Premium
Nondestructive identification of green tea varieties based on hyperspectral imaging technology
Author(s) -
Sun Jun,
Tang Kai,
Wu Xiaohong,
Dai Chunxia,
Chen Yong,
Shen Jifeng
Publication year - 2018
Publication title -
journal of food process engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.507
H-Index - 45
eISSN - 1745-4530
pISSN - 0145-8876
DOI - 10.1111/jfpe.12800
Subject(s) - hyperspectral imaging , support vector machine , pattern recognition (psychology) , mathematics , feature selection , preprocessor , artificial intelligence , computer science
A new method for rapid detection of green tea varieties by hyperspectral imaging technology was proposed in this article. In this experiment, five different varieties of green tea were taken as the research object, and the hyperspectral images of five different varieties of green tea were collected. In order to reduce the impact of noise and spectral scattering, the spectral data were preprocessed using Savitzky–Golay (SG) and multiple scattering correction (MSC) preprocessing. Then iteratively retaining informative variables (IRIV) and variable iterative space shrinkage approach (VISSA) variable selection method were used to make variable selection on the pre‐processed spectral data to select the best variable combination. Since the randomness of support vector machine (SVM) parameters has a certain influence on the model, the firefly algorithm (FA) was used to optimize the parameters of SVM. Finally, the SVM green tea varieties identification models were established based on the total spectral data and the spectral data selected by variables selection, and the different modeling results were compared and analyzed. The results show that the VISSA‐FA‐SVM model has the best identification effect, and the classification accuracies of the calibration set and the prediction set are 100 and 96%, respectively. Practical applications The practical application of this article is to identify the different varieties of green tea by using hyperspectral imaging technology. Compared with traditional methods, hyperspectral imaging technology can be used to identify different varieties of green tea quickly, nondestructive and accurately. Optimizing the parameters of the model in appropriate can improve the performance of the model. In this article, firefly algorithm was used to optimize SVM parameters to get the optimal parameters for modeling. In addition, the selection of preferred variables by variables selection can provide a theoretical basis for the identification of portable green tea varieties.