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 1,101–1,200 of 1,338
Steel Surface Defect Recognition Based on Evolutionary Network Architecture Search
Lu, T., & Wu, G. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10864969
Local Fine-Gained Weighted Distillation for Industrial Defect Detection
Du, W., & Ding, Z.-J. (2024) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai65059.2024.10893845
Robust Adversarial Training for Industrial Defect Classification with Long-Tailed Data
Xu, S., Lyu, J., Man, D., Xiong, H., Liu, T., & Yang, W. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10887770
“To validate the effectiveness of the proposed method, we evaluate it in CIFAR10 [22] and NEU-CLS [23]– [25].”
A New Energy Battery Lightweight Network Based on YOLOv8
Li, D., & Zhang, J. (2024) · doi:10.1109/icftic64248.2024.10912992
“As a core component of new energy vehicles, surface defects [2] of new energy batteries may have a serious impact on the safety and performance of vehicles.”
Task-guided dynamic feature selection and loss optimization for multi-scale defect detection
Liu, P., Xia, G., Fang, L., et al. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104772
Xiao, H., Liu, G., Hang, S., Jin, Z., Liang, T., & Li, X. (2024) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd64214.2024.10920564 · Cited by 1
“For example, edge detection techniques like Sobel and Canny operators are used to identify edges in images [17].”
SGNet: A Multi-Scale Method for Steel Surface Defect Detection
Liu, S., Liu, X., Man, J., et al. (2024) · IEEE Smart World Congress (SWC) · doi:10.1109/swc62898.2024.00215
“The NEU-DET dataset [17], developed by the team of Ke Chen Song at Northeastern University, is used for evaluating surface defect detection on hot-rolled steel plates.”
CP-YOLO: An Algorithm for Cigarette Pack Defects Detection Based on CCD Images
Dong, P. M., Feng, W., Wang, R., et al. (2025) · IEEE Access · doi:10.1109/access.2025.3554989
“The proposed method was extensively tested on the CigPack defect dataset and validated on the Northeastern University steel surface defect dataset (NEU-DET) [43] and Peking University board defect dataset (PKU-market-PCB) [44] to verify its effectiveness and robustness.”
Improved Mask R-CNN for defect detection in aluminum alloy rims
Yeh, M.-T., Wu, E.-T., & Lu, Y.-T. (2026) · Soft Computing · doi:10.1007/s00500-026-11392-x
“The second is the two-stage network based on region proposal, which includes R-CNN, Fast R-CNN, Faster R-CNN, and Mask R-CNN (Girshick et al. 2014; Girshick 2015; Ren et al. 2017; He et al. 2020a, b).”
InfluentialDetecting Misalignments of Drilled Holes Using Machine Vision
Ambaye, G. A., Boldsaikhan, E., & Krishnan, K. (2025) · Green energy and technology · doi:10.1007/978-3-031-77339-6_2
Gao, W., & Zhou, Y. (2024) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc62609.2024.10942311 · Cited by 2
“In 2021, Kou et al. [15] introduced an improved YOLOv3 [16] for defect detection, which improved detection accuracy and computational efficiency through specially designed dense convolutional blocks, reaching a mean Average Precision (mAP) of 72.2% on the NEU-DET dataset [17].”
InfluentialTdef-Yolo: A Powerful Surface Defect DetectorPreprint
Li, J., Li, H., Feng, Y., Qian, S., & Hu, X. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5205180
Lightweight Strip Steel Surface Defect Detection Algorithm Based on YOLOv8s
Feng, Z., Sun, S., Shi, N., et al. (2024) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml63543.2024.10957902
“2, among the two-stage object detectors, Faster R-CNN[8] has an excessive number of parameters and computational complexity, making it unsuitable for practical applications in industrial scenarios.”
Tatar, H., & Küçük, M. F. (2025) · Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi · doi:10.28948/ngumuh.1641247
LAGNet: A Location-Aware Guidance Network for Weak and Strip Defect Detection
Cui, L., Jiao, H., Liu, T., Niu, C., Ma, M., Jiang, X., & Xu, M. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-5809-1_19
Energy-Friendly Federated Neural Architecture Search for Industrial Cyber-Physical Systems
Wang, X., Zhao, Y., Qiu, C., Gao, F., Zhao, Z., Yao, H., & Li, X. (2025) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2025.3574599 · Cited by 4
“Surface defect detection in ICPS involves identifying and localizing defects on product surfaces using machine vision techniques [16], [17].”
Real time Application of Image Recognition Technology in Defect Detection of Mechanical Products
Wang, F., Hu, J., & Zhang, S. (2025) · ZKG International · doi:10.63386/618764
DI-Net: Dynamic Interconnected Network for Accurate Industrial Defect Detection
Lin, X., Xuan, Y., Hao, L., et al. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033618
Cross-Scale Collaborative Transformer for Flexible Printed Circuit Defect DetectionPreprint
Zuo, T., Chen, G., Cao, H., Liao, X., & pu, X. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5342407
Tan, L., Liao, X., Zheng, A., et al. (2025) · doi:10.1109/cisce65916.2025.11065589
“In this study, we use the NEU-DET [7] dataset to evaluate the performance of the proposed method.”
Xu, X., Li, F., Yang, C., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5352144
Steel Surface Defect Detection Algorithm Based on YOLOv8n-SLM
Fu, Y., Gu, Z., Hao, F., et al. (2025) · International Conference on Neural Networks, Information and Communication Engineering (NNICE) · doi:10.1109/nnice64954.2025.11064449
“The dataset used in this study is the publicly available NEU-DET steel surface defect dataset provided by Northeastern University[ [13] ].”
Li, Y., Lu, H., & Wan, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9961-2_13
Efficient Surface Defect Detection via Multi-scale Features and Lightweight Attention
Huang, X., Yu, H., Liang, A., Gao, Y., & Si, P. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9856-1_34
Using an Improved Lightweight YOLOv11 Model for Fuzzy Image Object Detection
Cheng, Y., Gong, L., Ning, Z., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9911-7_23
Yang, J., Luo, L., Chen, M., Su, S., & Yan, J. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2543974 · Cited by 3
“He et al. [22] proposed a steel surface defect detection approach, but its dependency on specific datasets limits its generalisation capability.”
Li, Y., Yin, M., Guo, J., Wu, X., Li, L., Zhang, L., & Bei, S. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adfafb · Cited by 1
“To further evaluate the adaptability and robustness of SFPE-NET across different datasets, we performed additional validation on the NEU-DET [50] dataset, as illustrated in figure 13.”
SCSP-YOLO: a method for detecting surface defects on strip steel
Jiang, S., Xu, Y., Lu, H., & Wang, S. (2025) · Pattern Analysis and Applications · doi:10.1007/s10044-025-01530-w
Pan, H., Yu-jin, Z., Song, J., & Xu, H. (2025) · Electronics · doi:10.3390/electronics14163302
A Dislocated 2*2 Convolution for Extracting Longitudinal and Transverse Features
Chen, S., Xiang, X., Zhang, J., et al. (2024) · International Conference on Mechatronics and Computer Technology Engineering (MCTE) · doi:10.1109/mcte62870.2024.11117828
“We used the neu-det dataset of Northeastern University for training and testing in object detection[9], which is a defect detection dataset with six defects: rolled-in-scale(Rs), patches(Pa), crazing(Cr), pitted-surface(Ps), inclusion(In), and scratches(Sc), with a total of 1800 images, Some of…”
A Wavelet Convolution-Based Improved YOLOv11 Model for Metallic Surface Defect Detection
Li, J., Xu, H., Xie, Z., Wang, S., Wei, S., & Qian, L. (2025) · International Symposium on Big Data and Applied Statistics (ISBDAS) · doi:10.1109/isbdas64762.2025.11117100
“The NEU-DET [3] and GC10-DET [4] datasets are large-scale datasets specifically curated for metallic surface defect detection.”
Improved Metal Surface Defect Detection Model of YOLOv5 Combining CBAM and BiFPN
Zhang, Y., Chang, Y., Yu, H., Wang, Y., Bai, K., Yang, Y., Li, H., Xiao, W., & Wu, C. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-1337-6_34
Zhao, Y., Xia, Z., Gu, J., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5433219
ICSnet: An efficient object detection network for industrial complex scenes
Li, D.-J., Bai, F., Li, S.-L., et al. (2026) · Measurement · doi:10.1016/j.measurement.2025.118836 · Cited by 1
Feature-Level and Object-Level Scale Enhancement for Few-Shot Defect Detection
Luo, S., Liu, B., & Chen, H. (2025) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea65512.2025.11149225
“We conducted experiments using two widely studied surface defect detection dataset NEU-DET[19] and PKU-Market-Phone[20].”
Defect Detection in Patterned Wafers Using Dynamic Local Adaptive Sensitivity Adjustment
Cai, X., Chen, Y., Yao, Z., & Wang, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3604128
“Many deep learning-based defect inspection methods have been tested in di ff erent industrial areas [33], [34], [35], [36], [37], [38].”
A Real-Time Defect Detection Algorithm for Photovoltaic Glass with High AccuracyPreprint
Fan, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5494104
Enhanced Industrial Defect Detection with Multi-scale KAN Convolution and GSHilo Attention Mechanism
Zhang, X., & Wang, R. (2025) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-025-10654-4
Sun, K., Sun, M., Zhou, H., et al. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07920-5
“The performance of the proposed LMFL-YOLO model is thoroughly evaluated on the NEU-DET [34] dataset.”
Wang, Z., Bai, S., & Pan, W. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3617394 · Cited by 1
“To evaluate the e ff ectiveness of the proposed method, we conducted experiments on the MSD dataset [40], the Magnetic Tile Surface Defect dataset [41], and the MVTec-FS dataset [43].”
Enhancing defect detection with diffusion model
Song, Z., Yu, X., Liang, Y., et al. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae10d3
“…[47] ResNet-34 70.0% Faster R-CNN [47] ResNet-50 76.6% DEA-RetinaNet [63] ResNet-50 79.1% CABF-FCOS [64] ResNet-50 76.7% DDN [65] VGG-16 76.3% DDN [65] ResNet-50 82.1% YOLOv5s [43] Modified CSPDarknet v6 76.6% YOLOv5m [43] Modified CSPDarknet v6 77.2% YOLOv5l [43] Modified CSPDarknet v6 77.3%…”
InfluentialMa, Z., Liu, M.-Q., Dong, S.-L., et al. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3619246
Algorithm for Detecting Defects on Steel Surfaces Based on DMO-YOLO
Li, G., & Zhu, F. (2025) · International Joint Conference on Information and Communication Engineering (JCICE) · doi:10.1109/jcice66205.2025.11182070
LDD-CAP: lightweight defect detection algorithms for class a priori
Shi, D., Zhang, T., & Duan, Y. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07936-x · Cited by 1
“(1) The Northeastern University Surface Defect (NEU-seg) [32] is a hot-rolled strip steel defect detection dataset, which includes three types of defects: inclusion (In), patch (Pa), and scratches (Sc).”
FS-SSDD: A Few-shot Steel Surface Defect Detection Network
Liu, G., Chu, M., Gong, R., et al. (2025) · Signal Image and Video Processing · doi:10.1007/s11760-025-04877-z
“All experiments in this work are conducted on the NEU-DET [29] and GC10-DET [30] datasets for training and validation purposes.”
An Energy Efficient Model Based on the Feature Pseudo-embedding
Chen, L., & Pastor-López, I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-08462-0_8
Communication Efficient Fuzzy Clustered Graph Federated Learning
Zhang, W., Wang, Z. G., Zhao, H., et al. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-03215-7_5
Wang, R., Pang, Q., Hu, Z., et al. (2025) · Journal of Material Cycles and Waste Management · doi:10.1007/s10163-025-02406-1
“In contrast, object detection technologies based on deep learning have been introduced to address these challenges, effectively extracting intricate features and enhancing recognition accuracy [16–18].”
Relational Enhancement Network for Industrial Defect Detection
Linghu, H., Liu, M., & Zhang, S. (2025) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme59968.2025.11209168
“NEU-DET [29] is a public dataset that contains six types of typical surface defects found on hot-rolled steel strips: crazing (Cr), inclusion (In), patches (Pa), pitted surface (PS), rolled-in scale (RS), and scratches (Sc).”
Self-supervised Surface Defect Inspection Method via Alignment of Content and Style
Ye, G., Zhang, Z., Ye, B., & Lai, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3393-0_15
Class-Incremental Learning for Surface Defect Detection
Lei, B., Huang, J., Jiang, W., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3393-0_46
Liao, J., Liu, M., Jiang, L., & Li, K. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae1aa8
DPFD-DETR: Directional Prior Guided Frequency Decomposition with Axial-Spatial Context Alignment
Zhang, C., Wu, W., Niu, H., Bao, S., & Wu, N. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4378-6_7
HSDNet: Hybrid Super-Resolution Assisted Detection Network for Surface Defect Detection
Lin, X., Yang, X., Sun, Y., et al. (2025) · doi:10.1109/ijcnn64981.2025.11227791
“A. Dataset and Metrics 1) Datasets Description : The proposed EUPSN network is experimentally verified on two datasets, NEU-DET [27] and PCB, in which the texture of the defect is relatively similar to the background, and most of them are small targets, which poses certain challenges.”
PD-YOLOv11s: An End-to-End Paper Surface Detection for Specific Visible Angle Defect
Li, S., Zhu, H., Zhong, X., Jiu, M., Guo, W. J., Chen, Y., & Xu, M. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228291
“As for industrial datasets, the NEU-DET dataset [9] from Northeastern University is designed specifically for surface defect detection in steel rolling, containing six types of defects, including scratches, dents, and spots, with 300 images per type of defect.”
Yang, X., Lin, X., Wang, Y., Sun, Y., & Qi, L. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228273
DMP-DETR: Dilation Multi-Scale and Partial Channel Gated Fusion Attention For Steel Defect Detection
Zhao, S., Wu, C., & Yu, F. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229140
“We employ two publicly available datasets, NEU-DET [21] and GC10-DET [22], in our experimental setup to evaluate and compare the efficacy of our proposed methodologies.”
A High-Quality Sample Generation Method via Cross-Scale Diffusion for Steel Defect Detection
Zhu, Z., & Wang, F. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228398
“Previous works usually use pre-trained models, such as ResNet and VGG network, to perform defect detection tasks on steel * denotes corresponding author. surface [5] [6].”
Xiong, T., Gu, J., Yang, Q., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5763951
Generating realistic 3D surface defects for training AI-Based industrial inspection systems
Toribio, S. R. H., Roos-Hoefgeest, M., Garcia, D., Álvarez, I., & González, R. C. (2025) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-025-16851-7 · Cited by 1
RDT-YOLO: An Improved Lightweight Model for Fish Maw Authenticity Detection
Xie, C., Liu, M., Zhang, W., Zhang, Y., Hassan, S. G., Guo, W., Liu, T., Liu, S., & Gao, X. (2025) · Electronics · doi:10.3390/electronics14234588
EFE-YOLO:A YOLO11n-based Efficient Feature Enhanced Framework for Steel Surface Defect DetectionPreprint
Chen, Y., Liao, Y., Chen, J., & Zhang, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5801545
IoU-Aware Clustering for Anchor Configuration Determination in Efficient Defect Detection
Zhao, Y., Ma, H., Zou, W., Liu, Z., Su, H., & Liu, S. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246867
“[16] proposed a two-stage steel defect detector by integrating multiple hierarchical feature maps into a single-level one for subsequent proposal prediction.”
A steel flaw detection method: lightweight edge information extraction network
You, H., & Chen, J. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/ae2531 · Cited by 2
“Consequently, reliable detection of surface defects is imperative for ensuring structural safety in both construction and manufacturing and for facilitating effective long-term monitoring [1].”
Huang, X., & Peilin, L. (2025) · Expert Systems · doi:10.1111/exsy.70177
Zeyi, 张. Z., Zhiyong, 陶. T., Lin, S., & Minglang, 李. L. (2025) · Laser & Optoelectronics Progress · doi:10.3788/lop250894
Qu, G., Liao, J., Liu, K., Xu, B., & Qian, Y. (2025) · Machines · doi:10.3390/machines13121107
Research on steel surface defect detection based on improved YOLOv5s
Wang, G., Zhao, G., Pan, Y., & Dai, Z. (2025) · International Symposium on Computer and Information Processing Technology (ISCIPT) · doi:10.1109/iscipt67144.2025.11265550
“The experiment in this paper uses the public data set NEU-DET [12] of Northeastern University.”
Liu, Q., Zhao, J., Wang, H., et al. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113468
A Hybrid-Visual Algorithm for Few-Shot Micro-Motor Winding Defect Detection
Si, K.-X., Cao, G., Yu, L., & Liang, D. (2025) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icia64617.2025.11277887
“For example, He et al. [10] employed Faster R-CNN to detect surface defects on steel belts; Li et al. [11] proposed a container sealing surface defect detection method based on MobileNet-SSD for filling production lines.”
ECGD-YOLO: An Efficient Convolutional Gated and Dynamic Network for Steel Surface Defect Detection
Chen, Z., Cheng, Y., & Song, Q. (2025) · doi:10.1145/3776759.3776830
“This paper mainly verifies the effectiveness of the method through the NEU-DET [ 6 ] and GC10-DET [ 7 ] datasets.”
Chen, J., Zhao, W., Liu, X., et al. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9964-3_1
Chan, S., Miao, Q., Yao, Y., et al. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3609718
“He et al. [12] integrated multilevel features into a unified feature map, employing a region proposal network (RPN) to generate regions of interest (ROI) for achieving high-quality predictions.”
Fan, X., Yang, C., Mei, Y., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5658890
Yazdi, R., Hassannayebi, E., Moshiri, A., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5674657
DCGF-YOLOv8: a lightweight and multi-scale model for wind turbine blade surface defect detection
Wang, Y., Zheng, Y., Cao, Y., Liu, Y., & Cui, T. (2025) · Engineering Research Express · doi:10.1088/2631-8695/ae2ce5
Dynamic convolution and attention-based steel surface defect detection via LDSE-YOLO
Wei, S., Liang, L., Wei, F., & Wang, C. (2025) · Intelligent Data Analysis · doi:10.1177/1088467x251395496 · Cited by 1
GCaSNet: Global Context-Aware Selective Detection Network for Rail Surface Defect Detection
Hua, Y., Yang, Y. H., Sheng, W., Zhu, S., Zhu, J., & Li, Q. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3612032
“He et al. [16] propose an end-to-end deep learning-based automated defect inspection system, called DNN, which obtains the specific class and detailed location of defects by fusing multi-level features.”
YOLO-LAMN: A Lightweight Attention-Guided Multi-Scale Detection Network for Wind Turbine DamagePreprint
Zhang, Z. Z., Li, H., Xu, K., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5991925
SLI-Net: Efficient Lightweight Networks Focused on Critical Defect Detection
Wang, X., Li, Z., Yu, J., Lin, Z., & Sun, W. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5699-1_9
A Dynamic Multi-Scale Fusion and Speed-Optimized Network for Steel Surface Defect Detection
Sun, K., Sun, M., Zhou, H., et al. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-4828-6_11
Li, X., Xiao, H., Wu, H. Y., & Luo, S. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae2ef0
“Reproduced with permission from [22].”
Chen, R., Hua, L., Li, J., et al. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2026.2615148
Contrastive learning enhanced MobileMamba for real time industrial defect detection on edge devices
Huang, J., Ariffin, S. A., Yang, Q., et al. (2026) · Scientific Reports · doi:10.1038/s41598-026-35515-4
L-DC-DETR: A Lite Distance-Content Aware DETR for Gas Pipeline Defect Detection
Chen, C., Zhang, T., Ma, C., Liu, Z., Rehman, S. U., Shi, Y., & Munshi, A. (2026) · Signal Image and Video Processing · doi:10.1007/s11760-025-05070-y
Defect Detection in Aircraft Materials using Generative AI and Deep Learning - A Review
Jingade, P. P., & Garai, B. (2025) · International Conference on Applied Artificial Intelligence and Computing (ICAAIC) · doi:10.1109/icaaic64647.2025.11330538
“ResNet (Residual Networks) greatly enhances performance on tasks like object detection and image categorization [17,40,44].”
RFG ‐ YOLO : Accurate and Lightweight Detection of Multi‐Scale Defects on Metallic Surfaces
Geng, J., Li, M., & Tang, C. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70563 · Cited by 2
“We utilize three public datasets to evaluate RFG-YOLO model’s multi-scale defect detection performance: NEU-DET [33], GEAR-DET [34], and GC10-DET [35].”
Bounding Box-Derived Mask Guidance Network for Accurate Surface Defect Detection
Cui, L., Ma, X., Tian, F., et al. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5764-6_8
AFFNet: Adaptive feature fusion network for defect detection of industrial product surface
Jia, Z., Wang, S., Zheng, J., Han, X., Tang, Y., & Sun, F. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07099-z
“Reducing the channel count to one transforms multi-channel features into a single-channel feature (1) NEU-DET [ 18 ]: This is a publicly available dataset for steel surface defect detection created by Northeastern University, containing six typical surface defects of hot-rolled steel strips: rolled…”
WG-DETR : A Wavelet Domain Enhancement-Based Graph Guided Fusion Model for Defect Detection
Zhang, C. C., Wu, W., Niu, H., Wu, N., & Shi, B. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342477
DSK-YOLO: Feature-level Super Resolution Boosted Industrial Defect Detection
Mu, M., Liu, M., Zhang, S., & Du, S. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11343713
“The NEU-DET [24] is a classic industrial dataset that includes six types of typical surface defects commonly observed on hot-rolled steel strips: crazing, inclusion, patches, pitted surfaces, rolled-in scale, and scratches.”
MAFSRM: A Multiangle Feature Separation and Reconstruction Module for Industrial Defect Detection
Zhang, Z., Gao, Y., Zhu, L., Rigall, E., Wang, X., & Dong, J. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3659550
A two-stage weakly supervised framework for endface defect detection in shaft metal parts
Liao, Y., Suo, X., Zhou, F., Liu, J., & Yin, S. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-025-02785-0 · Cited by 1
Tatar, H., & Küçük, M. F. (2025) · DergiPark (Istanbul University)
Huang, Y.-C., Lin, J.-C., & Wu, Y.-Z. (2026) · Scientific Reports · doi:10.1038/s41598-026-39233-9
“12, 13, 14 and 15.”
Cao, J., Sun, Z., He, Q., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6256553
He, Z., Jin, D., Bai, Z., Hu, Q., Jixuan, W., & Liu, W. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae4a8a
MCAM-Net: multi-scale convolutional attention for enhanced industrial surface defect detection
Zhang, Q., Dong, X., Xiong, J., Zhu, H., Wang, Q., Wang, J., & Dai, W. (2026) · The Visual Computer · doi:10.1007/s00371-026-04380-7 · Cited by 1
“NEU-DET: The NEU-DET dataset is a publicly available dataset collected by Northeastern University in China [36].”
An improved steel surface defects detection method based on YOLOv5
Zhang, Y., Wu, W., Yin, J., Zhang, Z., Lu, S., & Wang, W. (2025) · International Conference on Image, Signal Processing and Communication Technology (ISPCT) · doi:10.1109/ispct68220.2025.11406817
“The dataset used in this experiment is NEU-DET[13], a public Northeastern University steel surface defect database.”
ACP-Net: A Steel Defect Detection Network Based on Multi-Scale Fusion and Precise Localization
Cao, B., Yin, Y., Chen, C., Chen, Z., & Zhang, Y. (2025) · International Conference on Communication Technology and Information Technology (ICCTIT) · doi:10.1109/icctit68197.2025.11406547
“These defects are complex in shape, have large size differences, and significant background interference, which brings great difficulties to the accurate identification of automated detection systems [1].”
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.