Rapid Classification of Wheat Grain Varieties Using Hyperspectral Imaging and Chemometrics

Abstract

The classification of wheat grain varieties is of great value because its high purity is the yield and quality guarantee. In this study, hyperspectral imaging combined with the chemometric methods was applied to explore and implement the varieties classification of wheat seeds. The hyperspectral images of all the samples covering 874–1734 nm bands were collected. Exploratory analysis was first carried out while using principal component analysis (PCA) and linear discrimination analysis (LDA). Spectral preprocessing methods including standard normal variate (SNV), multiplicative scatter correction (MSC), and wavelet transform (WT) were introduced, and their effects on discriminant models were studied to eliminate the interference of instrumental and environmental factors. PCA loading, successive projections algorithm (SPA), and random frog (RF) were applied to extract feature wavelengths for redundancy elimination owing to the possibility of existing redundant spectral information. Classification models were developed based on full wavelengths and feature wavelengths using LDA, support vector machine (SVM), and extreme learning machine (ELM). This optimal model was finally utilized to generate visualization map to observe the classification performance intuitively. When comparing with other models, ELM based on full wavelengths achieved the best accuracy up to 91.3%. The overall results suggested that hyperspectral imaging was a potential tool for the rapid and accurate identification of wheat varieties, which could be conducted in large-scale seeds classification and quality detection in modern seed industry.

Rapid and Accurate Varieties Identification of Different Crop Seeds Under Sample-Limited Condition Based on Hyperspectral Imaging and Deep Transfer Learning

“…But different from our common sense that nonlinear models generally performed better than linear models, nonlinear model MLP achieved lower accuracy than linear model LDA in this study [41,[45][46]. Thus, many models need to be tried to determine which is the optimal one if we use traditional multivariate analysis methods [45][46][47][48]. Conversely, deep models will generally achieve satisfactory results if the training data is sufficient and the structure is properly designed.…”

Cultivar Discrimination of Single Alfalfa (Medicago sativa L.) Seed via Multispectral Imaging Combined with Multivariate Analysis

“…The difference between seed spectrums reflected the difference in the seed coat texture and chemical composition which may differ among different cultivars [ 24 ]. The reflectance at special wavelength differed significantly among cultivars in wheat [ 25 ] and corn [ 26 ]. Consistent with this, our study shows that cultivars can be divided into three groups according to spectral reflectance, these three groups partly reflect the origin of cultivars.…”

Machine Learning for Seed Quality Classification: An Advanced Approach Using Merger Data from FT-NIR Spectroscopy and X-ray Imaging

“…The use and combination of different techniques have gradually increased in seed technology, especially for detecting seed viability [12,[31][32][33][34][35]. Combinations based on merged data have shown the potential to increase reliability on seed classification when compared to the use of individual analytical techniques [3,19].…”