Deep Learning-Enabled Hyperspectral Classification of Zhambons

Shojaeilangari, Seyedehsamaneh; Kishani Farahani, Esmat; Basiri, Alireza

doi:10.22104/ift.2025.8010.2255

Deep Learning-Enabled Hyperspectral Classification of Zhambons

Document Type : Research Article

Authors

¹ Biomedical Engineering Group, Department of Electrical Engineering and Information Technology, Iranian Research Organization for Science and Technology (IROST)

² Information Technology and Intelligent Systems Group, Department of Electrical Engineering and Information Technology, Iranian Research Organization for Science and Technology

³ Department of Chemical Technologies, Iranian Research Organization for Science and Technology

10.22104/ift.2025.8010.2255

Abstract

Food authenticity is a crucial aspect of consumer protection, food safety, and quality assurance. Conventional methods for meat authentication often require destructive, time-consuming, or labor-intensive processes. Hyperspectral imaging, which combines imaging and spectroscopy, has emerged as a non-destructive alternative for food classification. This study investigates the application of hyperspectral imaging for differentiating between beef, chicken, and turkey zhambons using one-dimensional convolutional neural networks and long short-term memory networks. Following preprocessing—including segmentation, noise reduction, and spatial averaging—spectral signatures were extracted and classified using deep learning models and then compared to traditional machine learning approaches. The long short-term architecture demonstrated superior performance by effectively modeling sequential spectral dependencies, achieving 99.94% accuracy in the binary classification of chicken versus beef and 98.12% accuracy in the three-class problem (beef, chicken, and turkey zhambons). The findings highlight the potential of hyperspectral imaging combined with machine learning approaches as an efficient tool for processed meat authentication.

Graphical Abstract

Highlights

Non-destructive meat authentication using hyperspectral imaging (HSI)
Deep learning models (1D-CNN and LSTM) classify spectral signatures
LSTM achieved 99.94% (binary) and 98.12% (three-class) classification accuracy
HSI with deep learning enables rapid and reliable meat fraud detection

Keywords

Main Subjects

Food science and technology

References

[1] Sun, X., Wang, S., & Jia, W. (2024). Research progress of electronic nose and near-infrared spectroscopy in meat adulteration detection. Chemosensors, 12(3), Article 35. https://doi.org/10.3390/chemosensors12030035

[2] Yu, Y., et al. (2025). Meat species authentication using portable hyperspectral imaging. Frontiers in Nutrition, 12, Article 1577642. https://doi.org/10.3389/fnut.2025.1577642

[3] Arnalds, T., McElhinney, J., Fearn, T., & Downey, G. (2004). A hierarchical discriminant analysis for species identification in raw meat by visible and near infrared spectroscopy. Journal of Near Infrared Spectroscopy, 12(3), 183–188. https://doi.org/10.1255/jnirs.425

[4] Mortas, M., Awad, N., & Ayvaz, H. (2022). Adulteration detection technologies used for halal/kosher food products: An overview. Food Science and Biotechnology Reviews, 1, Article 0157. https://doi.org/10.1007/s44187-022-00015-7

[5] Li, Y., Wang, H., Yang, Z., Wang, X., Wang, W., & Hui, T. (2024). Rapid non-destructive detection technology in the field of meat tenderness: A review. Foods, 13(10), Article 1512. https://doi.org/10.3390/foods13101512

[6] Wang, Y., Teo, E., Lin, K. J., Wu, Y., Chan, J. S. H., & Tan, L. K. (2023). Quantification of pork, chicken, beef, and sheep contents in meat products using duplex real-time PCR. Foods, 12(15), Article 2971. https://doi.org/10.3390/foods12152971

[7] Chaudhary, V., Kajla, P., Dewan, A., Pandiselvam, R., Socol, C. T., & Maerescu, C. M. (2022). Spectroscopic techniques for authentication of animal origin foods. Frontiers in Nutrition, 9, Article 979205. https://doi.org/10.3389/fnut.2022.979205

[8] Pirhadi, S., Shariatifar, N., & Pirhadi, M. (2024). Identification of animal species in meat products using chemometrics-based high-performance liquid chromatography: A systematic review. Journal of Biochemicals and Phytomedicine, 3(1), 53–58. https://doi.org/10.34172/jbp.2024.11

[9] Lu, B., Dao, P. D., Liu, J., He, Y., & Shang, J. (2020). Recent advances of hyperspectral imaging technology and applications in agriculture. Remote Sensing, 12(16), Article 2659. https://doi.org/10.3390/rs12162659

[10] Ma, J., Sun, D.-W., Pu, H., Cheng, J.-H., & Wei, Q. (2019). Advanced techniques for detecting protein misfolding and aggregation in vitro and in vivo. Annual Review of Food Science and Technology, 10, 21–47. https://doi.org/10.1146/annurev-food-032818-121232

[11] Pu, H., Sun, D.-W., Ma, J., & Cheng, J.-H. (2023). Recent advances in muscle food safety evaluation: Hyperspectral imaging analyses and applications. Critical Reviews in Food Science and Nutrition, 63(18), 4665–4688. https://doi.org/10.1080/10408398.2022.2121805

[12] Zhang, Y., Zheng, M., Zhu, R., & Ma, R. (2022). Adulteration discrimination and analysis of fresh and frozen-thawed minced adulterated mutton using hyperspectral images combined with recurrence plot and convolutional neural network. Meat Science, 192, Article 108900. https://doi.org/10.1016/j.meatsci.2022.108900

[13] Edwards, K., Hoffman, L. C., Manley, M., & Williams, P. J. (2023). Raw beef patty analysis using near-infrared hyperspectral imaging: Identification of four patty categories. Sensors, 23(2), Article 697. https://doi.org/10.3390/s23020697

[14] Bai, Z., et al. (2024). Establishment and comparison of in situ detection models for foodborne pathogen contamination on mutton based on SWIR-HSI. Frontiers in Nutrition, 11, Article 1325934. https://doi.org/10.3389/fnut.2024.1325934

[15] Jiang, H., Yang, Y., & Shi, M. (2021). Chemometrics in tandem with hyperspectral imaging for detecting authentication of raw and cooked mutton rolls. Foods, 10(9), Article 2127. https://doi.org/10.3390/foods10092127

[16] Sentandreu, M. Á., & Sentandreu, E. (2014). Authenticity of meat products: Tools against fraud. Food Research International, 60, 19–29. https://doi.org/10.1016/j.foodres.2014.03.030

[17] Kamruzzaman, M., Sun, D.-W., ElMasry, G., & Allen, P. (2013). Fast detection and visualization of minced lamb meat adulteration using NIR hyperspectral imaging and multivariate image analysis. Talanta, 103, 130–136. https://doi.org/10.1016/j.talanta.2012.10.020

[18] Al-Sarayreh, M., Reis, M. M., Yan, W. Q., & Klette, R. (2018). Detection of red-meat adulteration by deep spectral–spatial features in hyperspectral images. Journal of Imaging, 4(5), Article 63. https://doi.org/10.3390/jimaging4050063

[19] Zhu, H., Gowen, A., Feng, H., Yu, K., & Xu, J. L. (2020). Deep spectral-spatial features of near infrared hyperspectral images for pixel-wise classification of food products. Sensors, 20(18), Article 5322. https://doi.org/10.3390/s20185322

[20] Xiong, Z., Sun, D.-W., Zeng, X. A., & Xie, A. (2014). Recent developments of hyperspectral imaging systems and their applications in detecting quality attributes of red meats: A review. Journal of Food Engineering, 132, 1–13. https://doi.org/10.1016/j.jfoodeng.2014.02.004

[21] Huang, H., Liu, L., & Ngadi, M. O. (2014). Recent developments in hyperspectral imaging for assessment of food quality and safety. Sensors, 14(4), 7248–7276. https://doi.org/10.3390/s140407248

[22] Jia, W., van Ruth, S., Scollan, N., & Koidis, A. (2022). Hyperspectral imaging (HSI) for meat quality evaluation across the supply chain: Current and future trends. Current Research in Food Science, 5, 1009–1022. https://doi.org/10.1016/j.crfs.2022.05.016

[23] Vercammen, A., et al. (2011). Shelf-life extension of cooked ham model product by high hydrostatic pressure and natural preservatives. Innovative Food Science & Emerging Technologies, 12(4), 407–415. https://doi.org/10.1016/j.ifset.2011.07.009

[24] Liu, Y., Dang, B., Li, Y., Lin, H., & Ma, H. (2016). Applications of Savitzky-Golay filter for seismic random noise reduction. Acta Geophysica, 64(1), 101–124. https://doi.org/10.1515/acgeo-2015-0062

[25] Choi, J. H., et al. (2022). Hyperspectral imaging-based multiple predicting models for functional component contents in Brassica juncea. Agriculture, 12(10), Article 1515. https://doi.org/10.3390/agriculture12101515

[26] Shiddiq, M., Candra, F., Anand, B., & Rabin, M. F. (2024). Neural network with k-fold cross validation for oil palm fruit ripeness prediction. Telkomnika (Telecommunication Computing Electronics and Control), 22(1), 164–174. https://doi.org/10.12928/telkomnika.v22i1.24845

[27] Ruffin, C., King, R. L., & Younan, N. H. (2008). A combined derivative spectroscopy and Savitzky-Golay filtering method for the analysis of hyperspectral data. GIScience & Remote Sensing, 45(1), 1–15. https://doi.org/10.2747/1548-1603.45.1.1

[28] Kingma, D. P., & Ba, J. (2015). Adam: A method for stochastic optimization. In Proceedings of the 3rd International Conference on Learning Representations (ICLR 2015). arXiv:1412.6980. http://arxiv.org/abs/1412.6980

[29] Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press. https://www.deeplearningbook.org

[30] Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018

[31] Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

[32] Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451