A Study of Computational Vision Methods for Corrosion Detection in Industrial Assets
Resumo
Corrosion has a significant impact on the global economy, leading to high costs for preventing damage, repairing deterioration, and replacing defective components. Industry 4.0 brings computational vision as a key role for visual inspection of assets ensuring quality and reducing the downtime. This study conducts a comparative analysis of computer vision techniques for detecting corrosion, with an emphasis on segmentation neural networks built upon U-Net architectures, focusing on the trade-off between segmentation accuracy and computational efficiency. We benchmark four U-Net-based segmentation models using pretrained backbones: MobileNetV2, ResNet152, InceptionV4 and VGG16 on a publicly available data set of corroded metallic surfaces. All models are trained using the full dataset and evaluated based on per-image F1-score and training time. Our results show that InceptionV4 achieves the highest F1-score (0.895), while MobileNetV2 offers a comparable score (0.892) with nearly half the training time. These findings suggest that lightweight backbones can deliver accurate segmentation with significantly reduced computational cost, making them promising candidates for near real-time industrial inspection systems under resource constraints.
Referências
G. H. Koch, M. P. H. Brongers, N. G. Thompson, Y. P. Virmani, and J. H. Payer, “Corrosion cost and preventive strategies in the united states [final report],” United States. Federal Highway Administration, Tech. Rep. FHWA-RD-01-156, Mar. 2002.
Association for Materials Protection and Performance, “Global cost of corrosion exceeds $2.5 trillion annually,” 2021, accessed: 2025-06-09. [Online]. Available: [link]
M. Iannuzzi and G. S. Frankel, “Opportunities and challenges for corrosion science in the 21st century,” npj Materials Degradation, vol. 6, no. 1, pp. 1–3, 2022. [Online]. Available: [link]
S. A. Bin Idris, F. A. Jafar, and N. Abdullah, “Study on corrosion features analysis for visual inspection & monitoring system: An ndt technique,” J. Teknol., vol. 77, no. 21, Dec. 2015.
V. Vasagar, M. K. Hassan, A. M. Abdullah, A. V. Karre, B. Chen, K. Kim, N. Al-Qahtani, and T. Cai, “Non-destructive techniques for corrosion detection: A review,” Corros. Eng. Sci. Technol., vol. 59, no. 1, pp. 56–85, Feb. 2024.
R. Senthilnathan, “Deep learning in vision-based automated inspection: Current state and future prospects,” Machine Learning in Industry, pp. 159–175, 2021.
J. E. See, C. G. Drury, A. Speed, A. Williams, and N. Khalandi, “The role of visual inspection in the 21st century,” in Proceedings of the Human Factors and Ergonomics Society Annual Meeting, vol. 61, no. 1. SAGE Publications Sage CA: Los Angeles, CA, 2017, pp. 262–266.
L. Leontaris, N. Dimitriou, A. Nikolousis, D. Tzovaras, and E. Papageorgiou, “Inspection of surface defects in metal processing industry using unet-based architectures,” 2023.
Z. Li and X. Liu, “Soldering defect segmentation method for pcb on improved unet,” Applied Sciences, vol. 14, no. 16, p. 7370, 2024.
I. Konovalenko, P. Maruschak, J. Brezinová, O. Prentkovskis, and J. Brezina, “Research of u-net-based cnn architectures for metal surface defect detection,” Machines, vol. 10, no. 5, p. 327, 2022.
S. K. Fondevik, A. Stahl, A. A. Transeth, and O. Ø. Knudsen, “Image segmentation of corrosion damages in industrial inspections,” in 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2020, pp. 787–792.
R. Wang, T. Lei, R. Cui, B. Zhang, H. Meng, and A. K. Nandi, “Medical image segmentation using deep learning: A survey,” IET image processing, vol. 16, no. 5, pp. 1243–1267, 2022.
L. G. Barros, R. T. de Oliveira, J. P. M. Santana, and A. R. D. Ribeiro, “Inspection of surface defects in metal processing industry using unet-based architecture,” in Proceedings of the 36th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). Rio de Janeiro, Brazil: IEEE, October 2023.
I. Ahmed, K. Saleh, and A. Alzahrani, “Segmentation-based deep learning approach for surface defect detection in industrial products,” in 2023 International Conference on Electrical and Computing Technologies and Applications (ICECTA). Ras Al Khaimah, UAE: IEEE, 2023.
L. Liu, W. Ouyang, X. Wang, P. Fieguth, J. Chen, X. Liu, and M. Pietikäinen, “Deep learning for generic object detection: A survey,” International journal of computer vision, vol. 128, pp. 261–318, 2020.
T. Van Erp, E. R. Da Silva, and M. Stenger, “Industrial digital twin as a facilitator for business model innovations in the manufacturing industry,” Procedia CIRP, vol. 118, pp. 330–335, 2023.
Y. Chen, Y. Ding, F. Zhao, E. Zhang, Z. Wu, and L. Shao, “Surface defect detection methods for industrial products: A review,” Applied Sciences, vol. 11, no. 16, p. 7657, 2021.
A. Saberironaghi, J. Ren, and M. El-Gindy, “Defect detection methods for industrial products using deep learning techniques: A review,” Algorithms, vol. 16, no. 2, p. 95, 2023.
R. Azad, E. K. Aghdam, A. Rauland, Y. Jia, A. H. Avval, A. Bozorgpour, S. Karimijafarbigloo, J. P. Cohen, E. Adeli, and D. Merhof, “Medical image segmentation review: The success of u-net,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.
Z. Lv, H. Huang, L. Gao, J. A. Benediktsson, M. Zhao, and C. Shi, “Simple multiscale unet for change detection with heterogeneous remote sensing images,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022.
P. Zhou, G. Zhou, Y. Li, Z. He, and Y. Liu, “A hybrid data-driven method for wire rope surface defect detection,” IEEE Sensors Journal, vol. 20, no. 15, pp. 8297–8306, 2020.
K. Shaikh, I. Hussain, and B. S. Chowdhry, “Wheel defect detection using a hybrid deep learning approach,” Sensors, vol. 23, no. 14, p. 6248, 2023.
sem, “cor dataset,” [link], jun 2025, visited on 2025-06-16. [Online]. Available: [link]
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-v4, inception-resnet and the impact of residual connections on learning,” in Proceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510–4520.
C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, “A survey on deep transfer learning,” in Artificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III 27. Springer, 2018, pp. 270–279.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
A. Mazinanian, B. Kabiri, and V. Hashemi, “Research of u-net-based cnn architectures for metal surface defect detection,” Mathematics, vol. 11, no. 17, p. 3693, 2023.
F. Milletari, N. Navab, and S.-A. Ahmadi, “V-net: Fully convolutional neural networks for volumetric medical image segmentation,” in 2016 fourth international conference on 3D vision (3DV). Ieee, 2016, pp. 565–571.
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg et al., “Scikit-learn: Machine learning in python,” the Journal of machine Learning research, vol. 12, pp. 2825–2830, 2011.
M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (voc) challenge,” International journal of computer vision, vol. 88, pp. 303–338, 2010.
J. W. Tukey, Exploratory Data Analysis. Reading, MA: Addison-Wesley, 1977.
Association for Materials Protection and Performance, “Global cost of corrosion exceeds $2.5 trillion annually,” 2021, accessed: 2025-06-09. [Online]. Available: [link]
M. Iannuzzi and G. S. Frankel, “Opportunities and challenges for corrosion science in the 21st century,” npj Materials Degradation, vol. 6, no. 1, pp. 1–3, 2022. [Online]. Available: [link]
S. A. Bin Idris, F. A. Jafar, and N. Abdullah, “Study on corrosion features analysis for visual inspection & monitoring system: An ndt technique,” J. Teknol., vol. 77, no. 21, Dec. 2015.
V. Vasagar, M. K. Hassan, A. M. Abdullah, A. V. Karre, B. Chen, K. Kim, N. Al-Qahtani, and T. Cai, “Non-destructive techniques for corrosion detection: A review,” Corros. Eng. Sci. Technol., vol. 59, no. 1, pp. 56–85, Feb. 2024.
R. Senthilnathan, “Deep learning in vision-based automated inspection: Current state and future prospects,” Machine Learning in Industry, pp. 159–175, 2021.
J. E. See, C. G. Drury, A. Speed, A. Williams, and N. Khalandi, “The role of visual inspection in the 21st century,” in Proceedings of the Human Factors and Ergonomics Society Annual Meeting, vol. 61, no. 1. SAGE Publications Sage CA: Los Angeles, CA, 2017, pp. 262–266.
L. Leontaris, N. Dimitriou, A. Nikolousis, D. Tzovaras, and E. Papageorgiou, “Inspection of surface defects in metal processing industry using unet-based architectures,” 2023.
Z. Li and X. Liu, “Soldering defect segmentation method for pcb on improved unet,” Applied Sciences, vol. 14, no. 16, p. 7370, 2024.
I. Konovalenko, P. Maruschak, J. Brezinová, O. Prentkovskis, and J. Brezina, “Research of u-net-based cnn architectures for metal surface defect detection,” Machines, vol. 10, no. 5, p. 327, 2022.
S. K. Fondevik, A. Stahl, A. A. Transeth, and O. Ø. Knudsen, “Image segmentation of corrosion damages in industrial inspections,” in 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence (ICTAI). IEEE, 2020, pp. 787–792.
R. Wang, T. Lei, R. Cui, B. Zhang, H. Meng, and A. K. Nandi, “Medical image segmentation using deep learning: A survey,” IET image processing, vol. 16, no. 5, pp. 1243–1267, 2022.
L. G. Barros, R. T. de Oliveira, J. P. M. Santana, and A. R. D. Ribeiro, “Inspection of surface defects in metal processing industry using unet-based architecture,” in Proceedings of the 36th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). Rio de Janeiro, Brazil: IEEE, October 2023.
I. Ahmed, K. Saleh, and A. Alzahrani, “Segmentation-based deep learning approach for surface defect detection in industrial products,” in 2023 International Conference on Electrical and Computing Technologies and Applications (ICECTA). Ras Al Khaimah, UAE: IEEE, 2023.
L. Liu, W. Ouyang, X. Wang, P. Fieguth, J. Chen, X. Liu, and M. Pietikäinen, “Deep learning for generic object detection: A survey,” International journal of computer vision, vol. 128, pp. 261–318, 2020.
T. Van Erp, E. R. Da Silva, and M. Stenger, “Industrial digital twin as a facilitator for business model innovations in the manufacturing industry,” Procedia CIRP, vol. 118, pp. 330–335, 2023.
Y. Chen, Y. Ding, F. Zhao, E. Zhang, Z. Wu, and L. Shao, “Surface defect detection methods for industrial products: A review,” Applied Sciences, vol. 11, no. 16, p. 7657, 2021.
A. Saberironaghi, J. Ren, and M. El-Gindy, “Defect detection methods for industrial products using deep learning techniques: A review,” Algorithms, vol. 16, no. 2, p. 95, 2023.
R. Azad, E. K. Aghdam, A. Rauland, Y. Jia, A. H. Avval, A. Bozorgpour, S. Karimijafarbigloo, J. P. Cohen, E. Adeli, and D. Merhof, “Medical image segmentation review: The success of u-net,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024.
Z. Lv, H. Huang, L. Gao, J. A. Benediktsson, M. Zhao, and C. Shi, “Simple multiscale unet for change detection with heterogeneous remote sensing images,” IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022.
P. Zhou, G. Zhou, Y. Li, Z. He, and Y. Liu, “A hybrid data-driven method for wire rope surface defect detection,” IEEE Sensors Journal, vol. 20, no. 15, pp. 8297–8306, 2020.
K. Shaikh, I. Hussain, and B. S. Chowdhry, “Wheel defect detection using a hybrid deep learning approach,” Sensors, vol. 23, no. 14, p. 6248, 2023.
sem, “cor dataset,” [link], jun 2025, visited on 2025-06-16. [Online]. Available: [link]
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
C. Szegedy, S. Ioffe, V. Vanhoucke, and A. Alemi, “Inception-v4, inception-resnet and the impact of residual connections on learning,” in Proceedings of the AAAI conference on artificial intelligence, vol. 31, no. 1, 2017.
M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L.-C. Chen, “Mobilenetv2: Inverted residuals and linear bottlenecks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2018, pp. 4510–4520.
C. Tan, F. Sun, T. Kong, W. Zhang, C. Yang, and C. Liu, “A survey on deep transfer learning,” in Artificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III 27. Springer, 2018, pp. 270–279.
A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84–90, 2017.
A. Mazinanian, B. Kabiri, and V. Hashemi, “Research of u-net-based cnn architectures for metal surface defect detection,” Mathematics, vol. 11, no. 17, p. 3693, 2023.
F. Milletari, N. Navab, and S.-A. Ahmadi, “V-net: Fully convolutional neural networks for volumetric medical image segmentation,” in 2016 fourth international conference on 3D vision (3DV). Ieee, 2016, pp. 565–571.
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg et al., “Scikit-learn: Machine learning in python,” the Journal of machine Learning research, vol. 12, pp. 2825–2830, 2011.
M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman, “The pascal visual object classes (voc) challenge,” International journal of computer vision, vol. 88, pp. 303–338, 2010.
J. W. Tukey, Exploratory Data Analysis. Reading, MA: Addison-Wesley, 1977.
Publicado
30/09/2025
Como Citar
MARCO, Anderson Gonçalves; OLIVEIRA, Marcos de Souza; PRATES, Rodrigo Leite; LOPES, Murilo Cruz; CASAL, Rogério Guedes; GUIMARÃES, Cristiani Vilela Ribeiro.
A Study of Computational Vision Methods for Corrosion Detection in Industrial Assets. In: WORKSHOP DE APLICAÇÕES INDUSTRIAIS - CONFERENCE ON GRAPHICS, PATTERNS AND IMAGES (SIBGRAPI), 38. , 2025, Salvador/BA.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 325-330.
