结合机器学习的高光谱成像技术在山核桃种子质量检测和品种分类中的应用

摘要：山核桃作为一种著名的干果和木本油料树种，其产业发展面临质量评估方法复杂和品种混淆等挑战，严重制约了 大规模深加工产业的推进。本研究旨在应用高光谱成像技术（（ HSI）结合机器学习方法，对山核桃种子的质量进行评估并 实现品种分类。实验样本包括19个品种的山核桃种子，每个品种30粒。经过光谱预处理后，采用特征提取方法从光谱 曲线中提取特征，并建立反向传播神经网络模型和偏最小二乘模型，用于预测山核桃种子中的粗脂肪和水分含量。最优 模型的预测结果表现出色，粗脂肪模型的 R²值为 0.887，水分模型的 R²值为 0.950。此外，研究还构建了支持向量机模 型用于山核桃品种识别，该模型在 19 个品种的分类中表现优异，准确率达到 0.965。综上所述，高光谱成像技术与机器 学习的结合为山核桃产业提供了一种有效的工具，能够为其生产提供可持续且高效的方法，具有重要的应用潜力。

关键词：山核桃种子；品质检测；品种分类；高光谱成像技术；机器学习；特征提取方法

期刊：Journal of Food Composition and Analysis

DOI：https://doi.org/10.1016/j.jfca.2024.106248

设备：GaiaField

Quality detection and variety classiffcation of pecan seeds using hyperspectral imaging technology combined with machine learning

Abstract：Pecan (Carya illinoinensis K.), a well-known dried seed and woody oil tree, faces challenges in its industry due to complex quality assessment methods and confusing varieties. These challenges have seriously hampered the development of a large-scale pecan deep processing industry. This work aimed to apply hyperspectral imaging technology (HSI) combined with machine learning to evaluate the quality of pecan seeds and perform variety classiffcation. The samples of this work were composed of 19 varieties of pecan seeds, with 30 seeds per variety. After spectral preprocessing, spectral features were extracted from the spectral proffles using feature extraction methods. Back-propagation neural network models and partial least squares models were established to predict the contents of crude fat and moisture in pecan seeds. Predictions of the best models gave good results with R2 - score of 0.887 for the crude fat model and 0.950 for the moisture model. Additionally, support vector machine models were developed to identify pecan varieties. The model achieved good results in 19 pecan varieties identiffcation with accuracy of 0.965. In conclusion, the combination of HSI and machine learning could be an effective tool in improving the pecan industry and providing sustainable and efffcient methods in the production of pecan seeds.

Keywords：Pecan seed; Quality detection; Variety classiffcation; Hyperspectral imaging technique; Machine learning; Feature extraction method