Food and Pharmaceutical Engineering Institute, Guiyang University, Guiyang, 550005, China.
Research Center of Nondestructive Testing for Agricultural Products of Guizhou Province, Guiyang, 550005, China.
Sci Rep. 2023 Aug 14;13(1):13189. doi: 10.1038/s41598-023-40553-3.
The traditional method for assessing the quality and maturity of loquats has disadvantages such as destructive sampling and being time-consuming. In this study, hyperspectral imaging technology was used to nondestructively predict and visualise the colour, firmness, and soluble solids content (SSC) of loquats and discriminate maturity. On comparison of the performance of different feature variables selection methods and the calibration models, the results indicated that the multiple linear regression (MLR) models combined with the competitive adaptive reweighting algorithm (CARS) yielded the best prediction performance for loquat quality. Particularly, CARS-MLR models with optimal prediction performance were obtained for the colour (R = 0.96, RMSEP = 0.45, RPD = 5.38), firmness (R = 0.87, RMSEP = 0.23, RPD = 2.81), and SSC (R = 0.84, RMSEP = 0.51, RPD = 2.54). Subsequently, distribution maps of the colour, firmness, and SSC of loquats were obtained based on the optimal CARS-MLR models combined with pseudo-colour technology. Finally, on comparison of different classification models for loquat maturity, the partial least square discrimination analysis model demonstrated the best performance, with classification accuracies of 98.19% and 97.99% for calibration and prediction sets, respectively. This study demonstrated that the hyperspectral imaging technique is promising for loquat quality assessment and maturity classification.
传统的评估枇杷品质和成熟度的方法存在破坏性采样和耗时的缺点。在本研究中，使用高光谱成像技术对枇杷的颜色、硬度和可溶性固形物含量（SSC）进行无损预测和可视化，并对成熟度进行区分。在比较不同特征变量选择方法和校准模型的性能后，结果表明，竞争自适应重加权算法（CARS）与多元线性回归（MLR）模型相结合的方法对枇杷品质的预测性能最好。特别是，对于颜色（R=0.96，RMSEP=0.45，RPD=5.38）、硬度（R=0.87，RMSEP=0.23，RPD=2.81）和 SSC（R=0.84，RMSEP=0.51，RPD=2.54），CARS-MLR 模型具有最佳的预测性能。随后，基于最优的 CARS-MLR 模型结合伪彩色技术，获得了枇杷颜色、硬度和 SSC 的分布图谱。最后，在比较不同的枇杷成熟度分类模型时，偏最小二乘判别分析模型表现出最好的性能，其校准集和预测集的分类准确率分别为 98.19%和 97.99%。本研究表明，高光谱成像技术有望用于评估枇杷的品质和成熟度。
