An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features
Open accessThe DOI matches its Crossref record; 43 of the 53 references it cites were found in a registry or an index.
Abstract
A complete defect detection task aims to achieve the specific class and precise location of each defect in an image, which makes it still challenging for applying this task in practice. The defect detection is a composite task of classification and location, leading to related methods is often hard to take into account the accuracy of both. The implementation of defect detection depends on a special detection data set that contains expensive manual annotations. In this paper, we proposed a novel defect detection system based on deep learning and focused on a practical industrial application: steel plate defect inspection. In order to achieve strong classification ability, this system employs a baseline convolution neural network (CNN) to generate feature maps at each stage, and then the proposed multilevel feature fusion network (MFN) combines multiple hierarchical features into one feature, which can include more location details of defects. Based on these multilevel features, a region proposal network (RPN) is adopted to generate regions of interest (ROIs). For each ROI, a detector, consisting of a classifier and a bounding box regressor, produces the final detection results. Finally, we set up a defect detection data set NEU-DET for training and evaluating our method. On the NEU-DET, our method achieves 74.8/82.3 mAP with baseline networks ResNet34/50 by using 300 proposals. In addition, by using only 50 proposals, our method can detect at 20 ft/s on a single GPU and reach…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“There are some shortcomings in manual testing, such as low confidence and high labor intensity.”
From A New Steel Defect Detection Algorithm Based on Deep Learning (2021) · cites this paper as [5]
In the citing paper
“most classification tasks can only find the defects with the highest confidence level in the defect category, resulting in imprecise classification results [3].”
From Steel Surface Defect Recognition: A Survey (2022) · cites this paper as [3]
In the citing paper
“there are many types of steel surface defects and some of these defects may overlap”
From Steel Surface Defect Recognition: A Survey (2022) · cites this paper as [3]
In the citing paper
“Using manual inspection of steel surface defects, it is difficult to distinguish the type of defect and accurately detect the location of the defect [2].”
From A deep learning model for steel surface defect detection (2024) · cites this paper as [2]
In the citing paper
“There are many categories of steel surface defects and the size of each defect category varies widely. The average size of each category in the NEU-DET [34] dataset is shown in Table1.”
From A deep learning model for steel surface defect detection (2024) · cites this paper as [34]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“The third type is ResNet using residual blocks to make networks deeper without overfitting [23].”
MethodVery Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
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×
“cessful networks are based on the sequential pipeline architecture [25], which establish the basic structure of CNN and prove the importance of depth of networks.”
BackgroundLeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Faster 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 · cited 6×
“Next, RPN [14] is employed to generate region proposals”
BackgroundMethodInfluentialFaster 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 · cited 6×
“Next, RPN [14] is employed to generate region proposals”
BackgroundMethodInfluentialImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333 · cited 1×
“As current research in transfer learning [15], the key to drive large networks is pretraining on ImageNet [22].”
BackgroundGradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“combined? There are two essential conditions: nonadjacent, because adjacent layers have highly local correlation [32], and”
BackgroundYou Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803 · cited 1×
“The representative direct regression methods are YOLO [29] and SSD [30].”
MethodFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834 · cited 2×
“The most famous region-based detectors are the “R-CNN family” [27] [28] [14].”
BackgroundMethod
Cited by
Items 801–900 of 1,338
AI-based Endpoint Detection for Surface Defect Removal on Aircraft Components
Kähler, F., Shetty, A. C. K., & Schüppstuhl, T. (2023) · IEEE/SICE International Symposium on System Integration (SII) · doi:10.1109/sii55687.2023.10039239 · Cited by 5
“Commonly available databases such as NEU Surface Defect Database [9] and Image-based Corrosion Detection Dataset [22] consist of generic corrosion images.”
BackgroundMethodDeep Learning Applications in Identifying Deep Metallic Surface Defects
Leong, R. T. J. C. K., Rodriguez, F. E. A., Vidad, A. J. P., et al. (2022) · IEEE International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment, and Management (HNICEM) · doi:10.1109/hnicem57413.2022.10109392 · Cited by 3
“The output of each convolution is used in the later parts of the top-down pathway [19].”
MethodA Deep-Learning-Based Low-Cost Micro-Leakage Measurement System for Industrial Applications
Ding, Z., Song, W., Xu, J., Cheng, W., & Zhan, S. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3272797 · Cited by 3
“With the increasing application of deep learning and machine vision technology in the field of product defect detection [21], [22], [23], [24], [25], [26], [27], [28], [29], tightness detection based on machine vision technology has gradually attracted the attention of researchers [30], [31].”
BackgroundA Real-Time Inspection System for Industrial Helical Gears
Idzik, T., Veres, M., Tarry, C., et al. (2023) · Sensors · doi:10.3390/s23208541 · Cited by 3
“It has been used, for example, in problems such as: steel surface detection (6 defects) [4], vehicle body paint inspection [5] (6 defects), power-train transmission inspection [6] (2 defects), bearing inspection [7] (4 defects), wheel hub inspection [8] (4 defects), and others [9] (1 defect).”
MethodCHBS-Net: 3D Point Cloud Segmentation Network with Key Feature Guidance for Circular Hole Boundaries
Zhang, J., Wang, X., Li, Y., & Liu, Y. (2023) · Machines · doi:10.3390/machines11110982 · Cited by 4
Improved Yolov5n strip surface defect detection algorithm
Tang, L., Cai, L. C., Cheng, K., Wang, X., Luo, C., & Zhao, Y. (2023) · CAA Symposium on Fault Detection, Supervision and Safety for Technical Processes (SAFEPROCESS) · doi:10.1109/safeprocess58597.2023.10295728 · Cited by 3
“He[12] et al, proposed an inspection network that requires few defect samples for training to achieve good defect detection.”
BackgroundMethodWang, C., Wei, X., Wu, X., et al. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10393899 · Cited by 3
Phan, H.-A., Duong, V. T., Thi, M. N., Thi, A. N., Thu, H. K. T., Duc, T. L., Dang, V. H., Tran, H. Q. D., Van, N. T. T., & Bui, T. T. (2024) · ECTI Transactions on Computer and Information Technology (ECTI-CIT) · doi:10.37936/ecti-cit.2024181.253854 · Cited by 3
Prior-Guided YOLOX for Tiny Roll Mark Detection on Strip Steel
Luo, Q., Chen, Y., Su, J., Yang, C., Sílven, O., & Liu, L. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3374388 · Cited by 4
An Efficient Bidirectional Weighted Global Feature Extraction Algorithm for Steel Surface Defects
Zhang, T., Xie, G., Xie, X., Li, L., Zhang, H., & Liang, Y. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10451161 · Cited by 3
“In the process of strip steel production, a perfect quality inspection system can effectively guarantee the yield of products [1].”
BackgroundDippold, E. J., & Tsai, F. (2024) · Italian National Conference on Sensors · doi:10.3390/s24072358 · Cited by 2
“The process of feature detection [6] and matching is crucial [7] to successfully estimating the pose and triangulating the features [8].”
MethodSurface Defect Detection of Aluminum Profiles Based on Multiscale and Self-Attention Mechanisms
Shao, Y., Fan, S., Zhao, Q., Zhang, L., & Sun, H. (2024) · Sensors · doi:10.3390/s24092914 · Cited by 7
Slim-YOLOv8: A fast and accurate algorithm for surface defect detection of steel strips
Zhao, J., Liu, S., Tao, H., & Liu, W. (2024) · Ironmaking & Steelmaking Processes Products and Applications · doi:10.1177/03019233241266717 · Cited by 4
Scale Adaptive Attention Network for Accurate Defect Detection From Metal Parts
Sun, Z., Wang, X., Luo, F., Zhang, Z., & Li, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3432660 · Cited by 3
“…computer-assisted approaches are exploited to defect detection from the metal part surface [12], [13], and they The associate editor coordinating the review of this manuscript and approving it for publication was Bo Pu . can be classified as traditional approaches and deep learning methods [14].”
MethodAdvancing Robust Few-shot Surface Defect Detection through Meta-learning
Putri, W. R., Li, Y., & Wang, J. (2024) · International Conference on Integrated Circuits, Design, and Verification (ICDV) · doi:10.1109/icdv61346.2024.10616593 · Cited by 4
“We perform experiments using the NEU surface defect dataset, which was generated by Northeastern University [7].”
MethodRDMS: Reverse distillation with multiple students of different scales for anomaly detection
Chen, Z., Lyu, C., Zhang, L., Li, S., & Xia, B. (2024) · IET Image Processing · doi:10.1049/ipr2.13210 · Cited by 5
Xiong, Q., Chen, Q., Tang, S., & Li, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-85721-9 · Cited by 3
“He et al. 26 proposed a deep learning defect detection system for steel plate defect detection, based on a multilevel-feature fusion network (MFN).”
Efficient progressive aggregation enhancement network for defect detection
Yu, K., Zhang, H., Lyu, W., Guo, Q., Deng, Z., & Xu, W. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adbf86 · Cited by 4
“He et al [20] introduced a multilevel feature network that amalgamates multilevel features into a unified feature, thereby capturing finer details regarding the defect locations on the strip surface and effectively elevating the precision of strip surface defect detection.”
A Semi-Supervised Method for Steel Surface Defect Detection Based on Soft-teacher
Heng Xiao1, 2. (2023) · Academic Journal of Computing & Information Science · doi:10.25236/ajcis.2023.060302 · Cited by 2
“Percent of labeled AP50 mAP 20% 66.5 30.0 40% 69.2 31.4 50% 70.6 32.0 Faster-RCNN(20”
MethodInfluentialFeature Selection for Image Classification Based on Bacterial Colony Optimization
Wang, H., Zhou, Z., Wang, Y., et al. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-78811-7_40 · Cited by 3
Metal Surface Defect Detection Based on Weighted Fusion
Wang, C., Xu, J., Liang, X., & Yin, D. (2020) · International Conference on Virtual Reality and Visualization · doi:10.1109/icvrv51359.2020.00044 · Cited by 3
Steel Surface Defect Detection Based on Improved YOLOv5
Song, X. G., Li, W., & Lu, J. (2023) · IEEE International Conference on Control Science and Systems Engineering (ICCSSE) · doi:10.1109/iccsse59359.2023.10245740 · Cited by 3
“Therefore, with the popularity of computer vision methods based on deep learning [12] [13] [14] [15] [16] [17], more and more researchers apply deep learning methods to surface defect detection, replacing traditional methods and machine learning methods.”
Zhou, S., Liu, H., Cui, K., & Hao, Z. (2021) · ISIJ International · doi:10.2355/isijinternational.isijint-2021-115 · Cited by 3
An Improved Yolo-V5 Network for Defect Detection of a Boiler Inner WallPreprint
Sun, X., Jia, X., Liang, Y., Yang, B., Wang, M., & Chi, X. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4057058 · Cited by 3
YOLOv8-FCS: A more focused YOLOv8 model for defect detection in images of steel surfacePreprint
Hu, B., Lu, R., Wan, D., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-4368440/v1 · Cited by 3
Visual and corresponding tactile dataset of flexible material for robots and cross modal perception
Xu, S., Xu, H., Mao, F., et al. (2024) · Data in Brief · doi:10.1016/j.dib.2024.110836 · Cited by 3
Yue, H., Wang, R., Gao, Y. C., Xia, A., Su, K., & Zhang, J. (2024) · IET Collaborative Intelligent Manufacturing · doi:10.1049/cim2.12092 · Cited by 2
He, X., Fan, H., Du, C., Zhu, X., Zhou, Y., Chen, R., Li, Z., Zheng, G., Zhong, Y., Liu, C., et al. (2024) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2024.0150284 · Cited by 2
LAM-YOLOv10: lightweight and multiscale feature enhancement for paint surface defect detection model
Zhao, D., Sun, R. F., Li, W., Ma, Y., Tong, T., Yuan, X., Wang, D., Liu, P., Li, B., Kong, D., et al. (2025) · Journal of Electronic Imaging · doi:10.1117/1.jei.34.3.033022 · Cited by 2
“21 The subsequent content of this paper is outlined as follows: Sec.”
Huang, J., Ariffin, S. A., Zhu, Q., et al. (2025) · PLoS ONE · doi:10.1371/journal.pone.0327001 · Cited by 2
“Additionally, the publicly available NEU-DET [34] dataset was utilized to further validate the effectiveness and performance of our proposed approach.”
Improved of YOLOv8-n Algorithm for Steel Surface Defect Detection
Xiang, Q., Wu, G., Liu, Z., et al. (2025) · Metals · doi:10.3390/met15080843 · Cited by 2
Wu, R., Zhang, Y., Lan, R., & Zhou, L. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129867 · Cited by 5
FSU-YOLO: aero-engine blade defect detection based on improved YOLOv8
An, Y., Chen, X., He, X., Xiong, X., Kong, D., & Song, P. Y. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae0ea0 · Cited by 6
“Furthermore, to demonstrate the generalization capability of the proposed architecture, this paper conducted comparative generalization experiments using typical defects from the steel surface dataset NEU-DET [48].”
DFM-DETR: frequency-suppressed Mamba detector for high-reflectivity ceramic plates defects
Yang, L., Gu, Y., & Feng, H. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2593427 · Cited by 3
Fu, J., Zhang, Z., Peng, T., Hu, X., & Zhang, J. (2025) · Sensors · doi:10.3390/s26010023 · Cited by 2
“The NEU-DET [44] dataset comprises steel surface defects with six classes: Cr (crazing), Ic (inclusion), Ps (pitted surface), Rs (rolled-in scale), Sc (scratches), and Pc (patches).”
Yi, C., Wang, Z., Xiao, H., et al. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2584631 · Cited by 2
DGS-YOLO: A Lightweight YOLOv8-Based Method for Steel Surface Defect Detection
Zhang, X., Jian, M., Zhou, S., Cong, S., & Sheng, Z. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3649514 · Cited by 3
“Consequently, manual inspection struggles to achieve precise defect identification and localization on steel surfaces [1].”
Cai, R., Ouyang, H., Li, S., Wang, G., & Ding, W. (2026) · Information Sciences · doi:10.1016/j.ins.2026.123141 · Cited by 2
Gao, M., Kang, X., Zhou, K., & Xie, T. (2026) · Measurement · doi:10.1016/j.measurement.2026.120671 · Cited by 3
YOLO-MDMN: a new lightweight algorithm for efficient PCB defect detection
Tang, Z., Xiong, X., Lan, H., et al. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae46b6 · Cited by 2
AHD-Net: A damage detector and dataset for architectural heritage
Long, L., Zhao, B., Gan, Z., Zhang, D., & Li, Q. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.131775 · Cited by 3
EDS-YOLO: an enhanced steel surface defect detection method based on improved YOLO11
Fei, Z., Liu, L., Zhao, R., Yang, C., Li, Y., & Xiang, X. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae5271 · Cited by 3
DSF-Net: A directional spatial-frequency fusion network for accurate metal surface defect detection
Zuo, Y., Qu, Z., Zhang, S.-S., Yu, Z., Cai, X., Yang, Y., Yang, Y., Jiang, X., & Lin, C. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132378 · Cited by 3
YOLOv11-LLR: An Enhanced Framework for Steel Surface Defect Detection in Industrial Settings
Li, J., Yang, Y., Geng, R., et al. (2026) · Applied Sciences · doi:10.3390/app16104609 · Cited by 2
A Novel Defect Detection Method for Ferrite Shield Surface Defects by Improved Faster R-CNN
Ye, X., Ye, J., He, Z., Zhang, D., Hu, X., & Chen, Q. (2022) · Scientific Programming · doi:10.1155/2022/5695243 · Cited by 3
“added a multilevel feature fusion network (MFN) on the basis of the CNN model [10] and combined with the region proposals network to achieve 82.”
MethodLi, K., Yang, Q. Z., Lei, S., Gu, J., & Wensheng, S. (2022) · Journal of Mechanical Engineering · doi:10.3901/jme.2022.24.032 · Cited by 4
Meta++ Network for Few-Shot Aerospace Crack Segmentation
Xu, C., Liu, K., & Li, X. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10097127 · Cited by 2
“In recent years, machine learning methods have gradually been widely used in various environments crack detection due to their accuracy and robustness, such as hot-rolled steel plates [1], nanofiber materials [2], fabric [3] and so on.”
BackgroundSteel Surface Defect Detection and Classification Using Bag of Visual Words with BRISK
Ibrahim, A. A. M. S., & Tapamo, J. (2023) · Smart innovation, systems and technologies · doi:10.1007/978-981-99-2468-4_18 · Cited by 6
Surface Defect Detection Method for Steel Materials Based on Improved YOLOv7
Luo, S., Jia, B., Zhao, J., & Niu, Q. (2023) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc58118.2023.10270248 · Cited by 3
“To verify the improvements made to the YOLOv7 model in this paper, we used the publicly available dataset NEU-DET [19] .”
MethodA Novel Image Super-Resolution Approach for Industrial Product Visual Enhancement
Zhang, H., Teng, L., Qu, H., Wang, P., & Tang, C. Y. (2023) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon51785.2023.10311675 · Cited by 3
“In the second experiment, the Northeastern University (NEU) Surface Defect Database (NEU-CLS) is employed [20-22].”
MethodAPPLICATION OF MACHINE LEARNING FOR RECOGNIZING SURFACE WELDING DEFECTS IN VIDEO SEQUENCES
Yemelyanova, M., & Smailova, S. S. (2024) · Scientific Journal of Astana IT University · doi:10.37943/16ryge2979 · Cited by 3
“Pattern recognition involves the tasks of detecting and classifying surface defects of products [1] occurring in industrial production, in particular, defects in fabric [2], marble slabs [3], steel plates [4], rolled steel sheets [5], and various steel products [6].”
BackgroundÇift Doğrusal CNN Kullanarak Çelik Yüzey Kusurlarının Sınıflandırılması
Güçlü, E., Aydın, İ., & Akın, E. (2024) · Fırat Üniversitesi Mühendislik Bilimleri Dergisi · doi:10.35234/fumbd.1323339 · Cited by 2
Detection of Surface Defect on Impeller Blade Images based on Improved Centernet Algorithm
Wang, C., Zhang, M., Zhu, W., Wang, C., Bo, C., & Peng, H. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10452033 · Cited by 2
MACN: A cascade defect detection for complex background based on mixture attention mechanism
Zhao, L., Wu, Y., Yuan, Y., et al. (2024) · IET Image Processing · doi:10.1049/ipr2.13108 · Cited by 2
New Possibilistic Formalism Based on Confidence Levels for Metallic Surface Defect Classification
Elleuch, J. F., Mehdi, M. Z., Kammoun, H. M., Bellaaj, M., & Sellami, D. (2024) · IEEE Access · doi:10.1109/access.2024.3414840 · Cited by 3
“For instance He et al. [4], built upon Faster R-CNN and suggested the aggregation of multiple hierarchical features into a unified feature for the ultimate defect prediction.”
BackgroundMethodMCAC-UNet: Multi scale Attention Cascade Compensation U-Net Network forRail Surface Defect Detection
Wu, Z., Lv, J., Sun, X., & Niu, W. (2024) · Asia Conference on Computer Vision, Image Processing and Pattern Recognition (CVIPPR) · doi:10.1145/3663976.3664009 · Cited by 3
“He et al.[6] proposed a defect detection system DDN based on a residual neural network (ResNet50) as the foundational model for classification.”
MethodMetal Structural Defect Detection Based-On Deep Learning and Grad-Cam
Mehadjbia, A., & Slaoui-Hasnaoui, F. (2024) · International Conference on Circuit, Systems and Communication (ICCSC) · doi:10.1109/iccsc62074.2024.10617066 · Cited by 2
“Although existing classification techniques are limited to accurately detecting faults that have high with value in term of confidence within a specific class [8].”
BackgroundA Study on the Improvement of YOLOv5 and the Quality Detection Method for Cork Discs
Qu, L., Chen, G., Liu, K., et al. (2024) · Photonics · doi:10.3390/photonics11090825 · Cited by 2
“Examples include rubber threading line detection [13], metal surface defect detection [14–16], fabric defect detection [17], and sanitary ceramic defect detection [18], providing new solutions for cork disc quality screening.”
Semantic Web-Based Image Super-Resolution for Enhanced Steel Surface Defect Detection
Hao, C., & Gu, H. (2024) · International Journal on Semantic Web and Information Systems · doi:10.4018/ijswis.358452 · Cited by 2
Liu, X., Liu, J., Fu, M., et al. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3508774 · Cited by 2
“2) NEU-CLS: The NEU-CLS [40] is an open-access dataset of hot-rolled steel strip collected by Northeast University in China, where defects are incurred due to various fac-Fig tors such as uneven cooling, improper rolling parameters, or contaminants present during the manufacturing process.”
Enhanced Sagger Crack Detection Integrating Deep Learning and Machine Vision
Song, T., Chen, T., Gong, Y., Wang, Y., Ran, L., Chen, J., Tang, H., & Zou, Z. (2024) · Electronics · doi:10.3390/electronics13245010 · Cited by 3
Metal Surface Defect Detection Method Based on Improved YOLOv7
Zhang, Y., Chao, Y., Pei, R., et al. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2625-0_22 · Cited by 2
DMC-Net: a lightweight network for real-time surface defect segmentation
Zuo, H., Zheng, Y., Huang, Q., Du, Z., & Wang, H. (2025) · Journal of Real-Time Image Processing · doi:10.1007/s11554-025-01639-5 · Cited by 2
“He et al. [7] designed an end-to-end detection model that can effectively locate and classify surface defects on steel.”
Li, H., Wang, Z., Qiu, L., & Wei, X. (2025) · Applied Sciences · doi:10.3390/app15052484 · Cited by 2
Industrial defect detection model based on transfer learning and spatial attention mechanisms
Li, W., Chen, Y., Wang, N., & Tian, J. (2025) · Engineering Optimization · doi:10.1080/0305215x.2025.2485147 · Cited by 2
“Baseline CNN combined with multilevel feature fusion and region proposal networks was employed by He et al .”
Luo, A., Wen, G., Chen, Z., & Liu, X. (2025) · IEEE Sensors Journal · doi:10.1109/jsen.2025.3578508 · Cited by 5
“I NDUSTRIAL anomaly detection is a crucial component in the field of industrial production, which significantly impacts the yield rate of products [1], [2], [3].”
Li, L., Yu, Y., Xie, J., & Cai, Y. (2025) · Knowledge-Based Systems · doi:10.1016/j.knosys.2025.113884 · Cited by 2
CSCP-YOLO: A Lightweight and Efficient Algorithm for Real-Time Steel Surface Defect Detection
Wang, C., Wang, H., Jiang, Y., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3581024 · Cited by 2
Zhao, Z. (2025) · Advances in Engineering Innovation · doi:10.54254/2977-3903/2025.24461 · Cited by 4
Edge-Guided DETR Model for Intelligent Sensing of Tomato Ripeness Under Complex Environments
Yao, J., Zhou, J., Nie, Y., Xue, J., Lin, K., & Tan, L. (2025) · Mathematics · doi:10.3390/math13132095 · Cited by 5
NGD-YOLO: An Improved Real-Time Steel Surface Defect Detection Algorithm
Li, B., Xiao, A., Hu, X., et al. (2025) · Electronics · doi:10.3390/electronics14142859 · Cited by 2
Dai, C., Lu, S., Wang, P., Yin, H., Wang, Y., Liu, X., & Guo, B. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3593950 · Cited by 3
“For industrial defect detection, we employ the NEU64 dataset [31], comprising 1800 high-resolution surface defect images across 9 categories, processed through a customized MobileNetV2 [32] architecture with 377 K parameters.”
Global-Regularized Neighborhood Regression for Efficient Zero-Shot Texture Anomaly Detection
Yao, H., Luo, W., Cao, Y., Zhang, Y., Yu, W., & Shen, W. (2025) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2025.3595539 · Cited by 8
“For example, a multilevel feature fusion network for end-to-end strip anomaly defect detection was proposed in [8].”
FDC-YOLO: A Blur-Resilient Lightweight Network for Engine Blade Defect Detection
Xu, X., Li, F., Xiong, L., He, C., Peng, H., Zhao, Y., & Song, G. (2025) · Algorithms · doi:10.3390/a18110725 · Cited by 2
“To validate the advantages of the FDC-YOLO model in metal surface defect detection, we selected the hot-rolled strip steel surface defect detection dataset published by North-eastern University (NEU-DET) [36].”
Li, D., Ci, X., & Li, C. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae2762 · Cited by 4
Spoon Surface Defect Detection Based on Improved YOLO V3
Wu, C., & Zeng, Z. (2022) · Frontiers in artificial intelligence and applications · doi:10.3233/faia220021 · Cited by 2
GFU-Net: A Deep Learning Approach for Automatic Metal Crack Detection
Zhang, Y., Li, X., Qiu, J., Zhai, X., & Wei, M. (2021) · Communications in computer and information science · doi:10.1007/978-981-16-5188-5_27 · Cited by 4
Texture Descriptors for Automatic Classification of Surface Defects of the Hot-Rolled Steel Strip
del Castillo, V. R., Sánchez-González, L., & Gutiérrez-Fernández, A. (2021) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-87869-6_24 · Cited by 3
Tang, J., Cao, S., Chen, J., Song, T., Xu, Z., Zhou, Q., & Jiang, Q. Y. (2022) · Applied Sciences · doi:10.3390/app12126049 · Cited by 2
An Intelligent Detection Method for Civil Aircraft Skin Damage Based on YOLOv3
Zhou, M., Zuo, H., Xu, J., et al. (2022) · Asia-Pacific Conference on Image Processing, Electronics and Computers (IPEC) · doi:10.1145/3544109.3544317 · Cited by 2
“[5] proposed a strip steel surface defect detection method based on Faster R-CNN.”
MethodImage Detection of Metal Surface Defects Based on Improved YOLOX-S Network
吴, 超. (2022) · Mechanical Engineering and Technology · doi:10.12677/met.2022.114044 · Cited by 2
“本文实验采用 NEU-DET 数据集与自制金属插头表面缺陷数据集,NEU-DET 数据集是东北大学的 NEU 数据集中目标检测部分的数据集,其图像数据部分是 NEU-CLS 数据集构成。数据集的缺陷边界框 的标注信息采用 xml 格式文件保存,标注的边界框信息共 4186 个,其中夹杂种类缺陷标注数最多,达到 了 1011 个,麻点种类缺陷标注数最少,为 432 个。对于自制金属插头表面缺陷数据集,使用图像标注工 具 LabelImg 对含有缺陷的图像进行目标的边界框标注,形成标签数据集。 将数据集按照 7:3 的比例划分为训练集与测试集,训练集中 10%的数据用于验证。采用的实验配置 环境见表 1,相关的实验主要分为两个主要部分…”
InfluentialShen, Z., Hu, H., Huang, Z., Zhang, Y., Wang, Y., & Li, X. (2022) · Materials · doi:10.3390/ma15197037 · Cited by 2
“Computer vision methods have been applied successfully to facial image recognition [4] and object detection [5] and can also be extended to industrial testing applications.”
MethodHuman-Centred Acoustic Detection for Smartphone Application in Healthcare
Qu, Y., Wang, X., Yu, L., et al. (2022) · Advances in medical technologies and clinical practice book series · doi:10.4018/978-1-6684-5092-5.ch006 · Cited by 2
PPT: Anomaly Detection Dataset of Printed Products with Templates
Tian, H., Li, X., Yang, L., Li, J., Yang, J. J., & Du, W. (2022) · Proceedings - International Conference on Image Processing · doi:10.1109/icip46576.2022.9897321 · Cited by 2
“In general, compared to other industrial anomaly detection datasets [7, 10], our dataset focuses on printed products and poses more challenges.”
ResultAn adaptive weighting multimodal fusion classification system for steel plate surface defect
Tu, F., Wei, M. H., Liu, J., & Liao, L. L. (2023) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-230170 · Cited by 3
“He et al. (2020) [4] proposed a new defect detection system based on deep learning.”
Shi, Y., Li, L., Yang, J. H., et al. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3301053 · Cited by 2
“2) SIPRPC: Considering that the grayscale of the surface defect images is varied with the brightness of photographs [22], we collect SIPRPC dataset including two parts, where the brightness of images from one part is Light and another is Dark.”
BackgroundCircuit defect detection based on AI deep learning
Wang, L. (2023) · Theoretical and Natural Science · doi:10.54254/2753-8818/12/20230455 · Cited by 2
A metal surface defect detection method based on improved YOLOv3
Wu, K., & Wang, Y. (2023) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc58219.2023.10326577 · Cited by 2
“This paper uses the public dataset NEU-DET [17] to validate the effectiveness of the proposed method.”
MethodRDDPA: Real-time Defect Detection via Pruning Algorithm on Steel Surface
Lu, K., Pan, X., Mi, C., Wang, W., Zhang, J., Chen, P., & Wang, B. (2023) · ISIJ International · doi:10.2355/isijinternational.isijint-2023-360 · Cited by 3
Super-resolution knowledge-distillation-based low-resolution steel defect images classification
Zhang, S., Pei, Z., & Ren, Z. (2024) · International Conference on Computer Graphics, Artificial Intelligence, and Data Processing (ICCAID) · doi:10.1117/12.3026364 · Cited by 2
“The dataset employed in the experiment is the NEU-CLS dataset [7], a specialized image dataset designed for surface defect detection, developed by scholars at Northeastern University (China).”
MethodMetal Surface Defect Detect Using Denoising Diffusion Probabilistic Model and Improved YOLOv8
Yang, H., & Qiuyu, W. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-97-1087-4_42 · Cited by 2
Surface Defect Detection of Remanufactured Products by Using the Improved Yolov5
Sun, W., Liu, Z., Wang, Q., & Zhu, B. (2024) · Lecture notes in mechanical engineering · doi:10.1007/978-3-031-52649-7_19 · Cited by 2
Identification and classification of surface defects for digital twin models of the workpiece
Qu, L., Huang, X., Zhang, D., & Zeng, C. (2024) · PLoS ONE · doi:10.1371/journal.pone.0302419 · Cited by 2
RetractedResearch on Internal Damage Identification of Wire Rope Based on Improved VGG Network
Li, P., & Tian, J. (2024) · Entropy · doi:10.3390/e26070531 · Cited by 2
“Among them, Yu, H. et al. [21] proposed a novel deep learning-based defect detection method for steel plates that used convolutional neural networks, multi-feature fusion networks (MFN) to extract the steel plate damage features, and area suggestion networks (MFN) combined with classifiers to…”
MethodMulti-Region Two-Stream Deep Architecture for Visual Power Monitoring Systems
Gan, J., Jiang, W., Zhao, T., Wu, P., Zhang, G., & Zhang, Z. (2021) · IEEE Access · doi:10.1109/access.2021.3061084 · Cited by 2
On the Performance of Deep Learning in the Full Edge and the Full Cloud Architectures
Benbarrad, T., Salhaoui, M., & Arioua, M. (2021) · International Conference on Networking, Information Systems & Security (NISS) · doi:10.1145/3454127.3457632 · Cited by 2
Application Study of YOLOv5 Algorithm on Automotive Wheel Surface Defect DetectionPreprint
Xia, X., Zhang, Z., & Liu, F. (2023) · Preprints.org · doi:10.20944/preprints202306.1069.v1 · Cited by 2
Wu, R., Zhang, Y., Lan, R., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5257434 · Cited by 2
ARDSwin-Unet: A Variant Swin Transformer for Fabric Defect Detection
Liu, C., Duan, S., & Pang, H. (2024) · doi:10.1109/isdh64927.2024.00009 · Cited by 3
“He et al.[4] proposed multi-level feature fusion network (MFN) to fuse more global context information.”
Ma, L., Shao, H., Xu, X., & Wu, X. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103910 · Cited by 3
Metadata
- Authors
- He, Y., Song, K., Meng, Q., & Yan, Y.
- Affiliations
- Northeastern University (CN)
- Loughborough University (GB)
- Venue
- IEEE Transactions on Instrumentation and Measurement
- Published
- 2020-04
- Volume
- 69
- Issue
- 4
- Pages
- 1493-1504
- ISSN
- 0018-9456 (ISSN-L)
- 1557-9662
- OpenAlex
- W2944303778
- Semantic Scholar
- 46d4a2b7ccf38b80b09574cf17544ff2297a8fbf
- Cited by
- 1,341
- References
- 53
- Citations by year
- 2026: 188 · 2025: 304 · 2024: 269 · 2023: 238 · 2022: 186 · 2021: 111 · 2020: 34
- FWCI
- 65.18
- Type
- journal article
- Language
- en
- Open access
- green
- figshare.com
- Licence
- Locations
- IEEE Transactions on Instrumentation and Measurement (publishedVersion)
- Figshare (submittedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (51805078, 51374063)
- National Basic Research Program of China (2017YFB0304200)
- Fundamental Research Funds for the Central Universities (N170304014, N150308001)
- China Scholarship Council (201806085007)
- Topics
- Physical Sciences › Engineering › Industrial and Manufacturing Engineering › Industrial Vision Systems and Defect Detection
- Physical Sciences › Engineering › Civil and Structural Engineering › Infrastructure Maintenance and Monitoring
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- multi-level feature fusion, hierarchical features, region proposal network, bounding box regression, NEU-DET dataset, real-time defect detection, industrial visual 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.
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.