Evaluation of near-infrared hyperspectral imaging for detection of peanut and walnut powders in whole wheat flour

Authors: ZHAO, XIN - China Agricultural University; WANG, WEI - China Agricultural University; Ni, Xinzhi; CHU, XUAN - China Agricultural University; LI, YU-FENG - Chinese Academy Of Sciences; SUN, CHANGPO - Chinese Academy Of Sciences

Submitted to: Applied Sciences
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 6/15/2018
Publication Date: 7/3/2018
Citation: Zhao, X., Wang, W., Ni, X., Chu, X., Li, Y., Sun, C. 2018. Evaluation of near-infrared hyperspectral imaging for detection of peanut and walnut powders in whole wheat flour. Applied Sciences. 8:Article 1076.

Interpretive Summary: A common practice of sharing of an equipment for processing multiple food products in food industry has increased the risk of foreign material contamination for a given food product. For example, peanut and walnut contaminants in whole wheat flour, which are threats to people who are allergic to nuts. Near Infrared hyperspectral imaging as a rapid and nondestructive tool for quantitative inspection of peanut and walnut contaminants in whole wheat flour was evaluated in this study. Hyperspectral images (within the range of 950 to 1700 nm wavelengths) of the samples were acquired in the reflectance mode and then transformed into absorbance. Individual prediction models for peanut or walnut contaminant, as well as general multispectral model for predicting the combined samples of peanut and walnut contamination, were developed. The optimal general model was established based on 17 selected wavelengths, and had promising results with a high determination coefficient of prediction value. Finally, the visualization maps graphically reflected the variation of contaminant concentrations from samples to samples and even within a sample. The results indicated that the near infrared hyperspectral imaging technique has the potential to quantitatively detect contaminants of peanut and walnut powders in the whole wheat flour.

Technical Abstract: The general utilization of processing equipment in industry has increased the risk of foreign material contamination. For example, peanut and walnut contaminants in whole wheat flour, which typically a healthy food, are a threat to people who are allergic to nuts. The feasibility of utilizing near-infrared hyperspectral imaging to inspect peanut and walnut powder in whole wheat flour was evaluated herein. Hyperspectral images at wavelengths 950–1700 nm were acquired. A standard normal variate combined with the Savitzky–Golay first derivative spectral transformation was adopted for the development of a partial least squares regression (PLSR) model to predict contamination concentrations. A successive projection algorithm (SPA) and uninformative variable elimination (UVE) for featured wavelength selection were compared. Two individual prediction models for peanut or walnut-contaminated flour, and a general multispectral model for both peanut-contaminated flour and walnut-contaminated flour, were developed. The optimal general multispectral model had promising results, with a determination coefficient of prediction (Rp2) of 0.987, and a root mean square error of prediction (RMSEP) of 0.373%. Visualization maps based on multispectral PLSR models reflected the contamination concentration variations in a spatial manner. The results demonstrated that near-infrared hyperspectral imaging has the potential to detect peanut and walnut powders in whole wheat flour for rapid quality control.