返回列表
近红外高光谱成像技术快速检测核桃中内源杂质
食品检测
2026/09/21
摘要：核桃产品中的杂质对人体健康构成重大风险，因此需要开发快速高效的方法来检测核桃破壳材料中的内源性杂质。 为解决这一问题，本研究旨在探讨近红外高光谱成像（（NIR-HSI）技术结合传统化学计量学方法和深度学习模型的可行性。 首先，生化实验表明不同核桃仁的总酚和类黄酮含量存在差异。基于蝴蝶优化算法改进的支持向量机模型被构建用于核 桃内源性杂质的近红外数据集分类，准确率达到96.12%。此外，本研究提出了WT-NIRSNet模型，这是一种带有额外注 意力机制的深度神经网络，并与传统化学计量学方法进行了比较。研究表明，使用 WT-NIRSNet 模型在测试集上解决核 桃内源性杂质的快速分类问题时，准确率达到99.03%。该模型仅需使用原始光谱数据而无需复杂的预处理操作即可实现 理想的分类效果，且优于传统的化学计量学模型。因此，结合深度神经网络的近红外高光谱成像技术在核桃内源性杂质 检测中具有显著潜力。
关键词：深度学习；特征提取；食品质量；高光谱成像；杂质检测；核桃
期刊：Journal of Food Composition and Analysis
DOI：https://doi.org/10.1016/j.jfca.2024.106290
设备：GaiaField
Rapid detection of endogenous impurities in walnuts using near-infrared hyperspectral imaging technology
Abstract：Impurities in walnut-based products pose a signiffcant risk to human health, necessitating the development of rapid and efffcient methods for detecting endogenous impurities in walnut shell-breaking materials. To address this issue, this study aims to investigate the feasibility of near-infrared hyperspectral imaging (NIR-HSI) in conjunction with conventional chemometric methods and deep learning models. First, biochemical experiments demonstrated differences in the total phenolic and ffavonoid contents of different walnut kernels. An improved support vector machine model based on the butterffy optimization algorithm was constructed for classiffcation using an NIR dataset of endogenous impurities in walnuts, achieving an accuracy of 96.12 %. In addition, this study proposed the WT-NIRSNet model, a deep neural network with an additional attention mechanism, and compared it to a traditional chemometric approach. The study demonstrated an accuracy of 99.03 % on the test set using WT-NIRSNet to solve the fast classiffcation problem of endogenous impurities in walnuts. It can achieve desirable classiffcation results using only raw spectral data without complex preprocessing operations and is superior to traditional chemometric models. Therefore, the NIR-HSI technique combined with deep neural networks has a signiffcant potential for detecting endogenous impurities in walnuts.
Keywords：Deep learning; Feature extraction; Food quality; Hyperspectral imaging; Impurities detection; Walnut
