Vestnik КRAUNC. Fiz.-Mat. Nauki. 2026. vol. 54. no. 2. P. 106 – 118. ISSN 2079-6641

COMPUTATIONAL AND INFORMATION TECHNOLOGIES
https://doi.org/10.26117/2079-6641-2026-54-2-106-118
Research Article
Full text in English
MSC 68T45

Contents of this issue

Read Russian Version

Intelligent Defect Recognition System for Fish Product Packaging Using Machine Vision

A. N. Sheremetev, E. A. Luttseva^{\ast}

Kamchatka State Technical University, 683003, Klyuchevskaya st., 35, Petropavlovsk-Kamchatsky, Russia

Abstract. This paper presents a study on the development of an automatic quality control system for fish product packaging based on computer vision and convolutional neural networks. The relevance of the work is driven by the need to reduce human factor influence during visual inspection on conveyor lines, especially under high production rates and given the perishable nature of the product. To address this problem, the YOLO26 model was selected. A two-stage architecture is proposed: at the first stage, the YOLO26n model detects the box region in the frame (the frame is then cropped); at the second stage, a binary classifier built upon YOLO26s determines whether a packaging defect is present. This approach reduces classification errors caused by background differences between the dataset and real-world conditions. A custom labelled image dataset was collected on a prototype conveyor line. An experimental comparison of the YOLO26s, YOLOv8s, and YOLO11s classifiers was performed on the test set. Testing on a set of 108 images demonstrated an accuracy of 96.3% with false positive and false negative rates of 3.7% each. It is concluded that the developed system is applicable to the existing conveyor line prototype and can potentially be scaled to industrial fish processing plants.

Key words: neural networks, computer vision, YOLO26, dataset, fishing industry, packaging defect.

Received: 23.06.2026; Revised: 26.07.2026; Accepted: 24.08.2026; First online: 14.09.2026

For citation. Sheremetev A. N., Luttseva E. A. Intelligent defect recognition system for fish product packaging using machine vision. Vestnik KRAUNC. Fiz.-mat. nauki. 2026, 54: 2, 106-118. EDN: ZQKLMN. https://doi.org/10.26117/2079-6641-2026-54-2-106-118.

Funding. The work was carried out within the framework of the research project of the GBT of the FSBEI HE “Kamchatka State Technical University”(state registration number 126022517947-0)

Competing interests. There are no conflicts of interest regarding authorship and publication.

Contribution and Responsibility. All authors contributed to this article. Authors are solely responsible for providing the final version of the article in print. The final version of the manuscript was approved by all authors.

^{\ast}Correspondence: E-mail: luttsevaea@gmail.com

The content is published under the terms of the Creative Commons Attribution 4.0 International License

© Sheremetev A. N., Luttseva E. A., 2026

© Institute of Cosmophysical Research and Radio Wave Propagation, 2026 (original layout, design, compilation)

References

1. Jiao X., Zhu J., Ye W., Zou H., Yan B., Zhang N., Qiang J., Tao Y., Zhang H., Zhang D., Fan D. Artificial intelligence in smart seafood safety across the supply chains: Recent advances and future prospects, Trends in Food Science & Technology, 2025. vol. 163, pp. 105161 DOI: 10.1016/j.tifs.2025.105161.
2. Mahatheesan A. J., Sharmilan T.Advancements and Challenges in Real-Time Electronic Vision Technologies for Canned Fish Quality Inspection: A Comprehensive Review, European Modern Studies Journal, 2024. vol. 8, no. 4, pp. 414–421 DOI: 10.59573/emsj.8(4).2024.19.
3. Savinov E. D., Ivashko E. E. Analytical review of technologies for contactless “weighing” fish, Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Rybnoe khozyaistvo, 2024. vol. 1, no. 1, pp. 84–94 DOI: 10.24143/2073-5529-2024-1-84-94 (In Russian).
4. Ivanovsky A. N. Application of neural networks in fish sorting systems on fishing fleet vessels, Vestnik Kerchenskogo gosudarstvennogo morskogo tekhnologicheskogo universiteta. Seriya: Morskie tekhnologii, 2023. vol. 1, no. 2, pp. 112–118 (In Russian).
5. Alekseev P.P., Kvyatkovskaya I.Yu. Application of neural networks in system of recognition of commercial aquatic organisms during increased fluctuation, Vestnik Astrakhanskogo gosudarstvennogo tekhnicheskogo universiteta. Seriya: Upravlenie, vychislitel’naya tekhnika i informatika, 2022. vol. 1, no. 2, pp. 76–86 DOI: 10.24143/2072-9502-2022-2-76-86 (In Russian).
6. Sheremetev A. N., Luttseva E. A. Development of a system for recognizing defects in fish product packaging /Tekhnicheskaya ekspluatatsiya vodnogo transporta: problemy i puti razvitiya, Materialy Vos’moi natsional’noi (vserossiiskoi) nauchno-tekhnicheskoi konferentsii (Petropavlovsk-Kamchatsky, November 27–28, 2025). Petropavlovsk-Kamchatsky, Kamchatka State Technical University, 2026, pp. 273–277 (In Russian).
7. CVAT.ai Data Annotation Platform for Vision AI, Website https://www.cvat.ai.
8. Ultralytics The ultimate end-to-end computer vision platform, Website, https://www.ultralytics.com.
9. Vychegzhanin S. V., Tatarinova A. G., Myshkin R. E. Comparative analysis of neural network models for detecting unmanned aerial vehicles, Komp’yuternaya optika, 2026. vol. 50, no. 2, pp. 17–28 DOI: 10.18287/COJ1728 (In Russian).
10. Beqqali Hassani I., Benhida S., Lamii N., et al. From YOLO V1 to YOLO V11: comparative analysis of YOLO algorithm (review), International Journal of Electrical and Computer Engineering, 2026. vol. 16, no. 1, pp. 450–462 DOI: 10.11591/ijece.v16i1.pp450-462.
11. Nebaba S. G., Markov N.G. Convolutional neural networks of YOLO family for mobile computer vision systems, Komp’yuternye issledovaniya i modelirovanie, 2024. vol. 16, no. 3, pp. 615–631 DOI:
    10.20537/2076-7633-2024-16-3-615-631 (In Russian).
12. Sapkota R., Karkee M. Ultralytics YOLO Evolution: An Overview of YOLO26, YOLO11, YOLOv8 and YOLOv5 Object Detectors for Computer Vision and Pattern Recognition, 2026, arXiv: arXiv:2510.09653.
13. COCO Consortium COCO Dataset, Website, https://cocodataset.org.
14. ImageNet ImageNet Dataset, Website, https://www.image-net.org.
15. Flach P. Mashinnoe obuchenie. Nauka i iskusstvo postroeniya algoritmov, kotorye izvlekayut znaniya iz dannykh [Machine Learning: The Science and Art of Building Algorithms that Extract Knowledge from Data]. Moscow: DMK Press, 2015. 400 pp. (In Russian)
16. Kalabin A. L., Tolstel O. V., Shirkin A. E. Construction of a computer vision system for aligning the contents of packages by a delta manipulator in food production, Programmnye produkty i sistemy, 2023. vol. 1, no. 2, pp. 334–341 DOI: 10.15827/0236-235X.142.334-341 (In Russian).

---

Information about the authors

---

---