Line Scan Hyperspectral Imaging Spectroscopy for the Early Detection of Melamine and Cyanuric Acid in Feed

Abstract

This study was aimed at exploring the feasibility of detecting and quantifying melamine, and the structural analogue cyanuric acid, contamination in soybean meal, using line-scan near infrared (NIR) hyperspectral imaging spectroscopy (HIS). Soybean meal is one of the main ingredients used in the feed industry because it offers a complete protein profile. Each year, demand increases for soybean products and soya oil, the consumption of which is directly boosted by Chinese consumers' growing wealth, and for soybean meal, which is indirectly affected by the growing demand for meat. Recent cases of deliberate melamine contamination of soybean meal have been reported. This study focuses on the development of a methodology based on NIR-HIS for the acquisition, treatment and interpretation of images and spectra, as well as for the detection and quantification of melamine and cyanuric acid contamination in soybean meal. A total of 40 commercial soybean meal samples were collected, and 17 adulterated samples were prepared by adding different amounts of melamine/cyanuric acid to the samples, with concentrations varying between 0.5% and 5%. The spectral data were collected using line-scan NIR-HIS, and a qualitative model was created based on a principal-component analysis (PCA), whereas partial least-squares discriminant analysis was used to obtain a discrimination model and a semi-quantitative prediction of the content of contaminant. This study has permitted the detection of low levels of melamine and also revealed some limitations for the feasibility of quantifying melamine in soybean meal.

Portable Spectroscopy

“…In addition, if the contaminant is homogeneously dispersed, then hyperspectral imaging does not deliver any advantage over single point spectroscopy. There have been a number of studies on particulate contamination on foods, [548][549][550][551][552][553][554] but there is a considerable time lag between laboratory demonstration and commercial deployment in the field, so it remains to be seen what the utility of very low-cost hyperspectral imagers will be for this application.…”

Hyperspectral to multispectral imaging for detection of tree nuts and peanut traces in wheat flour

“…Nevertheless, the high cost and complexity of HSI, together with its large data-storage requirements, represents an important limitation to its industrial application. 13 In this context, feasibility studies carried out using complete spectral information are commonly a first step for further simplification into multispectral technology. HSI can be used to determine the optimal wavebands for a particular application.…”

NIR hyperspectral imaging for animal feed ingredient applications

“…The addition of melamine and cyanuric acid to pure soybean meal is an example of spiking the mixture which is done to produce laboratory-scale samples that can enhance the calibration signal-to-noise ratio and contribute to a robust quantitative calibration (Cogdill and Anderson, 2005). The spectra and PCA plots in Figure 3 show that it was possible to characterize soybean meal and segregate the adulterants (Fernández Pierna et al, 2014). Moreover, the high R 2 of regression between laboratory % concentration and number of detected pixels, 0.89 for melamine and 0.94 for cyanuric acid, implied that both contaminants could be identified at levels as low as 0.5% concentration (Fernández Pierna et al, 2014).…”

“…Fernández Pierna et al explored the use of near infrared hyperspectral imaging (1118-2424 nm) in combination with principal component analysis (PCA) and partial least-squares discriminant analysis (PLS-DA) to detect and quantify melamine and cyanuric acid contamination in soybean meal (Fernández Pierna et al, 2014). Melamine and cyanuric acid contents from 0.5% to 5% were added to pure soybean meal after obtaining spectra of pure products (Fernández Pierna et al, 2014).…”

“…Fernández Pierna et al explored the use of near infrared hyperspectral imaging (1118-2424 nm) in combination with principal component analysis (PCA) and partial least-squares discriminant analysis (PLS-DA) to detect and quantify melamine and cyanuric acid contamination in soybean meal (Fernández Pierna et al, 2014). Melamine and cyanuric acid contents from 0.5% to 5% were added to pure soybean meal after obtaining spectra of pure products (Fernández Pierna et al, 2014). The addition of melamine and cyanuric acid to pure soybean meal is an example of spiking the mixture which is done to produce laboratory-scale samples that can enhance the calibration signal-to-noise ratio and contribute to a robust quantitative calibration (Cogdill and Anderson, 2005).…”