The DOI matches its Crossref record; 43 of the 53 references it cites were found in a registry or an index.
An End-to-End Steel Surface Defect Detection Approach via Fusing Multiple Hierarchical Features
Open accessAbstract
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 501–600 of 1,338
An Improved Feature Enhancement CenterNet Model for Small Object Defect Detection on Metal Surfaces
Zhu, X., Wang, Q., Zhang, B., et al. (2024) · Advanced Theory and Simulations · doi:10.1002/adts.202301230 · Cited by 9
Lightweight-detection: The strip steel surface defect identification based on improved YOLOv5d
Lu, Y., Huang, Z.-C., Jiang, Y., Liu, G., Wang, J., & Ma, Q. (2024) · Materials Today Communications · doi:10.1016/j.mtcomm.2024.109814 · Cited by 21
An efficient steel defect detection model based on multi-scale information extraction
Xu, W., Zhang, Y., Jiang, X., et al. (2024) · Robotic Intelligence and Automation · doi:10.1108/ria-03-2024-0065 · Cited by 9
Sparse cross-transformer network for surface defect detection
Huang, X., Li, Y., Bao, Y., & Zhu, X. (2024) · Scientific Reports · doi:10.1038/s41598-024-75680-y · Cited by 17
“He et al. 17 used a CNN to generate feature maps at each stage and proposed a multilevel feature fusion network to combine these hierarchical features into a single feature for surface defect detection.”
MethodSurface defect detection of steel strip at low resolution based on SAC-YOLOv5
rui, C., Wu, Z., Liu, C., et al. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad9e25 · Cited by 9
“Firstly, we use five defect types from the strip steel surface defect dataset NEU-DET [32] published by Northeastern University (NEU) as the dataset1.”
Deep Learning for Automated Aircraft Surface Defect Detection
Bhatia, V., Arora, R., & Sidharth, S. (2024) · International Conference on Intelligent Computing and Emerging Communication Technologies (ICEC) · doi:10.1109/icec59683.2024.10837564 · Cited by 11
“Multiple empirical studies consistently report outstanding accuracy levels in the metal surface detection of defects through fusion of computer vision and deep learning methodologies [10],[11],[12],[13],[14].”
Surface Defect Detector Based on Deformable Convolution and Lightweight Multi‐Scale Attention
Xia, Z., Huang, Z., Gu, J., & Wang, W. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70003 · Cited by 10
Kuo, S., Lin, P., Huang, X.-Z., Huang, G.-Z., & Chen, L.-B. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3548214 · Cited by 6
“Previous studies on automated steel surfaces [7], [8], [9], [10] lacked reliable public datasets, and the reported data were insufficient (insufficient classification of defects).”
Fu, R., Huang, Z., Cao, M., Novák, D., Xie, C., & Huang, J. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111521 · Cited by 9
Liu, J., Zhang, Z., Alam, M. D. K., Cai, Q., Xia, C., & Tang, Y. (2025) · Digital Signal Processing · doi:10.1016/j.dsp.2025.105432 · Cited by 10
Hao, Z., Liu, B., & Xu, B. (2025) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-025-01251-4 · Cited by 17
“Traditional methods for metal surface defect detection have predominantly relied on manual visual inspection, which is costly and prone to errors due to human fatigue, often resulting in missed detections and delayed corrective actions [8].”
ACRM: Attention Cascade R-CNN with Mix-NMS for Metallic Surface Defect Detection
Fang, J., Tan, X., & Wang, Y. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9412424 · Cited by 13
“For example, the public database NEU-DET used in [19] is a defect classification dataset which is opened seven years ago.”
BackgroundMethodTang, C., Feng, X., Wen, H., Xu, Z., Shao, Y., Zhou, X., Huang, B., & Li, Y. (2021) · Applied Sciences · doi:10.3390/app112210508 · Cited by 10
“[10] used Focal Loss function to improve the classification loss of Region Proposal Networks module to solve the dataset category imbalance problem.”
MethodA high-effective multitask surface defect detection method based on CBAM and atrous convolution
Xie, X., Lei, X. U., Xinlei, L. I., Wang, B., & Wan, T. (2022) · Journal of Advanced Mechanical Design Systems and Manufacturing · doi:10.1299/jamdsm.2022jamdsm0063 · Cited by 12
“proposed an end-to-end steel surface defect detection method, which uses a baseline CNN to generate feature maps at each stage, and then the proposed multilevel feature fusion network (MFN) to fuse multiple hierarchical features (He et al., 2020).”
MethodLuo, Q., He, H., Liu, K., Yang, C., Sílven, O., & Liu, L. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3265761 · Cited by 10
“in ensuring the quality of steel products [1], [2], [3].”
BackgroundIndustrial Knee-jerk: In-Network Simultaneous Planning and Control on a TSN Switch
Wang, Z., Xu, J., Wang, X., Zhuge, X., He, X., & Yang, Z. (2023) · International Conference on Mobile Systems, Applications, and Services · doi:10.1145/3581791.3596836 · Cited by 11
“Compared to mechanical arms with task-specific and pre-programmed operating instructions on traditional lines, autonomous arms could make intelligent and agile decisions according to production or environmental information, such as defective product detection and grabbing[8, 9, 17], obstacle avoidance and emergency br…”
BackgroundZhu, X., Liu, J., Zhou, X., Qian, S., & Yu, J. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16352-3 · Cited by 11
“The database includes 1800 grayscale images: 300 samples each of six different kinds of typical surface defects [1, 16, 40].”
Glass Wool Defect Detection Using an Improved YOLOv5
Jin, Y., Lu, Y., Zhou, G., et al. (2023) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw59228.2023.00461 · Cited by 9
“Deep learning-based image processing models that can classify and locate defects more accurately have been applied in industrial production [5–7].”
MethodCascaded adaptive global localisation network for steel defect detection
Yu, J., Wang, Y., Li, Q., Li, H., Ma, M., & Liu, P. (2023) · International Journal of Production Research · doi:10.1080/00207543.2023.2281664 · Cited by 11
“The effectiveness of CAGLNet is demonstrated through a series of experiments on the NEU-DET dataset, achieving an average accuracy of 85.40% with a fast FPS of 10.06.”
MethodInfluentialChen, S., Zhou, F., Gao, G., Ge, X., & Wang, R. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.1727 · Cited by 11
Efficient Optical Measurement of Welding Studs With Normal Maps and Convolutional Neural Network
Liu, H., Yan, Y., Song, K., Chen, H., & Yu, H. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3024389 · Cited by 11
“Since the camera was not on the top of the stud, the existing methods like [1] and [2] cannot be applied.”
BackgroundMethodSelf-citationAI Landing for Sheet Metal-Based Drawer Box Defect Detection Using Deep Learning (ALDB-DL)
Sheu, R., Chen, L.-C., Pardeshi, M. S., Pai, K.-C., & Chen, C.-Y. (2021) · Processes · doi:10.3390/pr9050768 · Cited by 10
“• AI landing rule for hardware: Applying AI with AOI [39,40] for automated visual inspection of industrial products with the help of multiple contactless cameras is the objective of AI landing.”
Intelligent vision based wear forecasting on surfaces of machine tool elements
Schlagenhauf, T., & Burghardt, N. (2021) · SN Applied Sciences · doi:10.1007/s42452-021-04839-3 · Cited by 10
“…interesting approach which implements deep learning techniques for the detection of defects on the NEU dataset (Song and Yunhui 2019) can be found in (He et al. 2020) where they use convolutional neural networks to produce features which are then combined in multilevel feature fusion networks.”
BackgroundMethodZhou, C., Li, D., Wang, P., Sun, J., Huang, Y., & Li, W. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3094837 · Cited by 9
A Surface Defect Detection Method Via Fusing Multi-Level Features
Ren, M., Shen, R., & Gong, Y. (2022) · Journal of Computing and Information Science in Engineering · doi:10.1115/1.4053520 · Cited by 9
A novel approach for flip chip inspection based on improved SDELM and vibration signals
Su, L., Zhang, S., Ji, Y., Wang, G., Ming, X., Gu, J., Li, K., & PECHT, M. G. (2022) · Science China Technological Sciences · doi:10.1007/s11431-021-1964-0 · Cited by 9
“He et al. [18] combined multiple hierarchical features generated from a baseline CNN into one feature to generate regions of interest, which can be used to detect steel surface defects via a detector consisting of a classifier and a bounding box regressor.”
MethodA pixel-wise framework based on convolutional neural network for surface defect detection
Dong, G. (2022) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2022408 · Cited by 9
“In [31], an end-to-end detection framework was proposed, which integrated multi-level features to complete the detection of the strip steel surface defect.”
MethodChen, Y., Tang, Y., Hao, H., Zhou, J., Yuan, H., Zhang, Y., & Zhao, Y. (2023) · Electronics · doi:10.3390/electronics12071662 · Cited by 10
Li, Y., He, L., Zhang, M., Cheng, Z., Liu, W., & Wu, Z. (2023) · Electronics · doi:10.3390/electronics12112440 · Cited by 10
Efficient Conflict-Filtered Network for Defect Detection
Zheng, Y., Lyu, W., Wang, C., Guo, Q., Zhou, D., & Xu, W. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3293557 · Cited by 8
“It is worth noting that DDN [39], based on RES-Net-50 backbone, obtains the highest score, 82.1% on mAP.”
BackgroundInfluentialLv, Z., Li, Y., Qian, S., Wu, L., & Yang, Y. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02317-8 · Cited by 9
Machine Vision-Based Lightweight Multiscale Automatic Defect Segmentation Network for MLCC
He, J., Cao, X., Takamasu, K., & Chen, M. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3415777 · Cited by 8
“In the field of flat steel, He et al. [8] proposed a multilevel feature fusion network (MFN) that achieved high detection accuracy and fast detection speed.”
BackgroundYOLOv5-ACCOF Steel Surface Defect Detection Algorithm
Hai-tao, X., & Song, J. (2024) · IEEE Access · doi:10.1109/access.2024.3486110 · Cited by 10
“This is an open and large-scale dataset for surface defect detection, published by the Institute of Song Kechen’s team at Northeastern University [19].”
MethodA computer vision system for recognition and defect detection for reusable containers
Wahyudi, V., Ziegler, C. C., Frieß, M., Schramm, S., Lang, C., Eberhardt, L., Freund, F., Dobhan, A., & Storath, M. (2025) · Machine Vision and Applications · doi:10.1007/s00138-024-01636-x · Cited by 12
“He et al. [20] implemented an end-to-end steel surface defect detection approach using a fusion of multiple hierarchical features for potential real-time detection.”
Surface Defect Detection of Continuous Casting Slabs Based on Deep Learning
Zhihua, M., Zeng, K., Chen, B., Xiao, P., & Zhu, L. (2025) · ISIJ International · doi:10.2355/isijinternational.isijint-2024-198 · Cited by 7
An efficient lightweight detection model for steel surface defects with dynamic deformable head
Li, C., Wen, Z., Huang, H., Mo, H., Zhou, S., & Zhu, Z. (2025) · Engineering Research Express · doi:10.1088/2631-8695/adbab4 · Cited by 8
Adaptive shape imitation and selective semantic guidance for industrial surface defect detection
Liang, X., Li, Y. Y., Wang, X., Liu, P., Shen, Y., & Guo, J. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127334 · Cited by 12
Hint-DETR: A Transfer Learning Model Based on DETR for Few-Shot Defect Detection
Liu, Y., Zhang, G., & Li, X. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3568997 · Cited by 23
“Toverify the generality and e ffi ciency of our method, we constructed two few-shot defect datasets (few-shot NEU and few-shot DAGM) using two di ff erent public defect datasets (NEU [8] and DAGM [9]).”
Renfei, C., Li, Z., & Zeyang, Z. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.111150 · Cited by 10
A lightweight steel surface defect detection network based on YOLOv9
Zheng, T., Yu, L. H., Shi, Y., & Niu, F. (2025) · AIP Advances · doi:10.1063/5.0273824 · Cited by 8
Steel surface defect detection based on PSO-Gabor and an improved faster RCNN
Song, F., Bao, K., Deng, M., Xia, X., Sun, L., Zhou, J. H., Liu, L., & Jiang, L. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2512553 · Cited by 9
“During production and processing, due to external forces, equipment fatigue, low-quality steel and other factors, the thin strip steel surface may exhibit edge cracks, inclusions, holes, scratches and other various defects [1–5].”
Detection of Surface Defects in Steel Based on Dual-Backbone Network: MBDNet-Attention-YOLO
Wang, X., Ma, S., Wu, S., Li, Z., Cao, J., & Xu, P. (2025) · Sensors · doi:10.3390/s25154817 · Cited by 11
“Additionally, to strengthen feature fusion capabilities, we incorporate the Dynamic Align Fusion module, which aligns and merges feature maps across different scales, thereby enhancing the model’s multi-scale perception [30].”
Orientation-aware detection system for real-time monitoring of cracks in steel structures
Xiao, H., Yang, B., Yu, Y., Han, J., Zhen, L., & Lai, S. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.129932 · Cited by 9
EL-DETR: a lightweight steel surface defect detection model
Su, F., & Peng, M. (2025) · Measurement science and technology · doi:10.1088/1361-6501/ae17e0 · Cited by 9
“Two steel surface defect datasets, NEU-DET [40] and GC10-DET [41], are employed to evaluate the performance of the EL-DETR model.”
Attention-guided hybrid learning for accurate defect classification in manufacturing environments
Kasem, M. S., Mahmoud, M., Senussi, M. F., Abdalla, M. I., & Kang, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-31654-2 · Cited by 14
Touch: A New Paradigm Based on Machine Tactile Sensation for Surface Microdefect Detection
Xi, Z., Li, X., Gao, L., & Gao, Y. (2025) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2025.3638047 · Cited by 8
“In an ideal scenario, a pit defect with a diameter of 0.09 mm captured by a microlens camera would represent only 36 pixels, accounting for about 1% of the entire image [19].”
InfluentialSemi-Supervised Training for Positioning of Welding Seams
Zhang, W., & Lang, J. (2021) · Sensors · doi:10.3390/s21217309 · Cited by 8
Akhyar, F., Lin, C., & Kathiresan, G. S. (2021) · International Conference on Multimedia Retrieval · doi:10.1145/3460426.3463666 · Cited by 8
“Existing automatic steel surface defect detection systems employ a deep learning approach in order to extract detailed information from steel defect images [1; 3; 4].”
MethodATNet: A Defect Detection Framework for X-ray Images of DIP Chip Lead Bonding
Huang, R., Zhan, D., Yang, X., Zhou, B., Tang, L., Cai, N., Wang, H., & Qiu, B. (2023) · Micromachines · doi:10.3390/mi14071375 · Cited by 8
“The NEU-DET dataset has more complex defect types and is more difficult to detect.”
InfluentialYang, L., Huang, X., Ren, Y., et al. (2023) · Engineering Computations · doi:10.1108/ec-12-2022-0720 · Cited by 8
Wang, J., Zhang, W., Fu, J., Song, K., Meng, Q., Zhu, L., & Jin, Y. (2023) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2023.3311171 · Cited by 10
Self-citationDeep Feature Contrasting for Industrial Image Anomaly Segmentation
Wan, Q., Cao, Y., Gao, L., Li, X., & Gao, Y. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3348901 · Cited by 12
“I NDUSTRIAL image anomaly segmentation, which is used to segment anomalous regions, such as scratches or color defects in images [1], [2], [3], [4], is common in industrial scenarios [5], [6].”
BackgroundWafer Map Defect Patterns Semi-Supervised Classification Using Latent Vector Representation
Wei, Q., Zhao, W. G., Zheng, X., & Zeng, Z. (2023) · IEEE Conference on Cybernetics and Intelligent Systems · doi:10.1109/cis-ram55796.2023.10370763 · Cited by 12
“Extensive experiments on the NEU-CLS defect dataset [29] demonstrate that even with limited original samples, this method is highly effective for defect classification.”
MethodA novel method for necking detection and measurement in automotive sheet metal components
Li, S., Wang, H., Zhang, Y., Zhou, Y., & Liu, C. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad1fce · Cited by 8
“On the other hand, image-based visual inspection techniques [2–4] heavily rely on the setup of the detection environment, with the reflectivity of metal parts significantly reducing the robustness of image-based meth-ods.”
Zeng, Q., Wei, D., Zhang, X. J., et al. (2023) · International Conference on New Trends in Computational Intelligence (NTCI) · doi:10.1109/ntci60157.2023.10403686 · Cited by 8
“…performance of MFAM-Net, we compare it with several state-of-the-art detection methods, including Faster-RCNN [10], YOLOv3 [11], YOLOv5s [12], YOLOv7 [13], YOLOv8 [14], DCAM-Net [2], and DDN [15]. mAP on the GC10-DET dataset can reach 67.7%, both of which are better than other detection algorithms.”
MethodInfluentialA High-Quality Sample Generation Method for Improving Steel Surface Defect Inspection
He, Y., Li, S., Wen, X., & Xu, J. (2024) · Sensors · doi:10.3390/s24082642 · Cited by 11
“He et al. [20] proposed an end-to-end defect inspection method based on the pre-trained Resnet models.”
MethodSelf-citationYOLOv8n-GAM: an improved surface defect detection network for hot-rolled strip steel
Xu, H., Xiao, X., Zhao, Z., & Wang, Z. (2024) · Engineering Research Express · doi:10.1088/2631-8695/ad5417 · Cited by 9
Patch Matching for Few-Shot Industrial Defect Detection
Chen, R., Yu, G., Qin, Z., Song, K., Tu, J., Jiang, X., Liang, D., & Peng, C. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3413170 · Cited by 11
“sensor-based systems, are used to automate and improve the accuracy of defect detection in industries such as manufacturing [1], [2], [3], [4], [5], electronics [6], automotive [7], and food production.”
MethodSelf-citationResearch on the Detection of Steel Plate Defects Based on SimAM and Twin-NMF Transfer
Zou, Y., Zhang, G., & Fan, Y. (2024) · Mathematics · doi:10.3390/math12172782 · Cited by 8
Semi-supervised adaptive network for commutator defect detection with limited labels
Wang, Z., Li, W., Wang, M., Liu, B., Niu, T., & Li, B. (2024) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2024.09.016 · Cited by 8
ADFormer: Generalizable Few-Shot Anomaly Detection With Dual CNN-Transformer Architecture
Zhu, B., Gu, Z., Zhu, G., Chen, Y., Tang, M., & Wang, J. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3522624 · Cited by 17
An ESG-ConvNeXt network for steel surface defect classification based on hybrid attention mechanism
Zhang, N., Liu, Z., Zhang, E., Chen, Y., & Yue, J. (2025) · Scientific Reports · doi:10.1038/s41598-025-88958-6 · Cited by 13
Lightweight detection algorithm for fine-grained surface defects of aerospace seal rings
Liu, H., He, B., He, Y. Q., & Tao, X. (2021) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-202614 · Cited by 8
“More specifically, it can be divided into methods based on shallow machine learning and methods based on deep learning [18, 19].”
Self-citationWavelet Subband-Based Tensor for Smartphone Physical Button Inspection
Giap, B. D., Le, N. T., Wang, J.-W., & Wang, C. (2021) · IEEE Access · doi:10.1109/access.2021.3099965 · Cited by 8
S2D2Net: An Improved Approach For Robust Steel Surface Defects Diagnosis With Small Sample Learning
Nath, V., & Chattopadhyay, C. (2021) · Proceedings - International Conference on Image Processing · doi:10.1109/icip42928.2021.9506405 · Cited by 9
YOT-Net: YOLOv3 Combined Triplet Loss Network for Copper Elbow Surface Defect Detection
Xian, Y., Liu, G., Fan, J., Yu, Y., & Wang, Z. (2021) · Sensors · doi:10.3390/s21217260 · Cited by 8
“[24] introduces a refined Fast R-CNN model and make a test on a defect dataset NEU-DET.”
MethodMEDEP: Maintenance Event Detection for Multivariate Time Series Based on the PELT Approach
Gashi, M., Gursch, H., Hinterbichler, H., Pichler, S., Lindstaedt, S., & Thalmann, S. (2022) · Sensors · doi:10.3390/s22082837 · Cited by 8
“Previous studies have focused mainly on improving labeling in the context of defect detection [9,10] and failure detection [11,12].”
BackgroundAn Image-Based Data-Driven Model for Texture Inspection of Ground Workpieces
Wang, Y.-H., Lai, J.-Y., Lo, Y.-C., Shih, C.-H., & Lin, P. (2022) · Sensors · doi:10.3390/s22145192 · Cited by 8
Surface Quality Automatic Inspection for Pharmaceutical Capsules Using Deep Learning
Dong, H., Yang, J., Wang, J., & Li, S. (2022) · Journal of Sensors · doi:10.1155/2022/4820618 · Cited by 10
“Deep learning-based methods have been proved to be a more efficient solution than traditional image processing or machine learning methods [9, 10].”
MethodA Novel Defect Inspection System Using Convolutional Neural Network for MEMS Pressure Sensors
Deng, M., Zhang, Q., Zhang, K., Li, H., Zhang, Y., & Cao, W. (2022) · Journal of Imaging · doi:10.3390/jimaging8100268 · Cited by 11
“Secondly, CNN is used for feedback control of the MEMS pressure-sensor chip package so as to obtain a more intelligent system.”
The Defects Detection in Steel Coil End Face Based on SCED-Net
Li, Y., Lin, S., Liu, C., & Kong, Q. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892172 · Cited by 8
“3% on the strip steel surface defect data set, and the effect was significant [9].”
BackgroundYOLOv5s‐GC‐Based Surface Defect Detection Method of Strip Steel
Li, X., Yang, R., & Zhou, H. (2024) · steel research international · doi:10.1002/srin.202300421 · Cited by 9
A lightweight real-time detection transformer model for surface defect detection systems
Hou, Y., & Zhang, X.-D. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122685 · Cited by 9
Real-time batch inspection system for surface defects on circular optical filters
Zheng, J., Yu, W., Ding, Z., et al. (2022) · Applied Optics · doi:10.1364/ao.474272 · Cited by 7
Continual learning for surface defect segmentation by subnetwork creation and selection
Dekhovich, A., & Bessa, M. A. (2024) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02393-4 · Cited by 11
“In general, the task-prediction problem is quite challenging in continual learning (Kim et al., 2020) and can be seen as an out-of-distribution (OOD) detection problem (Kim et al., 2022).”
InfluentialMa, X., Deng, X., Kuang, H., & Liu, X. (2024) · IEEE Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC) · doi:10.1109/imcec59810.2024.10575022 · Cited by 7
“The dataset used for the surface defect aspect is Northeast-ern University’s surface defect dataset (NEU-DET) [9] [10] [11], which collected a total of six typical surface defects of hot-rolled steel strip, namely Rolled-in Scale, Patches, Crazing, Pitted Surface, Inclusion, and Sratches.”
MethodDefect recognition network for optical fiber cables based on feature information compensation
Zheng, S., Ni, S.-S., Yan, P., et al. (2025) · Applied Soft Computing · doi:10.1016/j.asoc.2025.113139 · Cited by 7
A TBD-YOLO-Based Surface Defect Detection Method for Hot Rolled Steel Strips
Kong, S., Kong, Y., Chi, X., Feng, X., & Ma, L. (2025) · Russian Journal of Nondestructive Testing · doi:10.1134/s1061830924603192 · Cited by 9
Li, X., Xu, Y., Ji, Z., Zhang, Y., Chen, M., Wang, S., & Zhao, Q. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127949 · Cited by 7
A novel context-adaptive multi-scale defect detection method for object surface defects
Zhang, H., Liu, J., Pan, D., Jiang, Z., & Dong, J. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.130927 · Cited by 12
Lei, J., Wang, J., Li, Y., Zhang, M., Zhao, R., & Sun, H. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/aded2b · Cited by 9
“The experiments utilized the public NEU-DET [26] steel strip surface defect dataset, which includes six common types of To validate the improved performance of the proposed MLS-YOLOV11 model, four key metrics were selected as evaluation criteria: mAP, model parameter count (Parameters),…”
Shi, W., Dai, J., Li, C., & Niu, N. (2025) · Mathematics · doi:10.3390/math13172769 · Cited by 7
Zhang, W. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.112537 · Cited by 10
YOLO-KD: An Improved YOLOv8 Algorithm for Strip Steel Surface Defect Detection
Liu, L., Wang, J., & Liu, J. (2025) · IEEE Access · doi:10.1109/access.2025.3617474 · Cited by 8
“The CIoU loss function adopted by default in YOLOv8n introduces center point distance and aspect ratio penalty terms [29] based on IoU, achieving more comprehensive geometric constraints, with its formula expressed as : where IoU represents the intersection over union, ρ 2 ( b , b gt ) denotes the…”
Joint Architecture Design and Workload Partitioning for DNN Inference on Industrial IoT Clusters
Fang, W. W., Xu, W., Yu, C., & Xiong, N. N. (2022) · ACM Transactions on Internet Technology · doi:10.1145/3551638 · Cited by 11
“(3) We implement EdgeDI and evaluate its performance over the real industrial dataset NEU-CLS [11] on a cluster of Raspberry Pi’s.”
MethodResearch and prospects of virtual reality systems applying exoskeleton technology
Qi, W., Sun, S., Niu, T., & Zhao, D. (2022) · Universal Access in the Information Society · doi:10.1007/s10209-022-00929-0 · Cited by 7
“If the intersection region is detected, fine collision detection between objects is performed, and if the enclosed objects do not intersect, collision detection between objects ends [97].”
Accurate Vision-Based PCB Positioning Using Cosine-Convolutional Neural Networks
Solórzano, C. A. P., & Tsai, D. (2023) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2023.3263887 · Cited by 8
“Machine Vision methods for defect inspection have been applied for Printed Circuit Board (PCB) industry ( [1], [2]) and steels ( [3], [4]).”
MethodNath, V., Chattopadhyay, C., & Desai, K. A. (2023) · Manufacturing Letters · doi:10.1016/j.mfglet.2023.08.036 · Cited by 7
A Lightweight YOLOv7 Algorithm for Steel Surface Defect Detection
Zhou, Y., & Piao, J.-C. (2023) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai59366.2023.10331937 · Cited by 7
“Therefore, it is very important to detect defective steel surface in time and ensure the safety of industry [1].”
BackgroundZhao, H. M., Liu, J., Zhang, H., et al. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3355984 · Cited by 7
“In order to validate the effectiveness of the method, we performed validation on two publicly available industrial datasets, including the NEU dataset [37] and GC10-DET dataset [38].”
Learning-Based Approach for Automated Surface Inspection with Industrial Tomography Imaging
Saied, M., Ali, R., Francis, C., Radilla, G., & Noun, Z. (2024) · Journal of Nondestructive Evaluation Diagnostics and Prognostics of Engineering Systems · doi:10.1115/1.4065428 · Cited by 7
Steel Surface Defect Detection Based on Improved YOLOv7
Li, M., Wei, L., & Zheng, B. (2024) · International Conference on Computer, Control and Robotics (ICCCR) · doi:10.1109/icccr61138.2024.10585576 · Cited by 7
“He et al [5] proposed a CNN model-based approach using a Multilevel Feature Fusion Network (MFN) to combine multiple hierarchical features into a single feature that can contain more details of the location of the defects.”
MethodZhao, J., Hu, W., Li, D., Guo, S., Luo, B., Bao, T., Lv, Y., & Jia, H. (2024) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-024-09329-3 · Cited by 7
“To validate the universality of the model, we conducted comparative experiments on the open-source NEU surface defect database [57].”
Efficient minor defects detection on steel surface via res-attention and position encoding
Wu, C., & He, T. (2024) · The Visual Computer · doi:10.1007/s00371-024-03583-0 · Cited by 10
“…validity, we performed experiments on two distinct datasets: the NEU-DET dataset for steel surface defects, hosted by Northeastern University [35], and the GC10-DET dataset, provided by Lv Xiaoming et al. [36] The experiments were executed using a PyTorch-based network on an NVIDIA A800 GPU.”
Wang, X., Wang, X., Zhou, Z., & Song, Y. (2024) · Applied Intelligence · doi:10.1007/s10489-024-05768-5 · Cited by 11
“ResNet has several advantages [32].”
Fang, X., Liu, C., Yang, H., Zheng, X.-P., & Chen, X. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3449958 · Cited by 8
“…networks that have been successfully implemented across various fields such as fault diagnosis [30], [31], [32], [33], materials science [34], [35], [36], [37], and health monitoring [38], [39], [40], these networks typically require a combination of data-driven approaches and a prior knowledge.”
BackgroundSethy, P. K., Korada, L., Behera, S. K., Shirole, A., Amat, R., & Nanthaamornphong, A. (2024) · Systems and Soft Computing · doi:10.1016/j.sasc.2024.200170 · Cited by 11
FPDNet: A fast and high-precision detection network for hot-rolled strip surface defects
Jiang, F., Lü, K. L., Wang, W., Pan, X., Zhang, J., Chen, P., & Wang, B. (2025) · Measurement · doi:10.1016/j.measurement.2025.117309 · Cited by 11
CSAMamba-YOLOv8: a method for detecting defects on steel surfaces
Zhao, Z., & Liu, X. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04044-4 · Cited by 7
“This study uses the NEU-DET steel surface defect dataset created by Northeastern University [26].”
Xu, H., Zhang, Z., Ye, H., Song, J., & Chen, Y. (2025) · Electronics · doi:10.3390/electronics14102029 · Cited by 10
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.