Research on nondestructive identification of grape varieties based on EEMD‐DWT and hyperspectral image

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.

Identification of maize seed varieties based on stacked sparse autoencoder and near‐infrared hyperspectral imaging technology

“…The grayscale image (Figure 3c) at 1108.41 nm with the most prominent difference between the background spectral reflectance and the sample spectral reflectance was selected for threshold segmentation (shown in Figure 3b). According to the principle that the threshold value should be greater than the maximum reflectivity of the background image and less than the minimum reflectivity of the target image, the threshold value is set to 0.21 to obtain the mask image (Figure 3d) (Xu et al, 2021). Finally, the mask image was applied to the original NIR hyperspectral image to obtain the ROI image (Figure 3e), and the average spectrum of each pixel in the ROI region was calculated as sample data (Figure 3f).…”

Non‐destructive prediction of total soluble solids and titratable acidity in Kyoho grape using hyperspectral imaging and deep learning algorithm

“…Due to the insensitivity of the CCD detector at the start of the wavelength, which results in the spectra in this range being noisy, and thus the spectra within the range of 493–1001 nm (400 bands) were utilised for subsequent research. Next, the spectra were pre‐processed by multiplicative scatter correction (MSC) for mitigating the spectral scattering caused by heterogeneity among the samples, and the ensemble empirical mode decomposition combined with discrete wavelet transform (EEMD‐DWT) was applied to suppress the noise in the spectra (Xu et al ., 2021). Additionally, the latent outliers among samples were identified via Monte Carlo (MC) outlier detection algorithm for further improving the predictive ability of the models (Cao et al ., 2010).…”

Detection of peanut seed vigor based on hyperspectral imaging and chemometrics

“…Composed of spatial imaging, spectroscopy (Kucha et al, 2021), and chemical measurement tools, hyperspectral imaging techniques (Xu et al, 2021) can provide information on seed quality characteristics and characterization parameters(Jun Yang et al, 2021), overcoming the limitations of machine vision and nearinfrared spectroscopy techniques (Laborde et al, 2021). In recent years, some studies have used hyperspectral imaging technology as a powerful tool for seed vigor monitoring.…”