Non-destructive discrimination of illicium verum from poisonous adulterant using vis/nir hyperspectral imaging combined with chemometrics

Authors: LU, YAO - China Agricultural University; WANG, WEI - China Agricultural University; Ni, Xinzhi; Zhuang, Hong

Submitted to: Infrared Physics and Technology
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 9/8/2020
Publication Date: 9/12/2020
Citation: Lu, Y., Wang, W., Ni, X., Zhuang, H. 2020. Non-destructive discrimination of illicium verum from poisonous adulterant using vis/nir hyperspectral imaging combined with chemometrics. Infrared Physics and Technology. 111: Article 103509. https://doi.org/10.1016/j.infrared.2020.103509.
DOI: https://doi.org/10.1016/j.infrared.2020.103509

Interpretive Summary: Hyperspectral imaging technology, as a non-invasive, non-contact and non-traditional sampling technology, combines spectroscopy with imaging techniques in one system that can provide spectral and spatial information simultaneously for a given sample. This technology has been used for a variety of food product quality control and adulterant detection in recent years with high precision. The previous reports have demonstrated that the hyperspectral imaging technology has become the choice for identification of food product adulteration, especially in the spice quality control. Therefore, the purpose of this study was to utilize hyperspectral imaging technology to distinguish the true star anise spice from its poisonous relative. The detailed examination using three forms (i.e., intact, broken and fallen follicle) of samples with different arrangements and two placements (face-up and back-up) have proved that all poisonous relative of the star anise could be identified using the hyperspectral imaging technology. The findings have established a theoretical and modelling foundation for the development of high-throughput online sorting equipment in future.

Technical Abstract: Poisonous relative of the star anise, Illicium lanceolatum A. C. Smith, was found mixed with the true spice star anise, Illicium verum Hook. f., in the postharvest stage, which was difficult to separate the two species with naked eyes, especially broken samples and fallen follicles. A Vis/ NIR hyperspectral imaging (HSI) system with wavelength range between 400 and 1000 nm was used as a non- destructive method to distinguish the two species with the purpose of safety control for I. verum. Firstly, spectral comparison and explanatory PCA was conducted to prove the discriminability between the two species in either face-up or back-up placement position, and a good clustering effect for I. lanceolatum samples was discovered. Then, linear partial least squares discriminant analysis (PLSDA) and nonlinear support vector machine (SVM) were developed to classify the two species based on full-wavelength, key wavelengths selected by successive projections algorithm (SPA) and regression coefficients (RC) and the most contributing principal components, in which SPA-PLSDA was selected as the most effective model (CCRc = 100%, CCRv = 96.88% and CCRcv = 98.44%). Furthermore, three forms (i.e., intact, broken and fallen follicle) of samples with different arrangements and two placements (face-up and back-up) were used to verify the applicability of the enhanced model. Correct classification rate (CCR) of the three independent tests were satisfactory (CCRset1 = 98.44%, CCRset2 = 100% and CCR set3 = 95.83%), and the sensitivity of I. verum (=91.67%) and I. lanceolatum (100%) also proved that all I. lanceolatum could be identified using HSI technique, which establishes a theoretical and modelling foundation for the development of high-throughput online sorting equipment in future.