Determination of damaged wheat kernels with hyperspectral imaging analysis

Yuanyuan Shao,Zhichao Hu,Youqing Chen,Guantao Xuan,Chong Gao,Xuemei Gao

doi:10.25165/j.ijabe.20201305.4413

Abstract

Hyperspectral imaging was applied to classify the damaged wheat kernels and healthy kernels. The spectral information was extracted from damaged wheat kernels and healthy kernels samples. The effective wavelengths were obtained from spectral of 865-1711 nm by X-loadings of principal component analysis (PCA) and successive projection algorithm (SPA) method, respectively. Partial least square method (PLS) and least square-support vector machine (LS-SVM) were then used to build classification models on full spectral data and effective wavelengths dataset, respectively. The results showed that the classification accuracy of every LS-SVM model was the best, being 100%. While the accuracy of the PLS model was slightly lower, still over 97%. The confusion matrix showed that several damaged wheat kernels samples were misclassified as healthy samples, while all healthy samples were correctly classified. The overall results indicated that hyperspectral imaging could be used for discriminating the damaged wheat kernels and could provide a reference for detecting other grain kernels grading degrees. Further, this study can provide a research basis for the development of online or portable detectors on grain damaged kernels recognition, which will be beneficial for grain grading or post-harvest quality processing of other grains. Keywords: hyperspectral image, damaged wheat kernels, determination, PCA, SPA, LS-SVM DOI: 10.25165/j.ijabe.20201305.4413 Citation: Shao Y Y, Gao C, Xuan G T, Gao X M, Chen Y Q, Hu Z C. Determination of damaged wheat kernels with hyperspectral imaging analysis. Int J Agric & Biol Eng, 2020; 13(5): 194–198.

Highlights

Wheat is one of the major crops and one of the three major staple foods in China
The wheat grade depends on the proportion of damaged wheat kernels, grade 1 and 2 requires the proportion is less than or equal to 6%, while grade 3, 4 requires the proportion is less than 8%, and grade 5 requires less than or equal to 10%[1]
The damaged wheat kernels normally are caused by insect infestation, mechanical damage, diseased kernels, germinal kernels and moldy kernels during harvest and storage

Summary

Introduction

Wheat is one of the major crops and one of the three major staple foods in China. It is of great importance to classify the quality of wheat for the purpose of ensuring food security, realizing quality prices in wheat market transactions. According to wheat national standards of China[1], damaged wheat kernel is one important degrading factor in classifying wheat grade. The damaged wheat kernels normally are caused by insect infestation, mechanical damage, diseased kernels, germinal kernels and moldy kernels during harvest and storage. Such damages seriously affect the quality of food and the safe storage of wheat. Damaged wheat kernels are detected by manual method, which is time-consuming, inefficient, and being subjective, and so on[2]

Methods

Results

Conclusion