|HUANG, MIN - Jiangnan University
|Chao, Kuanglin - Kevin Chao
|Qin, Jianwei - Tony Qin
|MO, CHANGYEUN - Rural Development Administration - Korea
|ESQUERRE, CARLOS - University College Dublin
|Delwiche, Stephen - Steve
|ZHU, QIBING - Jiangnan University
Submitted to: Sensors
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/22/2016
Publication Date: 3/25/2016
Citation: Huang, M., Kim, M.S., Chao, K., Qin, J., Mo, C., Esquerre, C., Delwiche, S.R., Zhu, Q. 2016. Penetration depth measurement of near-infrared hyperspectral imaging light for milk powder. Sensors. 16(4):441.
Interpretive Summary: In recent years, incidents of milk powder adulteration by melamine to boost apparent protein content have caused illnesses and resulted in wide recognition of melamine contamination as a food safety problem. Research has demonstrated the potential applications of spectral imaging techniques for ingredient analysis of powder foods. This study was aimed at determining optimal light penetration depth of a near-infrared hyperspectral imaging system for detection of adulterant in milk powder samples. The results suggest that a 2-mm sample depth is recommended for screening/evaluation of milk powders using the near-infrared spectral imaging method. The research presented in this paper provides insightful information for developing image-based screening methods for powder food adulteration and benefits food processing industries.
Technical Abstract: The increasingly common application of near-infrared (NIR) hyperspectral imaging technique to the analysis of food powders has led to the need for optical characterization of samples. This study was aimed at exploring the feasibility of quantifying penetration depth of NIR hyperspectral imaging light for milk powder. Hyperspectral NIR reflectance images were collected for eight different milk powder products that included five brands of non-fat milk powder and three brands of whole milk powder. For each milk powder, five different powder depths ranging from 1 mm to 5 mm were prepared on the top of a base layer of melamine, to test spectral-based detection of the melamine through the milk. A relationship was established between the NIR reflectance spectra (937.5 nm – 1653.7 nm) and the penetration depth was investigated by means of the partial least squares-discriminant analysis (PLS-DA) technique to classify pixels as being milk-only or a mixture of milk and melamine. With increasing milk depth, classification model accuracy was gradually decreased. The results from the 1-mm, 2-mm, and 3-mm models showed that the average classification accuracy of the validation set for milkmelamine samples was reduced from 99.86% to 94.93% as the milk depth increased from 1 mm to 3 mm. As the milk depth increased to 4 mm and 5 mm, model performance deteriorated further to accuracies as low as 81.83% and 58.26%, respectively. The results suggest that a 2-mm sample depth is recommended for screening/evaluation of milk powders using an online NIR hyperspectral imaging system similar to that used in this study.