Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network
Open accessThe DOI matches its Crossref record; 42 of the 42 references it cites were found in a registry or an index; 2 of the 6 sources its claims cite were checked for support.
Abstract
Metallic surface defect detection is an essential and necessary process to control the qualities of industrial products. However, due to the limited data scale and defect categories, existing defect datasets are generally unavailable for the deployment of the detection model. To address this problem, we contribute a new dataset called GC10-DET for large-scale metallic surface defect detection. The GC10-DET dataset has great challenges on defect categories, image number, and data scale. Besides, traditional detection approaches are poor in both efficiency and accuracy for the complex real-world environment. Thus, we also propose a novel end-to-end defect detection network (EDDN) based on the Single Shot MultiBox Detector. The EDDN model can deal with defects with different scales. Furthermore, a hard negative mining method is designed to alleviate the problem of data imbalance, while some data augmentation methods are adopted to enrich the training data for the expensive data collection problem. Finally, the extensive experiments on two datasets demonstrate that the proposed method is robust and can meet accuracy requirements for metallic defect detection.
Overview
CoChat Summary
## TL;DR
The paper introduces GC10-DET, a new real-industry metallic surface defect dataset with 10 defect types and 3,570 grayscale images, and proposes an end-to-end defect detector (EDDN) based on SSD. Experiments on GC10-DET and NEU-DET show the method is robust, improves multi-scale defect detection, and achieves the best mAP on GC10-DET.
## Key findings
- GC10-DET contains 10 defect types and 3,570 grayscale images collected in a real industrial setting; NEU-DET has 6 defect types and 1,800 grayscale images.
- On NEU-DET, the proposed method achieves the best mAP of 0.724 and the best results on most defect categories; SSD300 is slightly better on Sc recall (0.990 vs. 0.981) and on In AP (0.796 vs. 0.763) and Rs AP (0.621 vs. 0.581).
- On GC10-DET, the proposed method achieves the best mAP and the best results on most categories; SSD300 is slightly better on Rp recall (0.667 vs. 0.333) and Faster-RCNN is better on Cr recall (1 vs. 0.857).
- Runtime is reported as 27 ms/image on NEU-DET and 33 ms/image on GC10-DET for the proposed method; the paper says this is fast enough for real-time use, though YOLO-V2 is slightly faster on GC10-DET testing set time (4.49 s vs. 8 s).
## Methods
- The paper proposes EDDN, an end-to-end detector built on Single Shot MultiBox Detector (SSD) with VGG16, multi-scale feature maps, default boxes, and non-maximum suppression.
- It introduces hard negative mining, limiting negatives to at most a 3:1 ratio with positives, and applies data augmentation using full images, random patches, and patches with minimum Jaccard overlaps of 0.1, 0.3, 0.5, 0.7, or 0.9.
- Evaluation uses Recall, AP, and mAP on NEU-DET and GC10-DET, with comparisons against SSD, Faster-RCNN, YOLO-V2, YOLO-V3, and traditional LBP/HOG methods.
## Limitations
- The paper states that existing defect datasets are generally unavailable for deployment because of limited data scale and defect categories, and that metallic defect detection is difficult due to illumination, light reflection, and metal material effects.
- It notes that traditional methods are sensitive to lighting and background clutter and need repeated parameter tuning; this is a limitation of prior work, not the proposed method.
- Evident from the text: some reported gains are modest or mixed across categories, since other methods outperform the proposed method on a few defect classes (for example, SSD300 and Faster-RCNN on some NEU-DET and GC10-DET classes).
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures





Verification
Claims the paper makes
2 Valid · 1 Not valid · 1 Not checked · 29 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“we propose an end-to-end metallic surface defect network based on the Single Shot MultiBox Detector [6].”
- Also stated in: § 5. Conclusions · plain
“we propose an end-to-end defect detection and classification network based on the Single Shot MultiBox Detector.”
§ Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network > 1. Introduction
What the sources say
- Supportedcites [6] Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.Y., and Berg, A.C. (2016, January 8–16). Ssd: Single Shot Multibox Detector. Proceedings of the European conference on computer vision, Amsterdam, The Netherlands. source
The citation identifies the Single Shot MultiBox Detector as the basis for the citing authors’ proposed network. The cited paper introduces SSD (Introduction, p. 2) and describes its single-network object detection method (p. 1); it need not describe the citing authors’ metallic-surface defect network. (LLM, conf=0.93)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 5. Conclusions · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Besides, the proposed method shows the best mAP accuracy.”
- Also stated in: § 4.4. Accuracy Comparisons with Deep Methods · plain
“the proposed method shows the best mAP accuracy.”
§ Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network > 4. Experiments > 4.4. Accuracy Comparisons with Deep Methods
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 4.4. Accuracy Comparisons with Deep Methods · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“we contribute a new dataset called GC10-DET for large-scale metallic surface defect detection.”
- Also stated in: § 1. Introduction · plain
“We contribute a new dataset named”
- Also stated in: § 4.1. Datasets · plain
“GC10-DET is the surface defect dataset collected in a real industry. It contains ten types of surface defects”
§ Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network > Abstract
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Also stated in: § 1. Introduction · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the mAP can reach 0.724.”
§ Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network > 4. Experiments > 4.4. Accuracy Comparisons with Deep Methods
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“the YOLO methods are difficult to distinguish the six types of defects.”
§ Deep Metallic Surface Defect Detection: The New Benchmark and Detection Network > 4. Experiments > 4.4. Accuracy Comparisons with Deep Methods
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
7 more claims
Create a free account to see all 33 claims and to verify the 1 reference still open.
- Probably not a substantial claim. 8
- It may state two separate claims as one. 14
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155 · cited 1×
“Since the introduction of AlexNet [26], convolutional neural networks have been successfully deployed to detect surface defects.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460 · cited 1×
“The pre-trained models are often trained on ImageNet [34] and MS COCO [35] datasets.”
MethodImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“The pre-trained models are often trained on ImageNet [34] and MS COCO [35] datasets.”
Method(2016) · Cited by 31,590
SSD: Single Shot MultiBox Detector
Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., & Berg, A. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46448-0_2 · Cited by 22,128 · cited 15×
“The proposed method can obtain the best results on the defects of Pu, In, and Rp, while the SSD300 is slightly higher than proposed on Wl (0.974 vs. 0.885), Ss, (0.689 vs. 0.650) and Wf (1 vs. 0.919).”
MethodInfluentialYOLO9000: Better, Faster, Stronger
Redmon, J., & Farhadi, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.690 · Cited by 19,892 · cited 8×
“Therefore, the SSD method utilizes VGG16 as the pre-trained model, YOLO-V2 uses Darknet19 model, YOLO-V3 uses Darknet53 model, and Faster R-CNN adopts Resnet50 model.”
MethodInfluentialYOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Sermanet, P., Eigen, D., Zhang, X., Mathieu, M., Fergus, R., & LeCun, Y. (2013) · arXiv · doi:10.48550/arxiv.1312.6229 · Cited by 2,680 · cited 1×
“In [29], the OverFeat network [30] was implemented to detect 5 different types of surface defects.”
Method
Cited by
Surface Defect Detection Methods for Industrial Products: A Review
Chen, Y., Ding, Y., Zhao, F., Zhang, E., Wu, Z., & Shao, L. (2021) · Applied Sciences · doi:10.3390/app11167657 · Cited by 457
“com/ujik132016/industrial-metallic-surface-dataset (accessed on 21 June 2021) GC10-Det [113] Metal https://www.”
RDD-YOLO: A modified YOLO for detection of steel surface defects
Zhao, C., Shu, X., Yan, X., Zuo, X., & Zhu, F. (2023) · Measurement · doi:10.1016/j.measurement.2023.112776 · Cited by 386
Defect Detection Methods for Industrial Products Using Deep Learning Techniques: A Review
Saberironaghi, A., Ren, J., & El-Gindy, M. (2023) · Algorithms · doi:10.3390/a16020095 · Cited by 317
“com/c/severstal-steel-defect-detection/data (accessed on 2 February 2023) GC10–Det [116] Metal https://kaggle.”
A New Steel Defect Detection Algorithm Based on Deep Learning
Zhao, W., Chen, F., Huang, H., Li, D., & Cheng, W. (2021) · Computational Intelligence and Neuroscience · doi:10.1155/2021/5592878 · Cited by 259
“Lv et al. [16] proposed a new end-to-end defect detection network (EDDN) to deal with different types of steel surface defects.”
BackgroundDCC-CenterNet: A rapid detection method for steel surface defects
Tian, R., & Jia, M. (2022) · Measurement · doi:10.1016/j.measurement.2021.110211 · Cited by 222
Ameri, R., Hsu, C.-C., & Band, S. S. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107717 · Cited by 213
Steel Surface Defect Recognition: A Survey
Wen, X., Shan, J., He, Y., & Song, K. (2022) · Coatings · doi:10.3390/coatings13010017 · Cited by 210
Usamentiaga, R., Lema, D. G., Pedrayes, O. D., & Garcia, D. F. (2022) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2022.3151560 · Cited by 182
“A more recent research work on the topic can be found in [17].”
BackgroundMethodInfluentialDeep learning methods for object detection in smart manufacturing: A survey
Ahmad, H. M., & Rahimi, A. (2022) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2022.06.011 · Cited by 177
Cas-VSwin transformer: A variant swin transformer for surface-defect detection
Gao, L., Zhang, J., Yang, C., & Zhou, Y. (2022) · Computers in Industry · doi:10.1016/j.compind.2022.103689 · Cited by 166
Research Progress of Automated Visual Surface Defect Detection for Industrial Metal Planar Materials
Fang, X., Luo, Q., Zhou, B., Li, C., & Tian, L. (2020) · Sensors · doi:10.3390/s20185136 · Cited by 160
MSC-DNet: An efficient detector with multi-scale context for defect detection on strip steel surface
Liu, R., Huang, M., Gao, Z., Cao, Z., & Cao, P. (2023) · Measurement · doi:10.1016/j.measurement.2023.112467 · Cited by 159
Surface defect detection and classification of steel using an efficient Swin Transformer
Zhu, W., Zhang, H., Zhang, C., Zhu, X., Guan, Z., & Jia, J. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.102061 · Cited by 173
Deep Learning for Automatic Vision-Based Recognition of Industrial Surface Defects: A Survey
Prunella, M., Scardigno, R. M., Buongiorno, D., Brunetti, A., Longo, N., Carli, R., Dotoli, M., & Bevilacqua, V. (2023) · IEEE Access · doi:10.1109/access.2023.3271748 · Cited by 196
“[244] evaluated a set of boxes with different aspect ratios at each depth; these boxes are matched with the ground truth and the network predicts both the offsets and the confidences for each category.”
BackgroundEfficient Fused-Attention Model for Steel Surface Defect Detection
Yeung, C.-C., & Lam, K. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3176239 · Cited by 163
WSS-YOLO: An improved industrial defect detection network for steel surface defects
Lu, M. L., Sheng, W., Zou, Y. Y., Chen, Y., & Chen, Z. (2024) · Measurement · doi:10.1016/j.measurement.2024.115060 · Cited by 142
A novel deep convolutional neural network algorithm for surface defect detection
Zhang, D., Hao, X., Liang, L., Liu, W., & Qin, C. (2022) · Journal of Computational Design and Engineering · doi:10.1093/jcde/qwac071 · Cited by 134
Zhang, Y., Wang, W., Li, Z., Shu, S., Lang, X., Zhang, T., & Dong, J. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105628 · Cited by 118
Real-Time Steel Surface Defect Detection with Improved Multi-Scale YOLO-v5
Wang, L., Liu, X., Ma, J., Su, W., & Li, H. (2023) · Processes · doi:10.3390/pr11051357 · Cited by 120
“There are six typical defects on steel surfaces: crazing, inclusion, patches, pitted surface, rolled-in scale and scratches [2].”
BackgroundMethodETDNet: Efficient Transformer-Based Detection Network for Surface Defect Detection
Zhou, H., Yang, R., Hu, R., Shu, C., Tang, X., & Li, X. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3307753 · Cited by 146
“The results from [62] are reported in Table VIII.”
ResultYang, G., Liu, K., Zhang, J., Zhao, B., Zhao, Z., Chen, X., & Chen, B. M. (2022) · Construction and Building Materials · doi:10.1016/j.conbuildmat.2022.129226 · Cited by 104
Bai, D., Li, G., Jiang, D., Yun, J., Tao, B., Jiang, G., Sun, Y., & Ju, Z. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107697 · Cited by 116
A Systematic Review on Deep Learning with CNNs Applied to Surface Defect Detection
Cumbajin, E., Rodrigues, N., Costa, P., Miragaia, R., Frazao, L. A. L., Costa, N., Fernández‐Caballero, A., Carneiro, J., Buruberri, L. H., & Pereira, A. M. D. J. (2023) · Journal of Imaging · doi:10.3390/jimaging9100193 · Cited by 142
“These datasets are ALCIDE [64], BS5-DET [6], CSU_STEEL [41], GC10-DET [46], KolektorSDD [36], and the datasets created in [35,70].”
MethodInfluentialGlobal attention module and cascade fusion network for steel surface defect detection
Liu, G., Chu, M., Gong, R., & Zheng, Z. (2024) · Pattern Recognition · doi:10.1016/j.patcog.2024.110979 · Cited by 121
LFF-YOLO: A YOLO Algorithm With Lightweight Feature Fusion Network for Multi-Scale Defect Detection
Qian, X., Wang, X., Yang, S., & Lei, J. (2022) · IEEE Access · doi:10.1109/access.2022.3227205 · Cited by 98
“To validate the effectiveness of the model, we first compared our model with conventional target detection networks on the NEU-DET dataset, including the one-stage detection networks YOLOv4, EfficientDet [33], RetinaNet, SSD, and the two-stage network Faster-RCNN, and also with other steel surface defect detection model…”
MethodInfluentialZhang, H., Li, S., Miao, Q., Fang, R., Song, X., Hu, Q., Hu, J., & Chan, S. (2024) · Scientific Reports · doi:10.1038/s41598-024-57990-3 · Cited by 104
A light weight multi-scale feature fusion steel surface defect detection model based on YOLOv8
Xie, W., Sun, X., & Ma, W. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad296d · Cited by 95
“In this paper, the generalization performance of the model is verified by two steel surface defects datasets, NEU-DET [56] and GC10-DET [57].”
Rodríguez, F., Galarza, A., Vásquez, J. C., & Guerrero, J. M. (2021) · Energy · doi:10.1016/j.energy.2021.122116 · Cited by 80
Cross Position Aggregation Network for Few-Shot Strip Steel Surface Defect Segmentation
Feng, H., Song, K., Cui, W., Zhang, Y., & Yan, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3246519 · Cited by 115
“With the emergence of deep learning, numerous defect detection models [9], [10], [11] based on the convolution neural network (CNN) framework have been applied to extract complicated defect features.”
MethodSmall object detection method with shallow feature fusion network for chip surface defect detection
Huang, H., Tang, X., Wen, F., & Jin, X. (2022) · Scientific Reports · doi:10.1038/s41598-022-07654-x · Cited by 77
Depth-wise Squeeze and Excitation Block-based Efficient-Unet model for surface defect detection
Üzen, H., Türkoğlu, M., Aslan, M., & Hanbay, D. (2022) · The Visual Computer · doi:10.1007/s00371-022-02442-0 · Cited by 81
“As a result, these methods are costly to apply and usually inefficient on different surfaces [35, 48, 49].”
BackgroundA Dynamic Weights-Based Wavelet Attention Neural Network for Defect Detection
Liu, J.-H., Zhao, H., Chen, Z.-L., Wang, Q., Shen, X., & Zhang, H.-G. (2023) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3292512 · Cited by 60
“We employ five datasets to evaluate our method, namely NEU-DET [21], GC10-DET [22], MFL dataset, MFL noise data, and VOC dataset.”
MethodFaNet: Feature-aware network for few shot classification of strip steel surface defects
Zhao, W., Song, K., Wang, Y., Liang, S., & Yan, Y. (2023) · Measurement · doi:10.1016/j.measurement.2023.112446 · Cited by 76
Xie, W., Ma, W., & Sun, X. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128775 · Cited by 75
Systematic review of class imbalance problems in manufacturing
de Giorgio, A., Cola, G., & Wang, L. (2023) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2023.10.014 · Cited by 87
AGCA: An Adaptive Graph Channel Attention Module for Steel Surface Defect Detection
Xiang, X., Wang, Z., Zhang, J., Xia, Y., Chen, P., & Wang, B. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3248111 · Cited by 87
“[42] is the steel sheet surface defect dataset collected in a real production environment.”
BackgroundVisual structural inspection datasets
Bianchi, E., & Hebdon, M. H. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104299 · Cited by 71
Cui, W., Song, K., Feng, H., Jia, X., Liu, S., & Yan, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3290965 · Cited by 81
“Based on the SD-900 dataset, we obtain most strip surface defect images from the open-source X-SDD [62] and GC10-DET [63], which are taken in the production and manufacturing stages.”
MethodA detection network for small defects of steel surface based on YOLOv7
Gao, S., Chu, M., & Zhang, L. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104484 · Cited by 67
A novel MAS-GAN-based data synthesis method for object surface defect detection
Zhang, H., Pan, D., Liu, J., & Jiang, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.021 · Cited by 64
VCP-CLIP: A Visual Context Prompting Model for Zero-Shot Anomaly Segmentation
Qu, Z., Tao, X., Prasad, M., Shen, F., Zhang, Z., Gong, X., & Ding, G. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72890-7_18 · Cited by 157
Zhong, H., Fu, D., Xiao, L., Zhao, F., Liu, J., Hu, Y., & Wu, B. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102437 · Cited by 64
A Review of Metal Surface Defect Detection Technologies in Industrial Applications
Qiao, Q., Hu, H., Ahmad, A. A., & Wang, K. (2025) · IEEE Access · doi:10.1109/access.2025.3544578 · Cited by 79
“The GC10-DET [132] dataset contains over 12,000 images across 10 common defect types, including dents, scratches, and cracks.”
Shen, X., Wang, Y., Ma, Y., Li, L., Niu, Y., Yang, Z., & Shi, Y. (2025) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2025.113117 · Cited by 61
EFS-YOLO: a lightweight network based on steel strip surface defect detection
Chen, B., Wei, M., Liu, J., Li, H., Dai, C., Liu, J., & Ji, Z. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad66fe · Cited by 61
“The effectiveness of the proposed algorithm is demonstrated using NEU-DET [32] and GC10-DET [33].”
Li, S., Kong, F., Wang, R., Luo, T., & Shi, Z. (2023) · Measurement · doi:10.1016/j.measurement.2023.113359 · Cited by 62
Metal surface defect detection based on improved YOLOv5
Zhou, C., Lu, Z., Lv, Z., Meng, M., Tan, Y., Xia, K., Liu, K., & Zuo, H. (2023) · Scientific Reports · doi:10.1038/s41598-023-47716-2 · Cited by 55
Li, P., Tao, H., Zhou, H., Zhou, P., & Deng, Y. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01643-y · Cited by 57
“The NEU-DET (North East University Dataset for Defect Detection) dataset [37] is a metal surface defect dataset created by Northeastern University, and widely used for defect detection and classification research.”
ALADA: A lite automatic data augmentation framework for industrial defect detection
Wang, Y., Chung, S., Khan, W. A., Wang, T., & Xu, D. J. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.102205 · Cited by 52
Image-Based Structural Health Monitoring: A Systematic Review
Payawal, J. M. G., & Kim, D. K. (2023) · Applied Sciences · doi:10.3390/app13020968 · Cited by 63
Lv, Z., Lu, Z., Xia, K., Zuo, H., Jia, X., Li, H., & Xu, Y. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108482 · Cited by 56
Ma, R., Chen, J., Feng, Y., Zhou, Z., & Xie, J. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103377 · Cited by 70
A Comprehensive Survey on Machine Learning Driven Material Defect Detection
Bai, J., Wu, D., Shelley, T., Schubel, P. J., Twine, D., Russell, J., Zeng, X., & Zhang, J. (2025) · ACM Computing Surveys · doi:10.1145/3730576 · Cited by 82
Apostolopoulos, I. D., & Tzani, M. A. (2022) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03688-7 · Cited by 57
“Known initially as GC10-DET dataset (Lv et al. 2020), this set refers to ten types of surface defects, i.e., punching (Pu), weld line (Wl), crescent gap (Cg), water spot (Ws), oil spot (Os), silk spot (Ss), inclusion (In), rolled pit (Rp), crease (Cr), waist folding (Wf).”
BackgroundHu, X., Yang, J., Jiang, F., Hussain, A., Dashtipour, K. K., & Gogate, M. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110578 · Cited by 57
Improving deep learning performance by using Explainable Artificial Intelligence (XAI) approaches
Bento, V., Kohler, M., Diaz, P., Mendoza, L. A. F., & Pacheco, M. A. C. (2021) · Discover Artificial Intelligence · doi:10.1007/s44163-021-00008-y · Cited by 55
Deep-learning-based anomaly detection for lace defect inspection employing videos in production line
Lu, B., Ding, X., & Huang, B. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101471 · Cited by 51
Tout, K., Meguenani, A., Urban, J.-P., & Cudel, C. (2021) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-020-06467-4 · Cited by 48
Industrial machine tool component surface defect dataset
Schlagenhauf, T., & Landwehr, M. (2021) · Data in Brief · doi:10.1016/j.dib.2021.107643 · Cited by 52
“Besides the classification of images, the authors introduce a dataset for instance segmentation which addresses the research problem of image-based size extraction and stands out from the already available datasets for metal surface defect detection like NEU-DET [3] , GC10-DET [4] , or SD-saliency-900 saliency [5] wit…”
MethodSharma, M., Lim, J., & Lee, H. (2022) · Applied Sciences · doi:10.3390/app12126004 · Cited by 49
“In this section, we provide a comparison between the proposed method and the traditional methods, which are HOG and LBP with two classifiers, neighbor classifier (NNC) and a support vector machine (SVM), based on the experimental results in [20].”
BackgroundMethodInfluentialSynthetic Object Recognition Dataset for Industries
Akar, C. A., Tekli, J., Jess, D., Khoury, M., Kamradt, M., & Guthe, M. (2022) · SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI) · doi:10.1109/sibgrapi55357.2022.9991784 · Cited by 59
“They focused on detecting defective casting [28], metal sheet surfaces [29], magnetic tiles [30], and solar module cells [31].”
BackgroundDefect Detection for Metal Base of TO-Can Packaged Laser Diode Based on Improved YOLO Algorithm
Liu, J., Zhu, X., Zhou, X., Qian, S., & Yu, J. (2022) · Electronics · doi:10.3390/electronics11101561 · Cited by 44
“However, these methods are susceptible to factors such as the shape, size, location, and external environment of the target object, making them difficult to be applied to practical projects on a large scale [11].”
BackgroundSchmedemann, O., Baaß, M., Schoepflin, D., & Schüppstuhl, T. (2022) · Procedia CIRP · doi:10.1016/j.procir.2022.05.115 · Cited by 55
Automatic quality inspection in additive manufacturing using semi-supervised deep learning
Manivannan, S. (2022) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-022-02000-4 · Cited by 48
“A morphological based image processing approach was proposed for fabric defect detection in Mallik-Goswami and Datta (2000).”
MethodPMSA-DyTr: Prior-Modulated and Semantic-Aligned Dynamic Transformer for Strip Steel Defect Detection
Su, J., Luo, Q., Yang, C., Gui, W., Sílven, O., & Liu, L. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2023.3347747 · Cited by 44
“7) Generalization ability: Experiments are conducted on defect databases, i.e., PCB-defect [35] and GC10-DET [36], which include various surface defects of industrial scenarios and are commonly used to verify the performance of defect detection models. which can be applied to practical complex…”
Cross-supervised contrastive learning domain adaptation network for steel defect segmentation
Zhao, L., Zhang, Y., Duan, J., & Yu, J. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102964 · Cited by 44
Selamet, F., Kaman, S. Ç., & Kotan, M. (2022) · IEEE Access · doi:10.1109/access.2022.3224037 · Cited by 44
“Lv et al. [22] created a new dataset called GC10-DET containing ten defect types for metallic surface defect detection.”
BackgroundCABF-YOLO: a precise and efficient deep learning method for defect detection on strip steel surface
Zhou, Q., & Wang, H. (2024) · Pattern Analysis and Applications · doi:10.1007/s10044-024-01252-5 · Cited by 39
“The GC10-DET dataset is a public dataset of surface defects on steel plates collected in real industrial scenarios [24].”
Large scale foundation models for intelligent manufacturing applications: a survey
Zhang, H., Semujju, S. D., Wang, Z., Lv, X., Xu, K., Wu, L., Jia, Y., Wu, J., Liang, W., Zhuang, R., et al. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02536-7 · Cited by 83
“…fine-tuning: Altough some preliminary work provided datasets for intelligent manufacturing scenarios such as HAR [366]–[368], quality control [369]–[371], and PHM [372], [373], these datasets were characterized by small scales, narrow coverage, singular scenes, simple operating conditions, and…”
Self-citationMetal Surface Defect Detection Method Based on Improved Cascade R-CNN
Wang, Y., Wang, X., Hao, R., Lu, B., & Huang, B. (2023) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4063860 · Cited by 47
TD-Net:tiny defect detection network for industrial products
Shao, R., Zhou, M., Li, M., Han, D., & Li, G. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01362-x · Cited by 47
“We conducted experiments on NEU–DET [33], GC10-DET [34] and Peking University PCB defect data sets [35] to verify the effectiveness of the proposed method.”
GDCP-YOLO: Enhancing Steel Surface Defect Detection Using Lightweight Machine Learning Approach
Yuan, Z., Hao, N., Tang, X., & Yang, Z. (2024) · Electronics · doi:10.3390/electronics13071388 · Cited by 43
Lv, S., Liang, T., Zhang, K., Jiang, S., Ouyang, B., Li, Q., & Li, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125727 · Cited by 45
A Graph Guided Convolutional Neural Network for Surface Defect Recognition
Wang, Y., Gao, L., Gao, Y., & Li, X. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3140784 · Cited by 39
“GCNN is tested on four famous benchmark datasets of surface defect, NEU-CLS [22], wood dataset [23], textile dataset [24], and GC10 [25].”
MethodLiu, B.-H., Zhang, T., Yao, Y., & Miao, L. (2023) · Computers in Industry · doi:10.1016/j.compind.2023.103963 · Cited by 39
HM-YOLOv5: A fast and accurate network for defect detection of hot-pressed light guide plates
Li, J., & Yang, Y. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105529 · Cited by 34
Huang, J., Zhang, X., Jia, L., & Zhou, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110214 · Cited by 41
A detection method of spangle defects on zinc-coated steel surfaces based on improved YOLO-v5
Xiao, D., Xie, F. T., Gao, Y., Li, Z. N., & Xie, H. (2023) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-11963-4 · Cited by 38
Zhao, H., Wan, F., Lei, G., Xiong, Y., Xu, L., Xu, C., & Wen, Z. (2023) · Sensors · doi:10.3390/s23146558 · Cited by 34
Steel surface defect detection based on MobileViTv2 and YOLOv8
Lv, Z., Zhao, Z., Xia, K., Gu, G., Liu, K., & Chen, X. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06248-w · Cited by 37
“Lv et al. [19] introduced a novel end-to-end defect detection network specifically designed for detecting various types of steel surface defects.”
An efficient detector for detecting surface defects on cold-rolled steel strips
Chen, S., Jiang, S., Wang, X., Sun, P., Hua, C., & Sun, J. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109325 · Cited by 43
WFRE-YOLOv8s: A New Type of Defect Detector for Steel Surfaces
Huang, Y., Tan, W., Li, L., & Wu, L. (2023) · Coatings · doi:10.3390/coatings13122011 · Cited by 39
“GC10-DET [52] was proposed by the team of Xiaoming Lv in 2020.”
BackgroundYOLO-ADS: An Improved YOLOv8 Algorithm for Metal Surface Defect Detection
Gui, Z., & Geng, J. (2024) · Electronics · doi:10.3390/electronics13163129 · Cited by 37
Wu, X., Duan, J., Yang, L., & Duan, S. (2024) · Computers in Industry · doi:10.1016/j.compind.2024.104146 · Cited by 35
Xia, Z., Zhao, Y., Gu, J., Wang, W., Zhang, W., & Huang, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.126142 · Cited by 36
Strip steel surface defect detecting method combined with a multi-layer attention mechanism network
Liu, G., & Ma, Q. (2023) · Measurement Science and Technology · doi:10.1088/1361-6501/acb5b5 · Cited by 33
“Figure 9 shows the detection performance of our model for various defects on GC10-DET, which is overall optimal.”
BackgroundInfluentialZhong, H., Xiao, L., Wang, H. F., Zhang, X., Wan, C., Hu, Y., & Wu, B. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112520 · Cited by 37
Nguyen, H.-V., Bae, J.-H., Lee, Y.-E., Lee, H., & Kwon, K. (2022) · Sensors · doi:10.3390/s22249926 · Cited by 41
“[10] contributed a novel large-scale steel surface defect dataset, namely GC10-DET, and also proposed improved SSD with hard negative mining to encounter the problem of different scales and data imbalance of defects.”
BackgroundEfficient Neural Net Approaches in Metal Casting Defect Detection
Lal, R., Bolla, B. K., & Ethiraj, S. (2023) · Procedia Computer Science · doi:10.1016/j.procs.2023.01.172 · Cited by 32
Research on a Metal Surface Defect Detection Algorithm Based on DSL-YOLO
Wang, Z., Zhao, L., Li, H., Xue, X., & Liu, H. (2024) · Sensors · doi:10.3390/s24196268 · Cited by 35
“This paper uses two public datasets, GC10-DET dataset [38] and NEU-DET dataset.”
MethodFD-YOLO11: A Feature-Enhanced Deep Learning Model for Steel Surface Defect Detection
Dang, Z., & Wang, X. (2025) · IEEE Access · doi:10.1109/access.2025.3559733 · Cited by 35
Huang, J., Zhang, X., Jia, L., & Zhou, Y. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad6281 · Cited by 31
“The effectiveness of the proposed method was evaluated on the steel surface defect samples from the NEU-DET dataset [3] and GC10-DET dataset [25], respectively.”
Ragab, K. (2023) · Sensors · doi:10.3390/s23010544 · Cited by 24
“It also outperforms the recent technique called end-to-end defect detection (EDDN) [71] that added to Vgg16 extra ar- chitectures including multi-scale feature maps and predictors for detection.”
MethodInfluentialQian, K., Zou, L., Wang, Z., & Wang, W. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.111589 · Cited by 31
A Review and Benchmark on State-of-the-Art Steel Defects Detection
Chazhoor, A. A. P., Ho, E. S. L., Gao, B., & Woo, W. L. (2023) · SN Computer Science · doi:10.1007/s42979-023-02436-2 · Cited by 41
“Lv et al. [33] contributed a new dataset GC10-DET and benchmarked state-of-the-art deep learning models including (single-stage detector) SSD, faster R-CNN, and YOLO (You Only Look Once) algorithms on the NEU-DET and GC10-DET dataset along with proposing a novel method to address the accuracy…”
MethodCFE-YOLOv8s: Improved YOLOv8s for Steel Surface Defect Detection
Yang, S., Xie, Y., Wu, J., Huang, W., Yan, H., Wang, J., Bi, W., Yu, X., Wu, Q., & Xie, F. (2024) · Electronics · doi:10.3390/electronics13142771 · Cited by 29
STD2: Swin Transformer-Based Defect Detector for Surface Anomaly Detection
Mia, M. S., & Li, C. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3492728 · Cited by 43
Liang, F., Wang, Z., Ma, W., Liu, B., En, Q., Wang, D., & Duan, L. (2024) · Measurement · doi:10.1016/j.measurement.2024.116255 · Cited by 27
Feature optimization-guided high-precision and real-time metal surface defect detection network
Chan, S., Li, S., Zhang, H., Zhou, X., Mao, J., & Hong, F. (2024) · Scientific Reports · doi:10.1038/s41598-024-83430-3 · Cited by 31
Surface Defect Detection with Modified Real-Time Detector YOLOv3
Wang, Z., Zhu, H., Jia, X., Bao, Y., & Wang, C. (2022) · Journal of Sensors · doi:10.1155/2022/8668149 · Cited by 31
“com/lvxiaoming2019/GC10-DETMetallic-Surface-Defect-Datasets) [26].”
Metadata
- Authors
- Lv, X., Duan, F., Jiang, J.-J., Fu, X., & Gan, L.
- Affiliations
- Tianjin University (CN)
- The State Key Lab of Precision Measuring Technology and Instruments, Tianjin University, Tianjin 300072, China
- Corresponding author
- Duan, Fajie
- Venue
- Sensors
- Publisher
- MDPI AG
- Published
- 2020-03-11
- Volume
- 20
- Issue
- 6
- Pages
- 1562
- ISSN
- 1424-8220 (ISSN-L)
- PMC
- PMC7146379
- OpenAlex
- W3012374719
- Cited by
- 643
- References
- 38
- Citations by year
- 2026: 188 · 2025: 188 · 2024: 125 · 2023: 81 · 2022: 40 · 2021: 18 · 2020: 3
- FWCI
- 18.23
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Sensors (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundations of China (No.61905175, 51775377, 61971307)
- National key research and development plan (2017YFF0204800)
- the TianJin Natural Science Foundations of China (No. 17JCQNJC01100)
- Equipment pre-research field fund (61405180505, 61400040303)
- Science and Technology on Underwater Information and Control Laboratory (6142218081811)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Keywords
- Single Shot MultiBox Detector, hard negative mining, class imbalance, data augmentation, industrial inspection, object detection
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.