Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology
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...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
China Food Publishing Company
2024-03-01
|
| Series: | Shipin Kexue |
| Subjects: | |
| Online Access: | https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-6-031.pdf |
| _version_ | 1797202824607563776 |
|---|---|
| author | YUAN Weidong, JIANG Hongzhe, YANG Shiyu, ZHANG Cong, ZHOU Yu, ZHOU Hongping |
| author_facet | YUAN Weidong, JIANG Hongzhe, YANG Shiyu, ZHANG Cong, ZHOU Yu, ZHOU Hongping |
| author_sort | YUAN Weidong, JIANG Hongzhe, YANG Shiyu, ZHANG Cong, ZHOU Yu, ZHOU Hongping |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-24T08:09:35Z |
| format | Article |
| id | doaj.art-83976b4cc7d547988ab4efc53edf59d0 |
| institution | Directory Open Access Journal |
| issn | 1002-6630 |
| language | English |
| last_indexed | 2024-04-24T08:09:35Z |
| publishDate | 2024-03-01 |
| publisher | China Food Publishing Company |
| record_format | Article |
| series | Shipin Kexue |
| spelling | doaj.art-83976b4cc7d547988ab4efc53edf59d02024-04-17T07:13:34ZengChina Food Publishing CompanyShipin Kexue1002-66302024-03-0145625426010.7506/spkx1002-6630-20230620-159Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging TechnologyYUAN Weidong, JIANG Hongzhe, YANG Shiyu, ZHANG Cong, ZHOU Yu, ZHOU Hongping0(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)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.https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-6-031.pdfhyperspectral imaging; lycium barbarum; geographical origin identification; characteristic wavelengths |
| spellingShingle | YUAN Weidong, JIANG Hongzhe, YANG Shiyu, ZHANG Cong, ZHOU Yu, ZHOU Hongping Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology Shipin Kexue hyperspectral imaging; lycium barbarum; geographical origin identification; characteristic wavelengths |
| title | Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology |
| title_full | Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology |
| title_fullStr | Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology |
| title_full_unstemmed | Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology |
| title_short | Geographical Origin Identification of Lycium barbarum Fruit Using Hyperspectral Imaging Technology |
| title_sort | geographical origin identification of lycium barbarum fruit using hyperspectral imaging technology |
| topic | hyperspectral imaging; lycium barbarum; geographical origin identification; characteristic wavelengths |
| url | https://www.spkx.net.cn/fileup/1002-6630/PDF/2024-45-6-031.pdf |
| work_keys_str_mv | AT yuanweidongjianghongzheyangshiyuzhangcongzhouyuzhouhongping geographicaloriginidentificationoflyciumbarbarumfruitusinghyperspectralimagingtechnology |