Research on nondestructive identification of grape varieties based on EEMD-DWT and hyperspectral image.
Journal:
Journal of food science
PMID:
33885160
Abstract
Grape varieties are directly related to the quality and sales price of table grapes and consumed products (raisin, wine, grape juice, etc.). To satisfy the identification requirements of rapid, accurate, and nondestructive detection, an improved denoising algorithm based on ensemble empirical mode decomposition (EEMD) and discrete wavelet transform (DWT) is proposed to couple with the hyperspectral image (HSI) of grape varieties in this study. First, the hyperspectral data of grape varieties are collected by using HSI instrument, and denoised by the proposed EEMD-DWT and other denoising algorithms. CARS-SPA (competitive adaptive reweighed sampling coupled with successive projections algorithm) is introduced to select the effective wavelengths and a discriminative model is constructed by using support vector machine (SVM). Finally, Monte Carlo experiments verified that EEMD-DWT was an effective and powerful spectra denoising method, and the SVM model constructed by combining with CARS-SPA had an excellent identification accuracy (99.3125%). The results suggested that the key wavelengths selected by using CARS-SPA and EEMD-DWT could be an alternative to the deal with HSI, and its potential to become a method for identifying grape varieties. PRACTICAL APPLICATION: Traditional grape varieties identification methods are destructive and time consuming. Therefore, HSI technology is applied to realize fast and nondestructive identification of grape varieties in this study. The research results indicate that it is feasible to combine HSI technology with machine learning algorithm to discriminate grape varieties. It is of great significance for grape grading and the promotion of excellent varieties, and also provides reference for grape industry producers to identify grape varieties quickly and accurately.