Tags

Type your tag names separated by a space and hit enter

Penetration Depth Measurement of Near-Infrared Hyperspectral Imaging Light for Milk Powder.
Sensors (Basel). 2016 Mar 25; 16(4):441.S

Abstract

The increasingly common application of the 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-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 (937.5-1653.7 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 milk-melamine samples was reduced from 99.86% down to 94.93% as the milk depth increased from 1 mm-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 the screening/evaluation of milk powders using an online NIR hyperspectral imaging system similar to that used in this study.

Authors+Show Affiliations

Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi 214122, China. huangmzqb@163.com. Environmental Microbial and Food Safety Laboratory, Agricultural Research Service, USDA, Beltsville, MD 20705, USA. huangmzqb@163.com.Environmental Microbial and Food Safety Laboratory, Agricultural Research Service, USDA, Beltsville, MD 20705, USA. moon.kim@ars.usda.gov.Environmental Microbial and Food Safety Laboratory, Agricultural Research Service, USDA, Beltsville, MD 20705, USA. kevin.chao@ars.usda.gov.Environmental Microbial and Food Safety Laboratory, Agricultural Research Service, USDA, Beltsville, MD 20705, USA. jianwei.qin@ars.usda.gov.National Institute of Agricultural Science, Rural Development Administration, 310 Nongsaengmyeong-ro, Wansan-gu, Jueonju-si, Jeollabuk-do 54875, Korea. cymoh100@korea.kr.School of Biosystems and Food Engineering, University College Dublin, Dublin 4, Ireland. carlos.esquerre@ucd.ie. Food Quality, Agricultural Research Service, USDA, Beltsville, MD 20705, USA. carlos.esquerre@ucd.ie.Food Quality, Agricultural Research Service, USDA, Beltsville, MD 20705, USA. stephen.delwiche@ars.usda.gov.Key Laboratory of Advanced Process Control for Light Industry, Ministry of Education, Jiangnan University, Wuxi 214122, China. zhuqib@163.com.

Pub Type(s)

Journal Article
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

27023555

Citation

Huang, Min, et al. "Penetration Depth Measurement of Near-Infrared Hyperspectral Imaging Light for Milk Powder." Sensors (Basel, Switzerland), vol. 16, no. 4, 2016, p. 441.
Huang M, Kim MS, Chao K, et al. Penetration Depth Measurement of Near-Infrared Hyperspectral Imaging Light for Milk Powder. Sensors (Basel). 2016;16(4):441.
Huang, M., Kim, M. S., Chao, K., Qin, J., Mo, C., Esquerre, C., Delwiche, S., & Zhu, Q. (2016). Penetration Depth Measurement of Near-Infrared Hyperspectral Imaging Light for Milk Powder. Sensors (Basel, Switzerland), 16(4), 441. https://doi.org/10.3390/s16040441
Huang M, et al. Penetration Depth Measurement of Near-Infrared Hyperspectral Imaging Light for Milk Powder. Sensors (Basel). 2016 Mar 25;16(4):441. PubMed PMID: 27023555.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Penetration Depth Measurement of Near-Infrared Hyperspectral Imaging Light for Milk Powder. AU - Huang,Min, AU - Kim,Moon S, AU - Chao,Kuanglin, AU - Qin,Jianwei, AU - Mo,Changyeun, AU - Esquerre,Carlos, AU - Delwiche,Stephen, AU - Zhu,Qibing, Y1 - 2016/03/25/ PY - 2015/09/01/received PY - 2016/03/21/revised PY - 2016/03/22/accepted PY - 2016/3/30/entrez PY - 2016/3/31/pubmed PY - 2017/1/10/medline KW - PLS-DA KW - hyperspectral imaging KW - milk powder KW - penetration depth SP - 441 EP - 441 JF - Sensors (Basel, Switzerland) JO - Sensors (Basel) VL - 16 IS - 4 N2 - The increasingly common application of the 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-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 (937.5-1653.7 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 milk-melamine samples was reduced from 99.86% down to 94.93% as the milk depth increased from 1 mm-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 the screening/evaluation of milk powders using an online NIR hyperspectral imaging system similar to that used in this study. SN - 1424-8220 UR - https://www.unboundmedicine.com/medline/citation/27023555/Penetration_Depth_Measurement_of_Near_Infrared_Hyperspectral_Imaging_Light_for_Milk_Powder_ L2 - https://www.mdpi.com/resolver?pii=s16040441 DB - PRIME DP - Unbound Medicine ER -