International Journal of Control, Automation, and Systems 2025; 23(2): 441-448
https://doi.org/10.1007/s12555-024-0550-8
© The International Journal of Control, Automation, and Systems
Recent advances in deep learning models for object detection and segmentation have received a lot of attention in various industry applications. However, applying deep learning methods on real world problems has In steel manufacturing industry, unexpected factors cause critical effects on the quality of steel products, and it is required to inspect defects in an early stage to reduce production costs. This paper proposes TAG-Net, a novel attention-based semantic segmentation network aimed at improving the performance for inspecting surface defects on steel products. TAG-Net estimates three attention maps each for background, defects, and boundaries of defects, and we introduce an auxiliary deep supervision to guide the boundaries of defective regions. Experiments were conducted on the NEU-Seg dataset, and experimental results demonstrate that our proposed method significantly outperforms previous methods with a significant margin.
Keywords Attention mechanisms, boundary segmentation, semantic segmentation, steel manufacturing industry, surface defect inspection.
International Journal of Control, Automation, and Systems 2025; 23(2): 441-448
Published online February 1, 2025 https://doi.org/10.1007/s12555-024-0550-8
Copyright © The International Journal of Control, Automation, and Systems.
Seyoung Jeong, Jimin Song, and Sang Jun Lee*
Jeonbuk National University
Recent advances in deep learning models for object detection and segmentation have received a lot of attention in various industry applications. However, applying deep learning methods on real world problems has In steel manufacturing industry, unexpected factors cause critical effects on the quality of steel products, and it is required to inspect defects in an early stage to reduce production costs. This paper proposes TAG-Net, a novel attention-based semantic segmentation network aimed at improving the performance for inspecting surface defects on steel products. TAG-Net estimates three attention maps each for background, defects, and boundaries of defects, and we introduce an auxiliary deep supervision to guide the boundaries of defective regions. Experiments were conducted on the NEU-Seg dataset, and experimental results demonstrate that our proposed method significantly outperforms previous methods with a significant margin.
Keywords: Attention mechanisms, boundary segmentation, semantic segmentation, steel manufacturing industry, surface defect inspection.
Vol. 23, No. 2, pp. 359~682
Hui Chen, Wanlou Chen, Yipeng Zuo, Peng Xu, and Zhonghua Hao*
International Journal of Control, Automation and Systems 2022; 20(10): 3321-3334