食品科学 ›› 2024, Vol. 45 ›› Issue (6): 254-260.doi: 10.7506/spkx1002-6630-20230620-159

• 安全检测 • 上一篇    下一篇

基于高光谱成像技术的宁夏枸杞产地溯源鉴别

袁伟东,姜洪喆,杨诗雨,张聪,周禹,周宏平   

  1. (1.南京林业大学机械电子工程学院,江苏 南京 210037;2.南京林业大学 林业资源高效加工利用协同创新中心,江苏 南京 210037)
  • 出版日期:2024-03-25 发布日期:2024-04-03
  • 基金资助:
    “十四五”国家重点研发计划重点专项(2022YFD2202100);国家林业和草原局应急科技项目(202202-3)

Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology

YUAN Weidong, JIANG Hongzhe, YANG Shiyu, ZHANG Cong, ZHOU Yu, ZHOU Hongping   

  1. (1. College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China;2. Co-Innovation Center of Efficient Processing and Utilization of Forest Resources, Nanjing Forestry University, Nanjing 210037, China)
  • Online:2024-03-25 Published:2024-04-03

摘要: 本研究基于高光谱成像(400~1 000 nm)结合化学计量学开发一种用于识别枸杞产地多元化的检测方法。获取宁夏、甘肃、内蒙古、青海和新疆5 个不同产地的枸杞高光谱图像,并基于阈值分割方法从感兴趣区域提取光谱数据。同时使用多种预处理方法消除光谱的干扰信息,研究表明基于归一化反射光谱的判别模型表现出较好的性能。进一步地采用连续投影算法、竞争性自适应重加权算法(competitive adaptive reweighted sampling,CARS)、粒子群优化算法、迭代保留信息变量算法(iteratively retaining informative variables,IRIV)和CARS+IRIV选择特征波长。研究结果表明CARS+IRIV选取波长建立的简化模型性能最优,从二元分类到五元分类模型,特征波长仅占全波长的15.6%~27.7%,预测集准确率分别为97.7%、90.9%、89.2%、87.1%。此外,为了更加直观辨别分类种类,使用混淆矩阵可视化最佳简化分类模型。在对宁夏枸杞分类中获得了令人满意的灵敏度、特异性和Kappa系数。综上,高光谱成像技术结合化学计量学方法可有效鉴别枸杞产地,可为枸杞产业发展提供关键技术支撑。

关键词: 高光谱成像, 枸杞, 产地鉴别, 特征波长

Abstract: This study aimed to develop a method based on hyperspectral imaging (400–1 000 nm) combined with chemometrics to identify the diverse geographical origins of Lycium barbarum fruit. Hyperspectral images of L. barbarum fruit from Ningxia, Gansu, Inner Mongolia, Qinghai and Xinjiang were acquired, and spectral data was extracted from the region of interest (ROI) by threshold segmentation method. Multiple preprocessing methods were employed to eliminate the interference information from the spectra, and the results showed that the discriminant model based on normalized reflectance spectrum (NR) exhibited better performance. Furthermore, the successive projection algorithm (SPA), competitive adaptive reweighted sampling (CARS), particle swarm optimization (PSO), iteratively retaining informative variables (IRIV), and CARS + IRIV were used to select characteristic wavelengths. The results showed that the simplified model based on the wavelengths selected by CARS + IRIV had the best performance. In the models ranging from binary to quintuple classifications, the selected characteristic wavelengths accounted for only 15.6% to 27.7% of the full spectra. The prediction accuracy was 97.7%, 90.9%, 89.2%, and 87.1%, respectively. In addition, a confusion matrix was employed to visualize the optimal simplified classification model in order to intuitively distinguish the classification categories. Satisfactory sensitivity, specificity and Kappa coefficients were obtained in classifying L. barbarum. The results illustrated that hyperspectral imaging technology combined with chemometric methods could effectively identify the geographical origin of L. barbarum and provide crucial technical support for the development of the L. barbarum industry.

Key words: hyperspectral imaging, Lycium barbarum, geographical origin identification, characteristic wavelengths

中图分类号: