Deep Learning Strategies for Visual Pattern Analysis in Metallic Surfaces

• Sandro Bessa de Lima IME
• Julio Cesar Duarte IME

DOI: https://doi.org/10.5753/webmedia.2025.16094

Resumo

Advances in multimedia systems and computer vision have enabled each time more sophisticated methods that are able to analyze complex visual patterns in industrial contexts. The inspection of failures in metallic alloys is important for sectors such as aerospace and defense, yet it faces limitations due to reliance on manual methods and data scarcity. This research presents a systematic approach for selecting convolutional neural network architectures by integrating data augmentation, image segmentation, and self-supervised learning. In particular, it uses the DINO technique to generate interpretable attention maps, enhancing model transparency and performance in defect detection tasks. The method was validated using three architectures, ResNetInceptionV2, DenseNet, and Xception, with DenseNet combined with DINO achieving the best results. Key contributions include the release of a hybrid dataset (real and synthetic), effective strategies for handling class imbalance, and a comparative study of architectures, offering insights for future industrial applications and deep learning research applied to pattern detection on metallic surfaces.

Palavras-chave: Computer vision, Defect detection, Metallic surfaces, Convolutional neural networks, Transfer learning, DINO

Referências

A. Abraham. 2005. Adaptation of Fuzzy Inference System Using Neural Learning. In Fuzzy Systems Engineering: Theory and Practice, Nadia Nedjah and Luiza de Macedo Mourelle (Eds.). Springer Berlin Heidelberg, Berlin, Heidelberg, 53–83. DOI: 10.1007/11339366_3

Ravulakollu K. Ahuja S, Shukla M. 2021. Optimized deep learning framework for detecting pitting corrosion based on image segmentation. International Journal of Performability Engineering Volume 17 (2021), Pages 627 – 637.

Deegan J Atha and Mohammad R Jahanshahi. 2018. Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection. Structural Health Monitoring 17, 5 (2018), 1110–1128. DOI: 10.1177/1475921717737051 arXiv: [link]

Blossom Treesa Bastian, Jaspreeth N, S. Kumar Ranjith, and C.V. Jiji. 2019. Visual inspection and characterization of external corrosion in pipelines using deep neural network. NDT & E International 107 (2019), 102134. DOI: 10. 1016/j.ndteint.2019.102134

Sandro Bessa, Julio Duarte, and Marcos Santos. 2025. A Bibliometric Study on the Applications of Neural Networks in Metal Surface Defect Inspection. Revista de Informática Teórica e Aplicada (RITA) 32, 2 (2025), 64–82. DOI: 10.22456/2175-2745.142111 Available online: [link].

Jakob Božič, Domen Tabernik, and Danijel Skočaj. 2021. Mixed supervision for surface-defect detection: from weakly to fully supervised learning. [link]. Accessed: [27/05/2025].

Mathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou, Julien Mairal, Piotr Bojanowski, and Armand Joulin. 2021. Emerging Properties in Self-Supervised Vision Transformers. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, Montreal, Canada, 9650–9659.

Le Dinh Duy, Ngo Tuan Anh, Ngo Tung Son, Nguyen Viet Tung, Nguyen Ba Duong, and Muhammad Hassan Raza Khan. 2020. Deep Learning in Semantic Segmentation of Rust in Images. In Proceedings of the 2020 9th International Conference on Software and Computer Applications (s.n ed.) (Langkawi, Malaysia) (ICSCA ’20, s.n). Association for Computing Machinery, New York, NY, USA, 129–132. DOI: 10.1145/3384544.3384606

Isack Farady, Chih-Yang Lin, Fityanul Akhyar, R. Roshini, and John Alex. 2021. Evaluation of Data Augmentation on Surface Defect Detection. In Proceedings of the IEEE International Conference on Consumer Electronics - Taiwan (ICCE-TW). IEEE, Tainan, Taiwan, 1–2. DOI: 10.1109/ICCE-TW52618.2021.9603212

M.W Gardner and S.R Dorling. 1998. Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences. Atmospheric Environment 32, 14 (1998), 2627–2636. DOI: 10.1016/S1352-2310(97)00447-0

Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Remi Munos, and Michal Valko. 2020. Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning. arXiv preprint arXiv:2006.07733. [link]

Iason Katsamenis, Eftychios Protopapadakis, Anastasios Doulamis, Nikolaos Doulamis, and Athanasios Voulodimos. 2020. Pixel Level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation. In Advances in Visual Computing, George Bebis, Zhaozheng Yin, Edward Kim, Jan Bender, Kartic Subr, Bum Chul Kwon, Jian Zhao, Denis Kalkofen, and George Baciu (Eds.). Springer International Publishing, Cham, 160–169. DOI: 10.1007/978-3-030-64556-4_13

Wenhao Li, Haiou Zhang, Guilan Wang, Gang Xiong, Meihua Zhao, Guokuan Li, and Runsheng Li. 2023. Deep learning based online metallic surface defect detection method for wire and arc additive manufacturing. Robotics and Computer-Integrated Manufacturing 80 (2023), 102470. DOI: 10.1016/j.rcim.2022.102470

Will Nash, Tom Drummond, and Nick Birbilis. 2019. Deep Learning AI for Corrosion Detection. In CORROSION 2019 (NACE CORROSION, Vol. All Days). NACE International, OnePetro, Richardson, Texas, NACE–2019–13267. arXiv: [link]

Atiqur Rahman, Zheng Wu, and Rony Kalfarisi. 2021. Semantic Deep Learning Integrated with RGB Feature-Based Rule Optimization for Facility Surface Corrosion Detection and Evaluation. Journal of Computing in Civil Engineering 35, 6 (08 2021), 04021018. DOI: 10.1061/(ASCE)CP.1943âĹŠ5487.0000982

V. Ramani, L. Zhang, and K. Kuang. 2021. Probabilistic assessment of time to cracking of concrete cover due to corrosion using semantic segmentation of imaging probe sensor data. Automation in Construction 132 (2021), 103961. DOI: 10.1016/j.autcon.2021.103961

Zhiren Tian, Guifeng Zhang, Yongli Liao, Ruihai Li, and Fanqi Huang. 2019. Corrosion Identification of Fittings Based on Computer Vision. In 2019 International Conference on Artificial Intelligence and Advanced Manufacturing (AIAM). IEEE, Dublin, Ireland, 592–597. DOI: 10.1109/AIAM48774.2019.00123

Hugo Touvron, Matthieu Cord, Alexandre Sablayrolles, and Hervé Jégou. 2021. Training data-efficient image transformers & distillation through attention. arXiv preprint arXiv:2012.12877. [link] arXiv:2012.12877.

Xuebing Xu, Yuanhang Wang, Jun Wu, and Yanzhi Wang. 2020. Intelligent Corrosion Detection and Rating Based on Faster Region-Based Convolutional Neural Network. In 2020 Global Reliability and Prognostics and Health Management (PHM-Shanghai). IEEE, Shanghai, China, 1–5. DOI: 10.1109/PHMShanghai49105.2020.9281005

Jong Pil Yun,Woosang Crino Shin, Gyogwon Koo, Min Su Kim, Chungki Lee, and Sang Jun Lee. 2020. Automated defect inspection system for metal surfaces based on deep learning and data augmentation. Journal of Manufacturing Systems 55 (2020), 317–324. DOI: 10.1016/j.jmsy.2020.03.009

Jong Pil Yun,Woosang Crino Shin, Gyogwon Koo, Min Su Kim, Chungki Lee, and Sang Jun Lee. 2020. Automated defect inspection system for metal surfaces based on deep learning and data augmentation. Journal of Manufacturing Systems 55 (2020), 317–324. DOI: 10.1016/j.jmsy.2020.03.009

Paweł Zuchniak, Witold Dzwinel, Tomasz Majerz, Andrzej Pasternak, and Kamil Dragan. 2021. Corrosion Detection on Aircraft Fuselage with Multi-teacher Knowledge Distillation. In Computational Science – ICCS 2021, Maciej Paszynski, Dieter Kranzlmüller, Valeria V. Krzhizhanovskaya, and Jack Dongarra (Eds.). Lecture Notes in Computer Science, Vol. 12747. Springer, Cham, 318–332. DOI: 10.1007/978-3-030-77970-2_25