Computer vision-based smart monitoring and control system for food drying: A study on carrot slices.

Convective dryer embedded with computer vision (CV) system and load cell was used to continuously monitor carrot slices that are either unblanched or blanched (90 degrees C for 2 min) during product drying (35 degrees C, 35 % R.H., 3 m s-1 airflow). The CV system and load cell were selected as in-line Process Analytical Technology tools within a proactive Quality-by-Design framework and embedded for, i) monitoring of product features (i.e., weight, colour, and size); and ii) developing shrinkage-dependent moisture prediction models using linear regression. The evaluated shrinkage-dependent linear models showed superior performances (RMSE, 0.005-0.007) benchmarked against selected thin-layer models of increasing complexity. The study tested a smart-enabled prototype dryer with the potential for automation and integrating proactive quality strategies.