Smart Detection of Rice Yield with HSI and Spectroscopy

Taghinezhad, E., Szumny, A., Figiel, A., Latifi Amoghin, M., Mirzazadeh, A., Blasco, J., Mazurek, S., & Castillo-Gironés, S. (2025). The potential application of HSI and VIS/NIR spectroscopy for non-invasive detection of starch gelatinization and head rice yield during parboiling and drying process. Journal of Food Composition and Analysis, 142, 107443. https://doi.org/10.1016/j.jfca.2025.107443

Monitoring starch gelatinization (SG) and head rice yield (HRY) in real time during parboiling is vital to minimizing product loss in rice production. Traditional measurement methods are labor-intensive and slow, which hinders process optimization. This study explores the use of hyperspectral imaging (HSI) and VIS/NIR spectroscopy (VNS) to non-invasively predict SG and HRY during drying and parboiling.

Rice samples were treated at various soaking and drying temperatures using a hybrid infrared-convective-microwave (ICM) dryer. Spectral data were preprocessed using five techniques, with the Savitzky–Golay method showing the best performance. Feature selection was optimized using a Decision Tree combined with a Learning Automata (DT-LA) algorithm. Regression models were built using Partial Least Squares Regression (PLSR) and Artificial Neural Networks (ANN).

The ANN models demonstrated high accuracy, with R² values of 0.99 for SG and 0.98 for HRY. HSI data slightly outperformed VNS in prediction capability. These results support the development of intelligent drying systems to improve rice processing efficiency.