Application of Hyperspectral Imaging and Artificial Intelligence for Freshness Assessment of Fish Raw Material during Refrigerated Storage

Introduction: Monitoring the freshness of refrigerated fish remains one of the persistent difficulties in the fish processing industry. Existing reference methods for assessing  refrigerated fish freshness are destructive and inherently unable to reflect the spatial distribution of spoilage markers. Hyperspectral imaging (HSI) has emerged as a powerful non-destructive tool that captures both spatial and spectral data at the pixel scale.

Purpose: The aim of this study is to evaluate the effectiveness of hyperspectral imaging for the binary classification of refrigerated rainbow trout (Oncorhynchus mykiss) fillets into early (≤48 h) and late (>48 h) storage stages.

Materials and Methods: The study was conducted on rainbow trout fillets stored at +2 ± 2 °C for 16 days. Hyperspectral images were acquired using a FigSpec FS-23 camera (spectral range 400–1000 nm). Principal component analysis (PCA) was performed, and a neural network model for binary classification of samples was developed using the TensorFlow framework and the high-level Keras API.

Results: A characteristic nonlinear dynamics of reflectance was observed during storage. PCA showed that the first principal component accounted for 93.8 % of the data variance. The neural network model achieved 90 % accuracy in binary classification of the samples.

Conclusion: The results demonstrate the potential of hyperspectral imaging as a non-destructive tool for assessing fish freshness. The developed method provides accurate discrimination between fresh and non-fresh samples and can be recommended for adoption in industrial incoming inspection protocols.

1. Chen, Z., Wang, Q., Zhang, H., & Nie, P. (2021). Hyperspectral Imaging (HSI) Technology for the Non-Destructive Freshness Assessment of Pearl Gentian Grouper under Different Storage Conditions. Sensors, 21(2), 583. https://doi.org/10.3390/s21020583

2. Cheng, M.-F., Mukundan, A., Karmakar, R., Valappil, M. A. E., Jouhar, J., & Wang, H.-C. (2025). Modern Trends and Recent Applications of Hyperspectral Imaging: A Review. Technologies, 13(5), 170. https://doi.org/10.3390/technologies13050170

3. Cheng, W., Sørensen, K. M., Engelsen, S. B., Sun, D.-W., & Pu, H. (2019). Lipid oxidation degree of pork meat during frozen storage investigated by near-infrared hyperspectral imaging: Effect of ice crystal growth and distribution. Journal of Food Engineering, 263, 311–319. https://doi.org/10.1016/j.jfoodeng.2019.07.013

4. Dai, Q., Cheng, J.-H., Sun, D.-W., Zhu, Z., & Pu, H. (2016). Prediction of total volatile basic nitrogen contents using wavelet features from visible/near-infrared hyperspectral images of prawn (Metapenaeus ensis). Food Chemistry, 197, 257–265. https://doi.org/10.1016/j.foodchem.2015.10.073

5. Dissing, B. S., Nielsen, M. E., Ersbøll, B. K., & Frosch, S. (2011). Multispectral Imaging for Determination of Astaxanthin Concentration in Salmonids. PLoS ONE, 6(5), e19032. https://doi.org/10.1371/journal.pone.0019032

6. García, M. R., Ferez-Rubio, J. A., & Vilas, C. (2022). Assessment and Prediction of Fish Freshness Using Mathematical Modelling: A Review. Foods, 11(15), 2312. https://doi.org/10.3390/foods11152312

7. Hardy, M., Moser, B., Haughey, S. A., & Elliott, C. T. (2024). Does the fish rot from the head? Hyperspectral imaging and machine learning for the evaluation of fish freshness. Chemometrics and Intelligent Laboratory Systems, 245(105059). https://doi.org/10.1016/j.chemolab.2023.105059

8. Jiang, H., Wang, W., Zhuang, H., Yoon, S.-C., Yang, Y., & Zhao, X. (2019). Hyperspectral imaging for a rapid detection and visualization of duck meat adulteration in beef. Food Analytical Methods, 12(10), 2205–2215. https://doi.org/10.1007/s12161-019-01577-6

9. Kamani, M. H., Safari, O., Mortazavi, S. A., Mehraban Sang Atash, M., & Azghadi, N. M. (2017). Using an image processing based technique and predictive models for assessing lipid oxidation in rainbow trout fillet. Food Bioscience, 19, 42-48. https://doi.org/10.1016/j.fbio.2017.05.005

10. Khoshnoudi-Nia, S., & Moosavi-Nasab, M. (2019a). Comparison of various chemometric analysis for rapid prediction of thiobarbituric acid reactive substances in rainbow trout fillets by hyperspectral imaging technique. Food Science & Nutrition, 7(4), 1875–1883. https://doi.org/10.1002/fsn3.1043

11. Khoshnoudi-Nia, S., & Moosavi-Nasab, M. (2019b). Nondestructive Determination of Microbial, Biochemical, and Chemical Changes in Rainbow Trout (Oncorhynchus mykiss) During Refrigerated Storage Using Hyperspectral Imaging Technique. Food Analytical Methods,12, 1635–1647. https://doi.org/10.1007/s12161-019-01494-8

12. Khoshnoudi-Nia, S., & Moosavi-Nasab, M. (2019с). Prediction of various freshness indicators in fish fillets by one multispectral imaging system. Scientific Reports, 9, 14704. https://doi.org/10.1038/s41598-019-51264-z

13. Khoshnoudi-Nia, S., Moosavi-Nasab, M., Nassiri, S. M., & Azimifar, Z. (2018). Determination of Total Viable Count in Rainbow-Trout Fish Fillets Based on Hyperspectral Imaging System and Different Variable Selection and Extraction of Reference Data Methods. Food Analytical Methods, 11(8), 2220–2233. https://doi.org/10.1007/s12161-018-1320-0

14. Khoshtaghaza, M. H., Khojastehnazhand, M., Mojaradi, B., Goodarzi, M., & Saeys, W. (2016). Texture Quality Analysis of Rainbow Trout Using Hyperspectral Imaging Method. International Journal of Food Properties, 19(5), 974-983. https://doi.org/10.1080/10942912.2015.1042111

15. Kim, S. S., Yun, D.-Y., Lee, G., Park, S.-K., Lim, J.-H., Choi, J.-H., Park, K.-J., & Cho, J.-S. (2024). Prediction and Visualization of Total Volatile Basic Nitrogen in Yellow Croaker (Larimichthys polyactis) Using Shortwave Infrared Hyperspectral Imaging. Foods, 13(20), 3228. https://doi.org/10.3390/foods13203228

16. Lu, Y., Saeys, W., Kim, M., Peng, Y., & Lu, R. (2020). Hyperspectral imaging technology for quality and safety evaluation of horticultural products: A review and celebration of the past 20-year progress. Postharvest Biology and Technology, 170, 111318. https://doi.org/10.1016/j.postharvbio.2020.111318

17. Madhubhashini, M. N., Liyanage, C. P., Alahakoon, A. U., & Liyanage, R. P. (2024). Current applications and future trends of artificial senses in fish freshness determination: A review. Journal of Food Science, 89(1), 33–50. https://doi.org/10.1111/1750-3841.16865

18. Moosavi-Nasab, M., Khoshnoudi-Nia, S., Azimifar, Z., & Kamyab, S. (2021). Evaluation of the total volatile basic nitrogen (TVB-N) content in fish fillets using hyperspectral imaging coupled with deep learning neural network and meta-analysis. Scientific Reports, 11(1), 5094. https://doi.org/10.1038/s41598-021-84659-y

19. Naqvi, L. H., Balasubramaniam, B., Li, J., Liu, L., & Li, B. (2025). Four-Dimensional Hyperspectral Imaging for Fruit and Vegetable Grading. Agriculture, 15(15), 1702. https://doi.org/10.3390/agriculture15151702

20. Pulcini, D., Capoccioni, F., Franceschini, S., Martinoli, M., Faccenda, F., Secci, G., Perugini, A., Tibaldi, E., & Parisi, G. (2021). Muscle pigmentation in rainbow trout (Oncorhynchus mykiss) fed diets rich in natural carotenoids from microalgae and crustaceans. Aquaculture, 543. https://agris.fao.org/search/en/providers/122535/records/65de34e46eef00c2ce9ff25b

21. Qin, J., Vasefi, F., Hellberg, R. S., Akhbardeh, A., Isaacs, R. B., Yilmaz, A. G., Hwang, C., Baek, I., Schmidt, W. F., & Kim, M. S. (2020). Detection of fish fillet substitution and mislabeling using multimode hyperspectral imaging techniques. Food Control, 114, 107234. https://doi.org/10.1016/j.foodcont.2020.107234

22. Rye, M. (1991). Prediction of carcass composition in Atlantic salmon by computerized tomography. Aquaculture, 99(1), 35–48. https://doi.org/10.1016/0044-8486(91)90286-G

23. Sun, D., Zhou, C., Hu, J., Li, L., & Ye, H. (2023). Off-flavor profiling of cultured salmonids using hyperspectral imaging combined with machine learning. Food Chemistry, 408, 135166. https://doi.org/10.1016/j.foodchem.2022.135166

24. Tahsin, K.N.; Soad, A.R.; Ali, A.M.; Moury, I.J. (2017). A Review on the Techniques for Quality Assurance of Fish and Fish Products. International Journal of Advanced Research in Science, Engineering and Technology, 4 (7), 4190-4206. https://www.ijarset.com/upload/2017/july/5-IJARSET-KAZI.pdf

25. Wang, C., Wang, S., He, X., Wu, L., Li, Y., & Guo, J. (2020). Combination of spectra and texture data of hyperspectral imaging for prediction and visualization of palmitic acid and oleic acid contents in lamb meat. Meat Science, 169, 108194. https://doi.org/10.1016/j.meatsci.2020.108194

26. Xu, J.-L., Riccioli, C., & Sun, D.-W. (2016). Efficient integration of particle analysis in hyperspectral imaging for rapid assessment of oxidative degradation in salmon fillet. Journal of Food Engineering, 169, 259–271. https://doi.org/10.1016/j.jfoodeng.2015.08.015

27. Yao, K., Sun, J., Zhou, X., Nirere, A., Tian, Y., & Wu, X. (2020). Nondestructive detection for egg freshness grade based on hyperspectral imaging technology. Journal of Food Process Engineering, 43(7) https://doi.org/10.1111/jfpe.13422

28. Zhang, Z.; Sun, Y.; Sang, S.; Jia, L.; Ou, C. (2022). Emerging Approach for Fish Freshness Evaluation: Principle, Application and Challenges. Foods, 11(13), 1897. https://doi.org/10.3390/foods11131897

29. Abramova, L. S., Kozin, A. V., Pogrebisskaya (Azarova), A. L. (2018). Methods for assessing the quality of food fish products. Production Quality Control, 6, 25–31.

30. Vorobyov, V. V. (2021). Strategic aspects of sustainable development fisheries complex of Russia. Fisheries, 5, 23–29. https://doi.org/10.37663/0131-6184-2021-5-23-29

31. GOST 814-2019 Chilled Fish. Specifications (with Amendment) — Docs.cntd.ru. (n.d.). Retrieved 4 October 2025, from https://docs.cntd.ru/document/1200167776

32. Donskova, L. А. (2023). Losses in the fishing sector in the context of sustainable development: ensuring quality and safety as factors of reduction. Economy and Business: Theory and Practice, 2 (96), 136–141.