Nondestructive identification of green tea varieties based on hyperspectral imaging technology

Abstract

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.

Investigation on Data Fusion of Multisource Spectral Data for Rice Leaf Diseases Identification Using Machine Learning Methods

“…For linearly separable data, a linear equation can be obtained to construct the hyperplanes. For data which are not linearly separable, SVM maps the original data into high-dimensional spaces to transform the problem into linearly separable issues and constructs hyperplanes to maximally divide the samples from different categories in the new spaces (Feng et al, 2018;Sun et al, 2018;Zhang et al, 2018). Kernel functions are essential for the mapping, and radial basis function (RBF) is a widely used kernel function of SVM.…”

Rapid and Nondestructive Discrimination of Geographical Origins of Longjing Tea using Hyperspectral Imaging at Two Spectral Ranges Coupled with Machine Learning Methods

“…Ge et al [29] used hyperspectral imaging (spectral range: 400.68-1001.612 nm) to identify oolong tea varieties, and the classification accuracy was over 97%. Sun et al [30] used hyperspectral imaging (spectral range: 390-1050 nm) to identify green tea varieties, and the classification accuracy was over 91%. Jia et al [31] used near-infrared spectroscopy (spectral range: 1350-1800 nm) to identify the growing area of Longjing tea, and the classification accuracy of two growing areas was 97.3%.…”

Grade Identification of Tieguanyin Tea Using Fluorescence Hyperspectra and Different Statistical Algorithms

“…HSI is an advanced analytical technique that combines traditional imaging and spectroscopy techniques to simultaneously acquire spatial and spectral information (Dale, Thewis, & Boudry, 2013). By combining appropriate analytical methods, it cannot only detect the main components of tea (Zhao, Wang, Ouyang, & Chen, 2011), but also effectively classify tea varieties (Puneet et al, 2018;Sun et al, 2018). Fluorescence spectroscopy, which is a mature, simple, fast, accurate and nondestructive technique, has been found to be highly effective in tea classification and quality assessment due to its high sensitivity (Dong et al, 2014;Seetohul, Scott, O'Hare, Ali, & Islam, 2013).…”