Nondestructive Detection of Authenticity of Thai Jasmine Rice Using Multispectral Imaging

Abstract

The detection of authenticity is essential to the development and management of Thai jasmine rice industry. In this study, the multispectral imaging system (405–970 nm) was used for the detection of adulteration in Thai jasmine rice combined with chemometric methods including principal component analysis (PCA), partial least squares (PLS), least squares-support vector machines (LS-SVM), and backpropagation neural network (BPNN). Three varieties of rice that were similar to Thai jasmine rice in appearance were selected to perform the classification and quantitative prediction experiments by multispectral images. For the classification experiment, four varieties of rice samples could be easily classified with accuracy achieved to 92% by the BPNN model. For the quantitative prediction of adulteration proportion experiments, the results showed that, among the different chemometric methods, LS-SVM achieved the best prediction performance comparing the results of coefficient of determination, root-mean-square error (RMSEP), bias, and residual predictive deviation (RPD). It can be concluded that multispectral imaging technology with chemometric methods can be applied in the rapid and nondestructive detection of authenticity of Thai jasmine rice.

The use of multispectral imaging for the discrimination of Arabica and Robusta coffee beans

“…Several other studies showed a potential of the MSI analysis using VideometerLab to discriminate different crop varieties. Liu et al (2021) applied MSI for the differentiation of four rice varieties and the authentication of Thai Jasmine rice. A combination of the analysis of spectral and morphological features was coupled with chemometrics (PCA, PLS, least squares-support vector machines (LS-SVM) and backpropagation neural network (BPNN)).…”

“…The rapid and non-destructive nature of these instruments, combined with no requirement for sample preparation or the use of specialised laboratory facilities and hazardous chemicals, are an advantage and mean that these systems have the potential to be used for screening applications. Spectral imaging has showed a great potential for its application in food authenticity screening over the recent years ( ElMasry et al, 2019 , Feng et al, 2019 , Liu et al, 2021 , Lohumi et al, 2015 , Su and Sun, 2018 ). Depending on the number of wavebands, at which the spectral image is acquired, two main types of spectral imaging techniques have been used: hyperspectral imaging (HSI), which acquires images by utilizing a large number of wavebands leading to a continuous spectral image, and multispectral imaging (MSI), which acquires images with a few (generally up to 20) discrete wavebands ( Boelt et al, 2018 , ElMasry et al, 2019 , Su and Sun, 2018 , Qin et al, 2013 ).…”

The Rapid Non-Destructive Differentiation of Different Varieties of Rice by Fluorescence Hyperspectral Technology Combined with Machine Learning

“…Among them, Thai jasmine rice's appearance, good quality, and fragrant smell are loved by consumers worldwide [7]. However, due to its limited production, the mixing of the expensive Thai jasmine rice with ordinary white rice is becoming an increasingly problematic phenomenon [8]. The malpractice creates unfair economic interests, undermining the consumer's trust in the producer [9], affecting the consumer's consumption of taste, and causing severe harm to the health of the body [10].…”

A Dual-Band High-Sensitivity THz Metamaterial Sensor Based on Split Metal Stacking Ring

“…Furthermore, terahertz spectroscopy can be used to characterize macromolecules because the vibration and rotation patterns of molecules are mostly in this frequency range [ 5 ], allowing for the generation of a distinct “fingerprint” spectrum of many substances. Therefore, terahertz spectroscopy has potential application in the fields of biomedicine [ 6 ], security inspection [ 7 ], and quality control [ 8 ], with the unique advantage of being a fast, non-destructive and label-free detection method. Nonetheless, in practice, the sensitivity and accuracy of detection are limited by the fact that the electromagnetic response of most substances in nature to THz waves is prone to be too weak [ 9 , 10 ].…”