HYPERSPECTRAL IDENTIFICATION OF COMPOSITE CHINESE SAUSAGES
DOI:
https://doi.org/10.31548/humanhealth.1.2026.154Keywords:
spectroscopic analysis; complex product structure; modeling; principal component analysis; classification; cross-validationAbstract
With the increasing diversity of compound sausage types, the development of a rapid, accurate, and non-destructive identification model has become essential. The aim is to develop a robust model that operates without damaging the sausage surface or structure, meeting real-time, lossless, and high-throughput recognition requirements in practical applications. “Lossless recognition” refers to non-destructive analysis of surface spectra using hyperspectral imaging technology – without chemical treatment, grinding, or slicing into the interior of the sausage. Hyperspectral imaging technology was employed to collect spectral data over 400 – 1000 nm for eight types of compound sausages. For each image, 50 sampling regions were randomly selected, and the average reflectance values were extracted. First, three preprocessing algorithms – Multiplicative Scatter Correction (MSC), Savitzky-Golay smoothing (SG), and Neighborhood Averaging (NA) – were applied to the raw hyperspectral data. To enhance modeling efficiency, Principal Component Analysis (PCA) was used to reduce the dimensionality of the original 328 spectral bands, retaining the first 10 principal components, which explained over 95% of the total variance, as the new feature set. The classification results demonstrate that hyperspectral imaging combined with machine learning algorithms can effectively distinguish between the eight compound sausage types. Among all methods, the SVM model exhibited the highest classification accuracy, highlighting its excellent discriminative ability and robustness in high-dimensional hyperspectral data analysis. Classification models that combined MSC preprocessing with any of the three algorithms achieved prediction accuracies of over 99%.
Received 30.12.2025
Accepted 1.03.2026
References
Das, M., Sharma, P., & Kumar, S. (2025). Machine learning in hyperspectral imaging for food safety and quality monitoring: A comprehensive review. Artificial Intelligence in Agriculture, 11, 35–52. https://doi.org/10.1016/j.aiia.2025.02.003
Dong, X., Guo, P., & Xu, P. (2017). Prediction of total viable count in sausages using hyperspectral imaging combined with an iterative decision tree. Modern Food Science and Technology, 33(7), 308–314. https://doi.org/10.13982/j.mfst.1673-9078.2017.7.043
Feng, T., Wang, X., Wang, H., Song, S., & Sun, J. (2020). Enhancement of nutritional value and functional properties of compound sausages through incorporation of edible mushrooms and coarse cereals. Journal of Food Science and Technology, 57(8), 3023–3034.
Huang, L., Zhao, J., Chen, Q., & Zhang, Y. (2023). Rapid detection of adulteration in minced mutton using hyperspectral imaging combined with chemometric methods. Chemosensors, 11(2), 136. https://doi.org/10.3390/chemosensors11020136
Jo, K., Lee, S., Jeong, S.-K., & Lee, D.-H. (2024). Hyperspectral imaging-based assessment of fresh meat quality: Progress and applications. Microchemical Journal, 197, 109785. https://doi.org/10.1016/j.microc.2023.109785
Kalinichenko, A., & Arseniyeva, L. (2020). An electronic nose combined with chemometric approaches to assess the authenticity and adulteration of sausages by soy protein. Sensors and Actuators B: Chemical, 303, 127250. https://doi.org/10.1016/j.snb.2020.127250
Kim, M., Park, J., & Lee, S. (2024). Early detection of beef quality indicators using hyperspectral imaging and spectral modeling. Food Control, 158, 110137. https://doi.org/10.1016/j.foodcont.2023.110137
Liu, Y., Pu, H., & Sun, D.-W. (2017). Hyperspectral imaging technique for evaluating food quality and safety: A review. Chemosensors, 5(4), 28. https://doi.org/10.3390/chemosensors5040028
Liu, Y., Zhang, M., & Wang, D. (2021). Consumer perception and market potential of novel healthy meat products: A case study of compound sausages in China. Food Control, 130, 108356. https://doi.org/10.1016/j.foodcont.2021.108356
Mushtruk, M., Palamarchuk, I., Palamarchuk, V., Petrychenko, I., & Pylypchuk, O. (2023). Mathematical modelling of quality assessment of cooked sausages with the addition of vegetable additives. Potravinarstvo Slovak Journal of Food Sciences, 17, 242–255.
Nikzadfar, M., Rahman, A., & Lee, J. (2024). Hyperspectral imaging aiding artificial intelligence for food quality and safety control: A review. Applied Sciences, 14(21), 9821. https://doi.org/10.3390/app14219821
Palamarchuk, I., Fu, Y., Zhuravel, D., Petrychenko, I., Blishch, R., Holovatyuk, A., Domin, O., & Kostiuk, T. (2024). Spectroscopic assessment and quantitative analysis of the trace element composition of vegetable additives to meat products. Potravinarstvo Slovak Journal of Food Sciences, 18, 480–496. https://doi.org/10.5219/1965
Palamarchuk, I., Zavialov, V., Fu, Y., Palamarchuk, V., & Popova, N. (2025). Mathematical modeling by the factorial area method in evaluating the quality characteristics of the studied samples. In Advances in design, simulation and manufacturing processes VIII (pp. 147–156). https://doi.org/10.1007/978-3-031-95218-0_13
Rogers, M. (2023). Wavelength and texture feature selection for hyperspectral food analysis: A review. Journal of Food Measurement and Characterization, 17, 5120–5136. https://doi.org/10.1007/s11694-023-02044-x
Son, W.-Y., Kang, M.-H., Hwang, J., Kim, J.-H., Dixit, Y., & Kim, H.-W. (2024). Hyperspectral imaging combined with machine learning can be used for rapid and non-destructive monitoring of residual nitrite in emulsified pork sausages. Foods, 13, 3173. https://doi.org/10.3390/foods13193173
Su, W.-H., & Sun, D.-W. (2018). Fourier transform infrared, Raman, and hyperspectral imaging techniques for quality determinations of powdery foods: A review. Comprehensive Reviews in Food Science and Food Safety, 17(4), 104–120.
Wang, Q., & He, Y. (2019). Rapid and nondestructive classification of Cantonese sausage degree using hyperspectral images. Applied Sciences, 9(5), 822. https://doi.org/10.3390/app9050822
Wang, Y., Yang, Z., & Cheng, J. (2020). Application progress of multispectral imaging for food nutritional quality detection. Science and Technology of Food Industry, 41(4), 339–347. https://doi.org/10.13386/j.issn1002-0306.2020.04.058
Xia, S. J., Yang, C. Y., Zhou, C. G., et al. (2021). Review of the application of common machine learning methods in the field of traditional Chinese medicine diagnosis. Journal of Guangzhou University of Traditional Chinese Medicine, 38(4), 826–831. https://doi.org/10.13359/j.cnki.gzxbtcm.2021.04.026
Xu, Z., Li, Y., Wang, H., & Chen, Y. (2024). Research progress on the quality detection of livestock and poultry meat using machine vision and hyperspectral technology. Foods, 13(3), 469. https://doi.org/10.3390/foods13030469
Yang, C., Zhao, Y., & Liu, H. (2025). Deep learning hyperspectral imaging: A rapid and reliable alternative for food quality and safety evaluation. Journal of Agricultural and Food Chemistry, 73, 14562–14575. https://doi.org/10.1021/acs.jafc.4c11492
Yang, J. F., Qiao, P. R., Li, Y. M., et al. (2019). A review of machine learning classification problems and algorithms. Statistics and Decision, 35(6), 36–40. https://doi.org/10.13546/j.cnki.tjyjc.2019.06.009
Yi, X., Zhang, Y., & Chen, L. (2025). Advances in hyperspectral imaging for multi-attribute analysis of meat quality. Food Chemistry, 435, 137558. https://doi.org/10.1016/j.foodchem.2024.137558
Zhao, J., Dong, Q., Chen, P., et al. (2022). Application progress of hyperspectral imaging technology in the rapid detection of microbial contamination in animal-derived food. Science and Technology of Food Industry, 43(7), 467–473. https://doi.org/10.13386/j.issn1002-0306.2021050236
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Human and nation's health
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All materials are distributed under the terms of the Creative Commons Attribution 4.0 International Public License, which allows others to extend the article with acknowledgment of authorship and first publication in this journal.
