Hyperspectral Imaging Aiding Artificial Intelligence: A Reliable Approach for Food Qualification and Safety
Source abstract
Abstract
Hyperspectral imaging (HSI) is one of the non-destructive quality assessment methods providing both spatial and spectral information. HSI in food quality and safety can detect the presence of contaminants, adulterants, and quality attributes, such as moisture, ripeness, and microbial spoilage, in a non-destructive manner by analyzing spectral signatures of food components in a wide range of wavelengths with speed and accuracy. However, analyzing HSI data can be quite complicated and time consuming, in addition to needing some special expertise. Artificial intelligence (AI) has shown immense promise in HSI for the assessment of food quality because it is so powerful at coping with irrelevant information, extracting key features, and building calibration models. This review has shown various machine learning (ML) approaches applied to HSI for quality and safety control of foods. It covers the basic concepts of HSI, advanced preprocessing methods, and strategies for wavelength selection and machine learning methods. The application of HSI to AI increases the speed with which food safety and quality can be inspected. This happens through automation in contaminant detection, classification, and prediction of food quality attributes. So, it can enable decisions in real-time by reducing human error at food inspection. This paper outlines their benefits, challenges, and potential improvements while again assessing the validity and practical usability of HSI technologies in developing reliable calibration models for food quality and safety monitoring. The review concludes that HSI integrated with state-of-the-art AI techniques has good potential to significantly improve the assessment of food quality and safety, and that various ML algorithms have their strengths, and contexts in which they are best applied.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Spectroscopy and Chemometric Analyses · Spectroscopy Techniques in Biomedical and Chemical Research · Advanced Chemical Sensor Technologies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Food Industry, University of Padua, 35122 Padua, Italy
National Centre of Excellence for Food Engineering, Sheffield Hallam University, Howard Street, Sheffield S1 1WB, UK
DAFE, Department of Agricultural, Forestry, Food and Environmental Sciences, University of Basilicata, 85100 Potenza, Italy
References (100+)
Show source-provided references
1. Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review10.1016/j.crfs.2021.01.002 ↗
2. Potential application of hyperspectral imaging in food grain quality inspection, evaluation and control during bulk storage
3. Guo, Z., Yang, J., and Liu, S. (2023). Research on Lightweight Model for Rapid Identification of Chunky Food Based on Machine Vision. Appl. Sci., 13.10.3390/app13158781 ↗
4. Jang, S.H., Moon, S.P., Kim, Y.J., and Lee, S.H. (2023). Development of potato mass estimation system based on deep learning. Appl. Sci., 13.10.3390/app13042614 ↗
5. Advances in machine learning and hyperspectral imaging in the food supply chain10.1007/s12393-022-09322-2 ↗
6. Recent advances in muscle food safety evaluation: Hyperspectral imaging analyses and applications10.1080/10408398.2022.2121805 ↗
7. Faqeerzada, M.A., Perez, M., Lohumi, S., Lee, H., Kim, G., Wakholi, C., Joshi, R., and Cho, B.K. (2020). Online application of a hyperspectral imaging system for the sorting of adulterated almonds. Appl. Sci., 10.10.3390/app10186569 ↗
8. A review of recent studies employing hyperspectral imaging for the determination of food adulteration10.3390/photochem1020008 ↗
9. Spectroscopic food adulteration detection using machine learning: Current challenges and future prospects10.1016/j.tifs.2024.104377 ↗
10. Matenda, R.T., Rip, D., Marais, J., and Williams, P.J. (2024). Exploring the potential of hyperspectral imaging for microbial assessment of meat: A review. Spectrochim. Acta Part A Mol. Biomol. Spectrosc., 315.10.1016/j.saa.2024.124261 ↗
11. Hyperspectral imaging combined with fluorescence for the prediction of microbial growth in chicken breasts under different packaging conditions10.1016/j.lwt.2023.114727 ↗
12. Vignati, S., Tugnolo, A., Giovenzana, V., Pampuri, A., Casson, A., Guidetti, R., and Beghi, R. (2023). Hyperspectral Imaging for Fresh-Cut Fruit and Vegetable Quality Assessment: Basic Concepts and Applications. Appl. Sci., 13.10.3390/app13179740 ↗
13. Torres-Rodríguez, I., Sánchez, M.T., Entrenas, J.A., Vega-Castellote, M., Garrido-Varo, A., and Pérez-Marín, D. (2022). Hyperspectral Imaging for the detection of bitter almonds in sweet almond batches. Appl. Sci., 12.10.3390/app12104842 ↗
14. Ayaz, H., Ahmad, M., Mazzara, M., and Sohaib, A. (2020). Hyperspectral imaging for minced meat classification using nonlinear deep features. Appl. Sci., 10.10.3390/app10217783 ↗
15. Applications of hyperspectral imaging technology in the food industry10.1038/s44287-024-00033-w ↗
16. Deep learning techniques for the exploration of hyperspectral imagery potentials in food and agricultural products10.1016/j.foohum.2024.100365 ↗
17. Advances in infrared spectroscopy and hyperspectral imaging combined with artificial intelligence for the detection of cereals quality10.1080/10408398.2022.2066062 ↗
18. A research review on deep learning combined with hyperspectral Imaging in multiscale agricultural sensing10.1016/j.compag.2023.108577 ↗
19. Assessment of food safety risk using machine learning-assisted hyperspectral imaging: Classification of fungal contamination levels in rice grain
20. Quality detection and variety classification of pecan seeds using hyperspectral imaging technology combined with machine learning10.1016/j.jfca.2024.106248 ↗
21. Ekramirad, N., Doyle, L., Loeb, J., Santra, D., and Adedeji, A.A. (2024). Hyperspectral Imaging and Machine Learning as a Nondestructive Method for Proso Millet Seed Detection and Classification. Foods, 13.10.3390/foods13091330 ↗
22. Predicting gypsum tofu quality from soybean seeds using hyperspectral imaging and machine learning10.1016/j.foodcont.2024.110357 ↗
23. Determination of quality and maturity of processing tomatoes using near-infrared hyperspectral imaging with interpretable machine learning methods10.1016/j.lwt.2023.114861 ↗
24. Li, C., He, M., Cai, Z., Qi, H., Zhang, J., and Zhang, C. (2023). Hyperspectral imaging with machine learning approaches for assessing soluble solids content of tribute citru. Foods, 12.10.3390/foods12020247 ↗
25. Rapid and nondestructive identification of rice storage year using hyperspectral technology10.1016/j.foodcont.2024.110850 ↗
26. Yang, K., Zhao, M., and Argyropoulos, D. (2025). Machine learning based framework for the detection of mushroom browning using a portable hyperspectral imaging system. Postharvest Biol. Technol., 219.10.1016/j.postharvbio.2024.113247 ↗
27. Rapid and non-destructive quality grade assessment of Hanyuan Zanthoxylum bungeanum fruit using a smartphone application integrating computer vision systems and convolutional neural networks10.1016/j.foodcont.2024.110844 ↗
28. Early bruise detection, classification and prediction in strawberry using Vis-NIR hyperspectral imaging10.1016/j.foodcont.2024.110794 ↗
29. Qualitative and quantitative analysis of Nanfeng mandarin quality based on hyperspectral imaging and deep learning10.1016/j.foodcont.2024.110831 ↗
30. Francis, J., George, S., Devassy, B.M., and George, S.N. (2025). Development of a unified framework of low-rank approximation and deep neural networks for predicting the spatial variability of SSC inSpania’watermelons using vis/NIR hyperspectral imaging. Postharvest Biol. Technol., 219.10.1016/j.postharvbio.2024.113222 ↗
31. Bai, R., Zhou, J., Wang, S., Zhang, Y., Nan, T., Yang, B., Zhang, C., and Yang, J. (2024). Identification and classification of Coix seed storage years based on hyperspectral imaging technology combined with deep learning. Foods, 13.10.3390/foods13030498 ↗
32. Application of hyperspectral imaging assisted with integrated deep learning approaches in identifying geographical origins and predicting nutrient contents of Coix seeds10.1016/j.foodchem.2022.134503 ↗
33. Optimizing starch content prediction in kudzu: Integrating hyperspectral imaging and deep learning with WGAN-GP10.1016/j.foodcont.2024.110762 ↗
34. Deep learning in food authenticity: Recent advances and future trends10.1016/j.tifs.2024.104344 ↗
35. An overview of pre-processing methods available for hyperspectral imaging applications10.1016/j.microc.2023.109129 ↗
36. Application of hyperspectral technology in detection of agricultural products and food: A Review10.1002/fsn3.1852 ↗
37. Visible/near-infrared Spectroscopy and Hyperspectral Imaging Facilitate the Rapid Determination of Soluble Solids Content in Fruits10.1007/s12393-024-09374-6 ↗
38. A Systematized Review on the Applications of Hyperspectral Imaging for Quality Control of Potatoes
39. Hyperspectral imaging systems for rapid assessment of moisture and chromaticity of foods undergoing drying: Principles, applications, challenges, and future trends10.1016/j.compag.2024.109101 ↗
40. FastHyMix: Fast and parameter-free hyperspectral image mixed noise removal10.1109/TNNLS.2021.3112577 ↗
41. An overview on the applications of typical non-linear algorithms coupled with NIR spectroscopy in food analysis10.1007/s12393-020-09210-7 ↗
42. Nondestructive discrimination of analogous density foreign matter inside soy protein meat semi-finished products based on transmission hyperspectral imaging10.1016/j.foodchem.2023.135431 ↗
43. Identification of geographical origin of beef by visible-near infrared hyperspectral recovery from color images10.1016/j.jfca.2024.106622 ↗
44. Robust hyperspectral image classification using generative adversarial networks10.1016/j.ins.2024.120452 ↗
45. A comparative analysis of hybrid SVM and LS-SVM classification algorithms to identify dried wolfberry fruits quality based on hyperspectral imaging technology10.1111/jfpp.16320 ↗
46. Rapid and noninvasive sensory analyses of food products by hyperspectral imaging: Recent application developments10.1016/j.tifs.2021.02.044 ↗
47. Nondestructive detection for egg freshness grade based on hyperspectral imaging technology10.1111/jfpe.13422 ↗
48. Hyperspectral imaging combined with convolutional neural network for accurately detecting adulteration in Atlantic salmon10.1016/j.foodcont.2022.109573 ↗
49. Oxby, P.W. (2021). An Optimal Weighting Function for the Savitzky-Golay Filter. arXiv.
50. Savitzky–Golay filter-based PLL: Modeling and performance validation10.1109/TIM.2022.3196946 ↗
51. An optimal Savitzky–Golay derivative filter with geophysical applications: An example of self-potential data10.1111/1365-2478.12892 ↗
52. Advanced Low-Pass Filters for Signal Processing: A Comparative Study on Gaussian, Mittag-Leffler, and Savitzky-Golay Filters10.18280/mmep.110713 ↗
53. Application of the Savitzky-Golay filter in multi-spectral signal processing10.62420/selco.v1i1.5 ↗
54. Agustika, D.K., Nawawi, M.R., Prasetyowati, R., Hidayat, S.H., Iliescu, D.D., and Leeson, M.S. (2022, January 24–26). Savitzky-Golay Parameter Optimization by using Linear Discriminant Analysis for FTIR Spectra. Proceedings of the 2022 IEEE 7th Forum on Research and Technologies for Society and Industry Innovation (RTSI), Paris, France.10.1109/RTSI55261.2022.9905171 ↗
55. Searching for Alternatives to the Savitzky–Golay Filter in the Spectral Processing Domain10.1177/00037028231154278 ↗
56. Prediction of water content in biscuits using near infrared hyperspectral imaging spectroscopy and chemometrics10.1177/0967033520902538 ↗
57. Estimation of water content in corn leaves using hyperspectral data based on fractional order Savitzky-Golay derivation coupled with wavelength selection10.1016/j.compag.2021.105989 ↗
58. Rapid determination of chemical compositions in chicken flesh by mining hyperspectral data10.1016/j.jfca.2022.105069 ↗
59. A non-destructive determination of protein content in potato flour noodles using near-infrared hyperspectral imaging technology10.1016/j.infrared.2023.104595 ↗
60. Prediction of soluble solid content of Agaricus bisporus during ultrasound-assisted osmotic dehydration based on hyperspectral imaging10.1016/j.lwt.2020.109030 ↗
61. Innovative strategies for protein content determination in dried laver (Porphyra spp.): Evaluation of preprocessing methods and machine learning algorithms through short-wave infrared imaging10.1016/j.fochx.2024.101763 ↗
62. The O-PLS methodology for orthogonal signal correction—Is it correcting or confusing?10.1002/cem.2884 ↗
63. The choice of scaling technique matters for classification performance10.1016/j.asoc.2022.109924 ↗
64. Hyperspectral imaging as a non-destructive technique for estimating the nutritional value of food10.1016/j.crfs.2024.100799 ↗
65. Yi, L., Zhao, Q., and Xu, Z. (2024). Hyperspectral Image Denoising by Pixel-Wise Noise Modeling and TV-Oriented Deep Image Prior. Remote Sens., 16.10.3390/rs16152694 ↗
66. Detection of spinach juice residues on stainless steel surfaces using VNIR hyperspectral images10.1007/s42853-021-00097-8 ↗
67. Essential processing methods of hyperspectral images of agricultural and food products10.1016/j.chemolab.2020.103936 ↗
68. Xue, T., Wang, Y., and Deng, X. (2022). A Novel Method for Fast Kernel Minimum Noise Fraction Transformation in Hyperspectral Image Dimensionality Reduction. Remote Sens., 14.10.3390/rs14071737 ↗
69. Hyperspectral imagery classification with minimum noise fraction 2D spatial filtering and SVM10.1142/S0219691322500254 ↗
70. Generic models for rapid detection of vanillin and melamine adulterated in infant formulas from diverse brands based on near-infrared hyperspectral imaging10.1016/j.infrared.2021.103745 ↗
71. Feature reduction of hyperspectral image for classification10.1080/14498596.2020.1770137 ↗
72. Early decay detection in fruit by hyperspectral imaging–Principles and application potential10.1016/j.foodcont.2023.109830 ↗
73. Zhang, W., Bai, X., Guo, J., Yang, J., Yu, B., Chen, J., Wang, J., Zhao, D., Zhang, H., and Liu, M. (2024). Hyperspectral imaging for in situ visual assessment of Industrial-Scale ginseng. Spectrochim. Acta Part A: Mol. Biomol. Spectrosc., 321.10.1016/j.saa.2024.124700 ↗
74. Feasibility of near infrared and Raman hyperspectral imaging combined with multivariate analysis to assess binary mixtures of food powders10.1016/j.powtec.2018.06.025 ↗
75. Total lipid prediction in single intact cocoa beans by hyperspectral chemical imaging10.1016/j.foodchem.2020.128663 ↗
76. Edwards, K., Hoffman, L.C., Manley, M., and Williams, P.J. (2023). Raw Beef Patty Analysis Using Near-Infrared Hyperspectral Imaging: Identification of Four Patty Categories. Sensors, 23.10.3390/s23020697 ↗
77. Vis-NIR hyperspectral imaging along with Gaussian process regression to monitor quality attributes of apple slices during drying10.1016/j.lwt.2021.112297 ↗
78. Development of NIR-HSI and chemometrics process analytical technology for drying of beef jerky10.1016/j.ifset.2021.102611 ↗
79. Vis-NIR hyperspectral imaging for the classification of bacterial foodborne pathogens based on pixel-wise analysis and a novel CARS-PSO-SVM model10.1016/j.infrared.2020.103220 ↗
80. Chen, Z., Wang, Q., Zhang, H., and Nie, P. (2021). Hyperspectral imaging (HSI) technology for the non-destructive freshness assessment of pearl gentian grouper under different storage conditions. Sensors, 21.10.3390/s21020583 ↗
81. Sayed, A.H. (2022). Inference and Learning from Data: Learning, Cambridge University Press.10.1017/9781009218276 ↗
82. Shelf life estimation and kinetic degradation modeling of chia seeds (Salvia hispanica) using principal component analysis based on NIR-hyperspectral imaging10.1016/j.foodcont.2020.107777 ↗
83. Visualized detection of quality change of cooked beef with condiments by hyperspectral imaging technique10.1007/s10068-022-01115-x ↗
84. A rapid classification method for sorghum seed varieties based on HSI and PCA-SICNN algorithm10.1016/j.microc.2024.111095 ↗
85. An improved successive projections algorithm version to variable selection in multiple linear regression10.1016/j.aca.2023.341560 ↗
86. Soluble solid content and firmness index assessment and maturity discrimination of Malus micromalus Makino based on near-infrared hyperspectral imaging10.1016/j.foodchem.2021.131013 ↗
87. Rapid evaluation of freshness of largemouth bass under different thawing methods using hyperspectral imaging10.1016/j.foodcont.2021.108023 ↗
88. Jiang, H., Yang, Y., and Shi, M. (2021). Chemometrics in tandem with hyperspectral imaging for detecting authentication of raw and cooked mutton rolls. Foods, 10.10.3390/foods10092127 ↗
89. Assessing canopy nitrogen and carbon content in maize by canopy spectral reflectance and uninformative variable elimination10.1016/j.cj.2021.12.005 ↗
90. Zhong, Q., Zhang, H., Tang, S., Li, P., Lin, C., Zhang, L., and Zhong, N. (2023). Feasibility Study of Combining Hyperspectral Imaging with Deep Learning for Chestnut-Quality Detection. Foods, 12.10.3390/foods12102089 ↗
91. Non-destructive determination of fat and moisture contents in Salmon (Salmo salar) fillets using near-infrared hyperspectral imaging coupled with spectral and textural features10.1016/j.jfca.2020.103567 ↗
92. Integration of spectral and image features of hyperspectral imaging for quantitative determination of protein and starch contents in maize kernels10.1016/j.compag.2024.108718 ↗
93. Yu, H.D., Yun, Y.H., Zhang, W., Chen, H., Liu, D., Zhong, Q., Chen, W., and Chen, W. (2020). Three-step hybrid strategy towards efficiently selecting variables in multivariate calibration of near-infrared spectra. Spectrochim. Acta Part A Mol. Biomol. Spectrosc., 224.10.1016/j.saa.2019.117376 ↗
94. VIS/NIR hyperspectral imaging with artificial neural networks to evaluate the content of thiobarbituric acid reactive substances in beef muscle10.1016/j.jfoodeng.2023.111500 ↗
95. Nondestructive freshness evaluation of mackerel fish using Vis/NIR hyperspectral imaging and multivariate analysis10.1016/j.jfoodeng.2024.112086 ↗
96. Nondestructive prediction and visualization of total flavonoids content in Cerasus Humilis fruit during storage periods based on hyperspectral imaging technique10.1111/jfpe.13807 ↗
97. Flash drought: Review of concept, prediction and the potential for machine learning, deep learning methods10.1029/2022EF002723 ↗
98. Machine learning methods to predict cadmium (Cd) concentration in rice grain and support soil management at a regional scale10.1016/j.fmre.2023.02.016 ↗
99. James, G., Witten, D., Hastie, T., Tibshirani, R., and Taylor, J. (2023). An Introduction to Statistical Learning: With Applications in Python, Springer Nature.10.1007/978-3-031-38747-0 ↗
100. A green method for the prediction of color in sugar using fingerprint signatures based on digital images and chemometrics10.1016/j.microc.2024.111120 ↗