Steel surface defect detection and segmentation using deep neural networks
Defect detection is a crucial task in the manufacturing industry, particularly in steel surface inspection. While manual recognition is one of the most reliable techniques, recent advances in computer vision and machine learning have led to the development of automatic defect detection techniques. T...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Results in Engineering |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S259012302500060X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841527162983677952 |
|---|---|
| author | Sara Ashrafi Sobhan Teymouri Sepideh Etaati Javad Khoramdel Yasamin Borhani Esmaeil Najafi |
| author_facet | Sara Ashrafi Sobhan Teymouri Sepideh Etaati Javad Khoramdel Yasamin Borhani Esmaeil Najafi |
| author_sort | Sara Ashrafi |
| collection | DOAJ |
| description | Defect detection is a crucial task in the manufacturing industry, particularly in steel surface inspection. While manual recognition is one of the most reliable techniques, recent advances in computer vision and machine learning have led to the development of automatic defect detection techniques. This paper proposes several deep-learning-based computer vision techniques, including semantic segmentation and object detection models, to detect surface defects on steel sheets. The U-Net, FCN-8, and FPN models are implemented for segmentation, while the YOLOv4 model is used for object detection. Moreover, a combined segmentation and object detection structure, referred to as two-stage defect detection, is developed to enhance the accuracy of detecting small defects. Based on the obtained results, the U-Net model with pre-trained backbones achieves a Dice Similarity Coefficient of 72%, outperforming existing methods. The object detection model with a resolution of 640 reaches the mean average precision of 49.32% and 35.06% for binary class and multi-class detection, respectively. Furthermore, the proposed two-stage defect detection structure achieves a Dice Similarity Coefficient of 84%. In summary, the results validate the efficient performance of the studied techniques for accurate defect detection on steel surfaces. |
| format | Article |
| id | doaj-art-5db3e0ffc1e0422598ea9f970d6cfd04 |
| institution | Kabale University |
| issn | 2590-1230 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Results in Engineering |
| spelling | doaj-art-5db3e0ffc1e0422598ea9f970d6cfd042025-01-16T04:29:13ZengElsevierResults in Engineering2590-12302025-03-0125103972Steel surface defect detection and segmentation using deep neural networksSara Ashrafi0Sobhan Teymouri1Sepideh Etaati2Javad Khoramdel3Yasamin Borhani4Esmaeil Najafi5Center of Excellence in Robotics and Control, Advanced Robotics and Automated Systems (ARAS), Faculty of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, IranFaculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, IranFaculty of Electrical Engineering, K. N. Toosi University of Technology, Tehran, IranCenter of Excellence in Robotics and Control, Advanced Robotics and Automated Systems (ARAS), Faculty of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, IranCenter of Excellence in Robotics and Control, Advanced Robotics and Automated Systems (ARAS), Faculty of Mechanical Engineering, K. N. Toosi University of Technology, Tehran, IranSmart Mechatronics and Robotics Research Group, Saxion University of Applied Sciences, Enschede, the Netherlands; Corresponding author.Defect detection is a crucial task in the manufacturing industry, particularly in steel surface inspection. While manual recognition is one of the most reliable techniques, recent advances in computer vision and machine learning have led to the development of automatic defect detection techniques. This paper proposes several deep-learning-based computer vision techniques, including semantic segmentation and object detection models, to detect surface defects on steel sheets. The U-Net, FCN-8, and FPN models are implemented for segmentation, while the YOLOv4 model is used for object detection. Moreover, a combined segmentation and object detection structure, referred to as two-stage defect detection, is developed to enhance the accuracy of detecting small defects. Based on the obtained results, the U-Net model with pre-trained backbones achieves a Dice Similarity Coefficient of 72%, outperforming existing methods. The object detection model with a resolution of 640 reaches the mean average precision of 49.32% and 35.06% for binary class and multi-class detection, respectively. Furthermore, the proposed two-stage defect detection structure achieves a Dice Similarity Coefficient of 84%. In summary, the results validate the efficient performance of the studied techniques for accurate defect detection on steel surfaces.http://www.sciencedirect.com/science/article/pii/S259012302500060XSteel surface defect detectionComputer visionSemantic segmentationObject detection |
| spellingShingle | Sara Ashrafi Sobhan Teymouri Sepideh Etaati Javad Khoramdel Yasamin Borhani Esmaeil Najafi Steel surface defect detection and segmentation using deep neural networks Results in Engineering Steel surface defect detection Computer vision Semantic segmentation Object detection |
| title | Steel surface defect detection and segmentation using deep neural networks |
| title_full | Steel surface defect detection and segmentation using deep neural networks |
| title_fullStr | Steel surface defect detection and segmentation using deep neural networks |
| title_full_unstemmed | Steel surface defect detection and segmentation using deep neural networks |
| title_short | Steel surface defect detection and segmentation using deep neural networks |
| title_sort | steel surface defect detection and segmentation using deep neural networks |
| topic | Steel surface defect detection Computer vision Semantic segmentation Object detection |
| url | http://www.sciencedirect.com/science/article/pii/S259012302500060X |
| work_keys_str_mv | AT saraashrafi steelsurfacedefectdetectionandsegmentationusingdeepneuralnetworks AT sobhanteymouri steelsurfacedefectdetectionandsegmentationusingdeepneuralnetworks AT sepidehetaati steelsurfacedefectdetectionandsegmentationusingdeepneuralnetworks AT javadkhoramdel steelsurfacedefectdetectionandsegmentationusingdeepneuralnetworks AT yasaminborhani steelsurfacedefectdetectionandsegmentationusingdeepneuralnetworks AT esmaeilnajafi steelsurfacedefectdetectionandsegmentationusingdeepneuralnetworks |