The feasibility of using a computer-vision (CV) system embedded in a hot-air dryer for non-destructive and real-time monitoring of the drying behaviour of organic apples was investigated in the present study. Apple cylinders were subjected to anti-browning treatments with different dipping solutions (water as control, trehalose (4% w/v) or trehalose + ascorbic acid (4% w/v and 1% w/v)) and dipping pressures (atmospheric, 101.3 kPa and sub-atmospheric pressure, 50 kPa) followed by drying at 60 °C to a final dry basis moisture content of 0.18 g g⁻¹. The CV system was used as an in-line process analytical technology (PAT) tool to capture images reflecting the physico-chemical changes during product drying coupled with in-line mass changes and off-line reference analyses. The spatial and colour changes from the image analysis described well the complex and non-homogenous nature of apple drying. The results of spatial changes allowed successful development of accurate linear prediction models for moisture content as a function of area shrinkage (on scaled variables) with excellent prediction capability (|BIAS| < 8.5 10⁻³, RMSE < 0.04, Adj-R² ~ = 99%). Also, the CV system identified the differently pre-treated samples, particularly the dipping pressures as reflected by two linear models and their respective parameters. The obtained results demonstrate the versatile advantages of CV systems as an in-line tool for continuous, real-time monitoring of apples during drying. The insights from this study can provide a platform for applications of CV embedded ‘Smart dryers’ as an efficient monitoring and control system for industrial drying processes.

本研究调查了使用嵌入热风干燥机中的计算机视觉 (CV) 系统对有机苹果的干燥行为进行无损实时监测的可行性。用不同的浸渍溶液（水作为对照、海藻糖（4% w/v）或海藻糖 + 抗坏血酸（4% w/v 和 1% w/v））和浸渍压力（大气压）对苹果圆筒进行抗褐变处理, 101.3 kPa 和亚大气压 50 kPa)，然后在 60 °C 下干燥至最终干基水分含量为 0.18 gg ^-1. CV 系统用作在线过程分析技术 (PAT) 工具，以捕获反映产品干燥过程中物理化学变化以及在线质量变化和离线参考分析的图像。图像分析的空间和颜色变化很好地描述了苹果干燥的复杂性和非均质性。空间变化的结果允许成功开发作为面积收缩函数的水分含量的准确线性预测模型（按比例变量），具有出色的预测能力（|BIAS| < 8.5 10 ^-3 , RMSE < 0.04, Adj-R ²~ = 99%）。此外，CV 系统识别了不同预处理的样品，特别是由两个线性模型及其各自参数反映的浸渍压力。获得的结果证明了 CV 系统作为在线工具在干燥过程中连续、实时监测苹果的多种优势。这项研究的见解可以为 CV 嵌入式“智能干燥机”作为工业干燥过程的有效监测和控制系统的应用提供一个平台。