 980 nm and 1450 nm were captured. The data was used to develop Gaussian Process Regression (GPR) and Partial Least Square Regression (PLSR) models in order to estimate quality attributes of moisture content, vitamin C, and soluble solids content (SSC). Overall, the predictions accuracies were slightly in favor of GPR models. Moisture content was best estimated with R-squared = 0.92 and RMSE = 7%, and R-squared = 0.93 and RMSE = 6.54% when GPR models were trained on 1450/980 nm data acquired by LLBI or 980 nm data acquired by BSI, respectively. LLBI-based GPR models predicted vitamin C with R-squared ≥ 0.79 and RMSE ≤ 0.83 mg/100 g fresh weight (FW), slightly better than that of BSI (R-squared = 0.80 and RMSE ≤ 1.01 mg/100 g). The most accurate predictions of SSC for LLBI (R-squared = 0.88 and RMSE = 6.39%) and BSI (R-squared = 0.82 and RMSE = 7.99%) were achieved at 980 nm. Furthermore, BSI monitoring system was embedded into an experimental dryer to study the interaction between sample temperature and biospeckle activity. Results showed an increase in biospeckle activity at the beginning of drying followed by a gradual decrease towards the end of drying. The findings of present study indicate the potential use of simple and promising monochrome imaging systems in monitoring of the drying process that can be considered as alternatives to more expensive imaging sensors such as hyperspectral imaging.