This study aimed to develop an effective method for detecting wheat flour contamination in rice flour using near-infrared hyperspectral imaging (NIR-HSI), with the goal of supporting raw material quality control and food safety. Rice flour samples contaminated with varying levels (0%–100%) of low-gluten and high-gluten wheat flour were analyzed using NIR-HSI, and classification models were developed using partial least squares–discriminant analysis (PLS-DA). The developed models successfully discriminated between pure rice flour and wheat flour–contaminated rice flour. The selected models based on the original spectra achieved classification accuracies of 98.18% and 100.00% for low-gluten and high-gluten wheat flour, respectively, in the independent prediction set. For the low-gluten wheat flour model, sensitivity, specificity, and F1-score values were 97.78%, 100.00%, and 98.88%, respectively, while all classification metrics for the high-gluten wheat flour model were 100.00%. The original spectra provided comparable or better classification performance than the SNV- and second derivative–pretreated spectra. In addition, color maps generated from the PLS-DA models enabled visualization of the spatial distribution of wheat flour contamination across the investigated concentration range. These findings demonstrate the potential of NIR-HSI combined with PLS-DA as a rapid and non-destructive approach for detecting and visualizing wheat flour contamination in rice flour.
Citation: Sunee Jungtheerapanich, Kraireuk Ngowsuwan, Anupun Terdwongworakul, Jaruporn Rakmai, Pornsuda Chawengrum, Jittraporn Chusrisom. Rapid detection and spatial visualization of wheat flour contamination in rice flour using near-infrared hyperspectral imaging coupled with PLS-DA[J]. AIMS Agriculture and Food, 2026, 11(3): 704-719. doi: 10.3934/agrfood.2026036
This study aimed to develop an effective method for detecting wheat flour contamination in rice flour using near-infrared hyperspectral imaging (NIR-HSI), with the goal of supporting raw material quality control and food safety. Rice flour samples contaminated with varying levels (0%–100%) of low-gluten and high-gluten wheat flour were analyzed using NIR-HSI, and classification models were developed using partial least squares–discriminant analysis (PLS-DA). The developed models successfully discriminated between pure rice flour and wheat flour–contaminated rice flour. The selected models based on the original spectra achieved classification accuracies of 98.18% and 100.00% for low-gluten and high-gluten wheat flour, respectively, in the independent prediction set. For the low-gluten wheat flour model, sensitivity, specificity, and F1-score values were 97.78%, 100.00%, and 98.88%, respectively, while all classification metrics for the high-gluten wheat flour model were 100.00%. The original spectra provided comparable or better classification performance than the SNV- and second derivative–pretreated spectra. In addition, color maps generated from the PLS-DA models enabled visualization of the spatial distribution of wheat flour contamination across the investigated concentration range. These findings demonstrate the potential of NIR-HSI combined with PLS-DA as a rapid and non-destructive approach for detecting and visualizing wheat flour contamination in rice flour.
| [1] |
Park J, Kim HS (2023) Rice-based gluten-free foods and technologies: A review. Foods 12: 4110. https://doi.org/10.3390/foods12224110 doi: 10.3390/foods12224110
|
| [2] |
Tian Y, Sun J, Li J, et al. (2024) Effects of milling methods on rice flour properties and rice product quality: A review. Rice Sci 31: 33–46. https://doi.org/10.1016/j.rsci.2023.11.002 doi: 10.1016/j.rsci.2023.11.002
|
| [3] |
Li Y, Liu Q, Godefroy S, et al. (2025) Gluten contamination of labelled gluten-free food products marketed in China. Foods 14. https://doi.org/10.3390/foods14122025 doi: 10.3390/foods14122025
|
| [4] |
Öcal HY, Özel HG (2025) Naturally gluten-free flours are commonly contaminated, while commercially produced gluten-free flours are relatively safe: A market-based study in Turkey. Front Nutr 12: 1707584. https://doi.org/10.3389/fnut.2025.1707584 doi: 10.3389/fnut.2025.1707584
|
| [5] |
Raju N, Joshi AKR, Vahini R, et al. (2020) Gluten contamination in labelled and naturally gluten-free grain products in southern India. Food Addit Contam A 37: 531–538. https://doi.org/10.1080/19440049.2020.1711970 doi: 10.1080/19440049.2020.1711970
|
| [6] |
Xu L, Yan SM, Cai CB, et al. (2013) Untargeted detection of illegal adulterations in Chinese glutinous rice flour (GRF) by NIR spectroscopy and chemometrics: Specificity of detection improved by reducing unnecessary variations. Foods Anal Methods 6. https://doi.org/10.1007/s12161-013-9575-y doi: 10.1007/s12161-013-9575-y
|
| [7] |
Radman M, Jurina T, Benković M, et al. (2018) Application of NIR spectroscopy in gluten detection as a cross-contaminant in food. Croat J Food Technol Biotechnol Nutr 13: 120–127. https://doi.org/10.31895/hcptbn.13.3-4.4 doi: 10.31895/hcptbn.13.3-4.4
|
| [8] |
Singla D, Malik T, Singh A, et al. (2024) Advances in understanding wheat-related disorder: A comprehensive review on gluten-free products with emphasis on wheat allergy, celiac and non-celiac gluten sensitivity. Food Chem Adv 4: 100627. https://doi.org/10.1016/j.focha.2024.100627 doi: 10.1016/j.focha.2024.100627
|
| [9] |
Vázquez-Polo M, Navarro V, Perez-Junkera G, et al. (2024) Assessment of a training course for cookery students regarding celiac disease and gluten-free Diet. Heliyon 10: e39060. https://doi.org/10.1016/j.heliyon.2024.e39060 doi: 10.1016/j.heliyon.2024.e39060
|
| [10] |
Zerbini C, De Canio F, Martinelli E, et al. (2024) Are gluten-free products healthy for non-celiac consumers? How the perception of well-being moderates gluten-free addiction. Food Qual Prefer 118: 105183. https://doi.org/10.1016/j.foodqual.2024.105183 doi: 10.1016/j.foodqual.2024.105183
|
| [11] |
Erkinbaev C, Henderson K, Paliwal J (2017) Discrimination of gluten-free oats from contaminants using near infrared hyperspectral imaging technique. Food Control 80: 197–203. https://doi.org/10.1016/j.foodcont.2017.04.036 doi: 10.1016/j.foodcont.2017.04.036
|
| [12] |
Martín-Masot R, Correa-López N, Herrador-López M, et al. (2025) Immunomodulatory effects of a short-term gluten-free diet on pediatric celiac disease: Findings from a single-cell transcriptomics study. J Nutr Biochem 146: 110063. https://doi.org/10.1016/j.jnutbio.2025.110063 doi: 10.1016/j.jnutbio.2025.110063
|
| [13] |
Moreno A, Hernandez S, Sanchis A, et al. (2025) Peptidomic insights into gluten peptide degradation: Exploring bacterial strains as a palliative strategy for celiac disease. Food Biosci 68: 106759. https://doi.org/10.1016/j.fbio.2025.106759 doi: 10.1016/j.fbio.2025.106759
|
| [14] |
Tovo PA, Armandi A, Bruno M, et al. (2025) Adults with celiac disease exhibit overexpression of endogenous retroviruses, TRIM28, and SETDB1 despite gluten-free diet. Virus Res 359: 199613. https://doi.org/10.1016/j.virusres.2025.199613 doi: 10.1016/j.virusres.2025.199613
|
| [15] |
Biesiekierski JR (2025) Clinical utility of gluten restriction in gastrointestinal disorders: Evidence, practice, and reappraisal of non-coeliac gluten sensitivity. Best Pract Res Cl Ga 79: 102086. https://doi.org/10.1016/j.bpg.2025.102086 doi: 10.1016/j.bpg.2025.102086
|
| [16] |
Huong NTM, Tien NNT, Phi NTL, et al. (2025) Quality and digestibility of gluten-free cookies made from rice flour substituted with highly enzyme-resistant mung bean starch. Int J Food Sci 1: 7689819. https://doi.org/10.1155/ijfo/7689819 doi: 10.1155/ijfo/7689819
|
| [17] | Codex Alimentarius (2015) Standard for foods for special dietary use for persons intolerant to gluten (CXS 118-1979), Rome. |
| [18] |
Zhao X, Wang W, Ni X, et al. (2019) Utilising near-infrared hyperspectral imaging to detect low-level peanut powder contamination of whole wheat flour. Biosyst Eng 184: 55–68. https://doi.org/10.1016/j.biosystemseng.2019.06.010 doi: 10.1016/j.biosystemseng.2019.06.010
|
| [19] |
Laborde A, Puig-Castellví F, Jouan-Rimbaud Bouveresse D, et al. (2021) Detection of chocolate powder adulteration with peanut using near-infrared hyperspectral imaging and multivariate curve resolution. Food Control 119: 107454. https://doi.org/10.1016/j.foodcont.2020.107454 doi: 10.1016/j.foodcont.2020.107454
|
| [20] |
Zhang J, Guo Z, Ren Z, et al. (2023) Rapid determination of protein, starch and moisture content in wheat flour by near-infrared hyperspectral imaging. J Food Compos Anal 117: 105134. https://doi.org/10.1016/j.jfca.2023.105134 doi: 10.1016/j.jfca.2023.105134
|
| [21] |
Jimoh KA, Hashim N, Shamsudin R, et al. (2025) Hyperspectral imaging for detection of macronutrients retained in glutinous rice under different drying conditions. Cur Res Food Sci 10: 100963. https://doi.org/10.1016/j.crfs.2024.100963 doi: 10.1016/j.crfs.2024.100963
|
| [22] |
Cui J, Cao S, Hao J, et al. (2025) A novel rapid technique for measuring wheat protein content using near-infrared hyperspectral imaging. J Food Compos Anal 148: 108415. https://doi.org/10.1016/j.jfca.2025.108415 doi: 10.1016/j.jfca.2025.108415
|
| [23] |
Miao YH, Zong LY, Su WH (2025) Machine learning in VIS/NIR spectroscopy and hyperspectral imaging for rapid detection of staple foods quality and safety: A review. J Food Compos Anal 148: 108422. https://doi.org/10.1016/j.jfca.2025.108422 doi: 10.1016/j.jfca.2025.108422
|
| [24] |
Lin N, Ren Y, Sun DW (2025) Advancements in novel polysaccharide analysis: Emerging spectral technology approaches. Trends Food Sci Tech 162: 105037. https://doi.org/10.1016/j.tifs.2025.105037 doi: 10.1016/j.tifs.2025.105037
|
| [25] |
Huang M, Kim MS, Delwiche SR, et al. (2016) Quantitative analysis of melamine in milk powders using near-infrared hyperspectral imaging and band ratio. J Food Eng 181: 10–19. https://doi.org/10.1016/j.jfoodeng.2016.02.017 doi: 10.1016/j.jfoodeng.2016.02.017
|
| [26] |
Verdú S, Vásquez F, Grau R, et al. (2016) Detection of adulterations with different grains in wheat products based on the hyperspectral image technique: The specific cases of flour and bread. Food Control 62: 373–380. http://dx.doi.org/10.1016/j.foodcont.2015.11.002 doi: 10.1016/j.foodcont.2015.11.002
|
| [27] |
Florián-Huamán J, Cruz-Tirado JP, Barbin DF, et al. (2022) Detection of nutshells in cumin powder using NIR hyperspectral imaging and chemometrics tools. J Food Compos Anal 108: 104407. https://doi.org/10.1016/j.jfca.2022.104407 doi: 10.1016/j.jfca.2022.104407
|
| [28] |
He HJ, Chen Y, Li G, et al. (2023) Hyperspectral imaging combined with chemometrics for rapid detection of talcum powder adulterated in wheat flour. Food Control 144: 109378. https://doi.org/10.1016/j.foodcont.2022.109378 doi: 10.1016/j.foodcont.2022.109378
|
| [29] |
Zhu J, Rao Z, Ji H (2024) Fast and simultaneous detection of wheat kernel adulteration using hyperspectral imaging technology and deep convolutional neural network. J Food Saf 44: e13133. https://doi.org/10.1111/jfs.13133 doi: 10.1111/jfs.13133
|
| [30] |
Kasemsumran S, Boondaeng A, Ngowsuwan K, et al. (2023) Mid-infrared and near-infrared spectroscopies to classify improper fermentation of pineapple wine. Chem Pap 77: 335–349. https://doi.org/10.1007/s11696-022-02472-x doi: 10.1007/s11696-022-02472-x
|
| [31] |
Lee NY, Na IS, Lee KW, et al. (2024) Detection of physical hazards from fruit processed products using hyperspectral imaging and prediction based on PLS-DA and logistic regression machine learning models. Appl Food Res 4: 100506. https://doi.org/10.1016/j.afres.2024.100506 doi: 10.1016/j.afres.2024.100506
|
| [32] |
Yang Z, Lu X, Chen L (2025) Discriminating the adulteration of varieties and misrepresentation of vintages of Pu'er tea based on Fourier transform near infrared diffuse reflectance spectroscopy. Front Chem 13: 1546702. https://doi.org/10.3389/fchem.2025.1546702 doi: 10.3389/fchem.2025.1546702
|
| [33] |
Beć KB, Grabska J, Huck CW (2020) Near-infrared spectroscopy in bio-applications. Molecules 25: 2948. https://doi.org/10.3390/molecules.25122948 doi: 10.3390/molecules.25122948
|
| [34] |
Wang Y, Lv Y, Wei Y, et al. (2018) Identification of maize haploid kernels based on hyperspectral imaging technology. Comput Electron Agr 153: 188–195. https://doi.org/10.1016/j.compag.2018.08.012. doi: 10.1016/j.compag.2018.08.012
|
| [35] |
Khamsopha D, Woranitta S, Teerachaichayut S (2021) Utilizing near infrared hyperspectral imaging for quantitatively predicting adulteration in tapioca starch. Food Control 123: 107781. https://doi.org/10.1016/j.foodcont.2020.107781 doi: 10.1016/j.foodcont.2020.107781
|
| [36] |
Jahani R, Yazdanpanah H, Van Ruth SM, et al. (2020) Novel application of near-infrared spectroscopy and chemometrics approach for detection of lime juice adulteration. Iran J Pharm Res 19: 34–44. https://doi.org/10.22037/ijpr.2019.112328.13686 doi: 10.22037/ijpr.2019.112328.13686
|
| [37] |
Fodor M, Matkovits A, Benes EL, et al. (2024) The role of near-infrared spectroscopy in food quality assurance: A review of the past two decades. Foods 13: 3501. https://doi.org/10.3390/foods13213501 doi: 10.3390/foods13213501
|
| [38] |
Saha D, Senthilkumar T, Singh CB, et al. (2023) Quantitative detection of metanil yellow adulteration in chickpea flour using line-scan near-infrared hyperspectral imaging with partial least square regression and one-dimensional convolutional neural network. J Food Compos Anal 120: 105290. https://doi.org/10.1016/j.jfca.2023.105290 doi: 10.1016/j.jfca.2023.105290
|