Robust Deep Learning Framework untuk Deteksi Cacat Permukaan pada Material Logam dalam Kondisi Pencitraan yang Terganggu Noise dan Blur
DOI:
https://doi.org/10.63447/jimik.v7i3.2083Keywords:
Surface Defect Detection, Deep Learning, Image Segmentation, Image Degradation, Noise and Blur, Industrial InspectionAbstract
Surface defect detection plays a crucial role in industrial quality control, especially in metal manufacturing, where defects can impact structural integrity and product reliability. Although deep learning-based inspection systems have shown promising results, most approaches assume ideal imaging conditions and experience significant performance degradation when faced with disturbances such as noise and blur. This study proposes a robust deep learning framework for surface defect detection under degraded imaging conditions. The framework integrates controlled image degradation simulation and a segmentation-based model using U-Net to enable precise pixel-level localization of defects. Robustness is evaluated through the addition of Gaussian noise, salt-and-pepper noise, and motion blur. Experimental results on the Severstal Steel Defect Dataset demonstrate that the proposed method outperforms the baseline segmentation model YOLOv8n-seg. Under clean conditions, the model achieves a precision of 0.6328 and an F1-score of 0.3199. In degraded conditions, the model remains stable despite performance drops, whereas other methods show significant declines. Additionally, the segmentation output allows for quantitative estimation of defect areas, providing valuable information for industrial applications. The findings indicate that segmentation-based approaches offer greater robustness and more reliable defect localization in challenging imaging environments.
Downloads
References
Chen, X., Liu, M., Niu, Y., Wang, X., & Cheng Wu, Y. (2024). Deep-learning-based lithium battery defect detection via cross-domain generalization. IEEE Access, 12, 78505–78514. https://doi.org/10.1109/ACCESS.2024.3408718.
Chen, X., Wu, Y., He, X., & Ming, W. (2023). A comprehensive review of deep learning-based PCB defect detection. IEEE Access, 11, 139017–139038. https://doi.org/10.1109/ACCESS.2023.3339561.
Dang, Z., & Wang, X. (2025). FD-YOLO11: A feature-enhanced deep learning model for steel surface defect detection. IEEE Access, 13, 63981–63993. https://doi.org/10.1109/ACCESS.2025.3559733.
Gao, Y., Lv, G., Xiao, D., Han, X., Sun, T., & Li, Z. (2024). Research on steel surface defect classification method based on deep learning. Scientific Reports, 14. https://doi.org/10.1038/s41598-024-58643-1.
Guan, S., Lei, M., & Lu, H. (2020). A steel surface defect recognition algorithm based on improved deep learning network model using feature visualization and quality evaluation. IEEE Access, 8, 49885–49895. https://doi.org/10.1109/ACCESS.2020.2979755.
Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOv8n-seg. GitHub repository:
Kaggle. (2019). Severstal: Steel defect detection. Retrieved from
Lin, H. I., & Wibowo, F. S. (2021). Image data assessment approach for deep learning-based metal surface defect-detection systems. IEEE Access, 9, 47621–47638. https://doi.org/10.1109/ACCESS.2021.3068256.
Luo, Q., Fang, X., Liu, L., Yang, C., & Sun, Y. (2020). Automated visual defect detection for flat steel surface: A survey. IEEE Transactions on Instrumentation and Measurement, 69, 626–644. https://doi.org/10.1109/TIM.2019.2963555
Mustafaev, B., Kim, S., & Kim, E. (2023). Enhancing metal surface defect recognition through image patching and synthetic defect generation. IEEE Access, 11, 113339–113359. https://doi.org/10.1109/ACCESS.2023.3322734.
Qiao, Q., Hu, H., Ahmad, A., & Wang, K. (2025). A review of metal surface defect detection technologies in industrial applications. IEEE Access. https://doi.org/10.1109/ACCESS.2025.3544578.
Ren, F., Fei, J., Li, H., & Doma, B. T. (2024). Steel surface defect detection using improved deep learning algorithm: ECA-SimSPPF-SIoU-Yolov5. IEEE Access, 12, 32545–32553. https://doi.org/10.1109/ACCESS.2024.3371584.
Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI) (pp. 234–241). Springer.
Selamet, F., Cakar, S., & Kotan, M. (2022). Automatic detection and classification of defective areas on metal parts by using adaptive fusion of Faster R-CNN and shape from shading. IEEE Access, 10, 126030–126038. https://doi.org/10.1109/ACCESS.2022.3224037
Wan, X., Zhang, X., & Liu, L. (2021). An improved VGG19 transfer learning strip steel surface defect recognition deep neural network based on few samples and imbalanced datasets. Applied Sciences, 11. https://doi.org/10.3390/app11062606.
Wang, C., & Xie, H. (2023). MeDERT: A metal surface defect detection model. IEEE Access, 11, 35469–35478. https://doi.org/10.1109/ACCESS.2023.3262264.
Wang, C., Zhou, Z., & Chen, Z. (2022). An enhanced YOLOv4 model with self-dependent attentive fusion and component randomized mosaic augmentation for metal surface defect detection. IEEE Access, 10, 97758–97766. https://doi.org/10.1109/ACCESS.2022.3203198.
Wang, H., Li, W., Zhang, B., & Gu, Z. (2025). n-GSE: Efficient steel surface defect detection method. IEEE Access, 13, 166343–166356. https://doi.org/10.1109/ACCESS.2025.3602360.
Yu, J., Shi, X., Wang, W., & Zheng, Y. (2024). LCG-YOLO: A real-time surface defect detection method for metal components. IEEE Access, 12, 41436–41451. https://doi.org/10.1109/ACCESS.2024.3378999.
Zhao, B., Dai, M., Li, P., Xue, R., & Ma, X. (2020). Defect detection method for electric multiple units key components based on deep learning. IEEE Access, 8, 136808–136818. https://doi.org/10.1109/ACCESS.2020.3009654.
Zhao, Y., Wang, H., Xie, X., Xie, Y., & Yang, C. (2023). An enhanced YOLOv5-based algorithm for metal surface defect detection. Applied Sciences, 13. https://doi.org/10.3390/app132011473.
Zheng, X., Wang, H., Chen, J., Kong, Y., & Zheng, S. (2020). A generic semi-supervised deep learning-based approach for automated surface inspection. IEEE Access, 8, 114088–114099. https://doi.org/10.1109/ACCESS.2020.3003588.
Zhou, C., Lu, Z., Lv, Z., Meng, M., Tan, Y., Xia, K., Liu, K., & Zuo, H. (2023). Metal surface defect detection based on improved YOLOv5. Scientific Reports, 13. https://doi.org/10.1038/s41598-023-47716-2.
Zhu, H., Wang, Y., & Fan, J. (2022). IA-Mask R-CNN: Improved anchor design Mask R-CNN for surface defect detection of automotive engine parts. Applied Sciences, 12. https://doi.org/10.3390/app12136633.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Santi Rahayu, Achmad Hindasyah, Nur Annisahaq
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (CC-BY 4.0) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
License: All articles are licensed under 
