Automated Analysis of Packaging Seal Failures Using Computer Vision Techniques

Ana Osias; Ian Otoni; Thiago L. Gomes; Michel M. Silva

doi:10.22456/2175-2745.150833

Authors

Ana Osias Universidade Federal de Viçosa (UFV) https://orcid.org/0009-0004-2562-372X
Ian Otoni Universidade Federal de Viçosa (UFV)
Thiago L. Gomes Universidade Federal de Viçosa (UFV)
Michel M. Silva Universidade Federal de Viçosa (UFV) https://orcid.org/0000-0002-2499-9619

DOI:

https://doi.org/10.22456/2175-2745.150833

Keywords:

computer vision, Convolutional neural networks, machine learning, Automated Defect Detection

Abstract

This work presents a computer vision–based method for the automated detection of sealing failures in carton packaging. In the juice industry, manual inspection of package flaps is destructive, time-consuming, and prone to human error, while defective sealing can lead to product leakage and economic losses. To address these challenges, we propose a two-stage approach: first, images of package flaps are preprocessed to accurately detect and align the flaps and detect the adhesive region; second, the adhesive region is segmented and classified into four categories: Aluminum, Background, Cardboard, and Cardboard-Aluminum using convolutional neural networks applied to image patches. Regions where aluminum appears in the same position on both flaps are identified as sealing failures. Experimental evaluation demonstrates that the method reliably detects defects, reducing reliance on manual inspection and providing an effective solution for automated quality control in industrial production.

Downloads

Download data is not yet available.

References

[1] ETTALIBI, A.; ELOUADI, A.; MANSOUR, A. AI and computer vision-based real-time quality control: A review of industrial applications. Procedia Computer Science, v. 231, p. 212–220, 2024. ISSN 1877-0509. Disponível em: ⟨https://www.sciencedirect.com/science/article/pii/S187705092302207X⟩.

[2] ZHOU, L.; ZHANG, L.; KONZ, N. Computer vision techniques in manufacturing. IEEE Transactions on Systems, Man, and Cybernetics: Systems, v. 53, n. 1, p. 105–117, 2023. Disponível em: ⟨https://doi.org/10.1109/TSMC.2022.3166397⟩.

[3] SZELISKI, R. Computer vision: algorithms and applications. [S.l.]: Springer Nature, 2022.

[4] VIKAS et al. Integration of computer vision systems in robotics and industry 4.0. In: 2024 International Conference on IoT, Communication and Automation Technology (ICICAT). [s.n.], 2024. p. 1492–1497. Disponível em: ⟨https://doi.org/10.1109/ICICAT62666.2024.10923326⟩.

[5] Tetra Pak. Mantendo os alimentos seguros e nutritivos. 2025. Acessado em: 17 set. 2025. Disponível em: ⟨https://www.tetrapak.com/pt-br/insights/cases-articles/keeping-food-safe-and-nutritious⟩.

[6] DIAZ, J. Z.; FAROOQ, M. A.; CORCORAN, P. Automatic inspection of seal integrity in sterile barrier packaging: A deep learning approach. IEEE Access, v. 12, p. 22904–22927, 2024. Disponível em: ⟨https://doi.org/10.1109/ACCESS.2023.3348779⟩.

[7] REN, Z. et al. State of the art in defect detection based on machine vision. International Journal of Precision Engineering and Manufacturing-Green Technology, Springer, v. 9, n. 2, p. 661–691, 2022. Disponível em: ⟨https://doi.org/10.1007/s40684-021-00343-6⟩.

[8] LI, X. et al. Surface defect detection of seals based on k-means clustering algorithm and particle swarm optimization. Scientific Programming, v. 2021, n. 1, p. 3965247, 2021. Disponível em: ⟨https://doi.org/10.1155/2021/3965247⟩.

[9] FISCHLER, M. A.; BOLLES, R. C. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, ACM New York, NY, USA, v. 24, n. 6, p. 381–395, 1981. Disponível em: ⟨https://doi.org/10.1145/358669.358692⟩.

[10] CANNY, J. A computational approach to edge detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, PAMI-8, n. 6, p. 679–698, 1986. Disponível em: ⟨https://doi.org/10.1109/TPAMI.1986.4767851⟩.

[11] PyTorch Foundation. ResNet Model – Torchvision 0.20.0 documentation. 2025. ⟨https://pytorch.org/vision/main/models/resnet.html⟩. Accessed: 2025-10-08.

[12] HE, K. et al. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). [s.n.], 2016. p. 770–778. Disponível em: ⟨https://doi.org/10.1109/CVPR.2016.90⟩.

[13] SHAPIRO, S. S.; WILK, M. B. An analysis of variance test for normality (complete samples). Biometrika, [Oxford University Press, Biometrika Trust], v. 52, n. 3/4, p. 591–611, 1965. ISSN 00063444, 14643510. Disponível em: ⟨https://doi.org/10.1093/biomet/52.3-4.591⟩.

[14] XU, M. et al. The differences and similarities between two-sample t-test and paired t-test. Shanghai Archives of Psychiatry, v. 29, n. 3, p. 184–188, 2017.