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 1,201–1,300 of 1,338
Research on Steel Surface Defect Detection Algorithm Based on Improved YOLOv12
Chen, J., Zhang, J., & Liu, D. (2025) · International Conference on Image Processing, Multimedia Technology and Machine Learning (IPMML) · doi:10.1109/ipmml68499.2025.11407396
Deep learning-based optical inspection system for multi-category surface defect detection in MLCC
Ding, J., Lin, S., zhang, D., et al. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.115052
Mao, Y., Xu, X., Luo, J., Cui, H., Luo, F., Huang, P., & Feng, P. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3670553 · Cited by 1
“Other approaches focus on pixel-level feature extraction methods [7], [8], [9], [10].”
An efficient algorithm for detecting defects on strip steel surfacesPreprint
Li, J., Kong, D., & Hua, C. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6362136
Ma, W., He, D., Sun, H., Jin, Z., & Ma, J. (2026) · Journal of Failure Analysis and Prevention · doi:10.1007/s11668-026-02383-z
“This data set consists of defect images of butt welds formed by Metal Inert Gas (MIG), and a total of 1,500 images were collected; the other is the steel surface defect dataset NEU-DET [53] publicly available from Northeastern University, which contains 1,800 defect images.”
Lightweight WSSG-YOLO for efficient and accurate steel surface defect detection
Peng, Y., He, S. T., Li, Z., Liu, J., Qian, Y., & Liu, B. (2026) · Multimedia Systems · doi:10.1007/s00530-026-02256-3
Zhou, X., Wang, X., Li, G., Liu, D., She, Q., Xu, X., & Cong, R. (2026) · IEEE Transactions on Image Processing · doi:10.1109/tip.2026.3671617 · Cited by 1
“S TRIP steel plays a crucial role in industrial production because it is widely used in many fields [1], [2], such as automobile manufacture, aerospace, shipbuilding, and so on.”
Sun, R., Zhao, D., Yuan, X., et al. (2026) · Journal of Nondestructive Evaluation · doi:10.1007/s10921-026-01351-9
TGNet: Texture-Guided Network for Strip Steel Surface Defect Detection
Gao, S., Wang, H., Lin, L., et al. (2025) · Global Reliability and Prognostics and Health Management Conference (PHM) · doi:10.1109/phm-xian66756.2025.11427629
“In this study, Surface Defects-4i Dataset [1] was used to evaluate the surface defect detection performance of the proposed method, and three benchmark datasets were used to evaluate the COD performance of the proposed method: CAMO, CHAMELEON, and COD10k [8, 9].”
Xiong, T., Gu, J., Yang, Q., Lv, Z., Shen, Z., Liu, J., & Xi, Y. (2026) · Displays · doi:10.1016/j.displa.2026.103439
guo, G., Delin, H., Dexian, W., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6444280
Fine-grained vehicle damage classification based on applicability network
Zhai, Y., Zhang, Z., Zhou, X., Wang, Z., & Wang, Q. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115076
Huang, D., guo, G., Yang, J., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6448479
Enhanced Multi-Scale Defect Detection in Steel Surfaces via Innovative Deep Learning Architecture
Zhou, Z., & Cao, Y. (2026) · Sensors · doi:10.3390/s26062001 · Cited by 1
“In this paper, the NEU-DET dataset [27] and the GC10-DET dataset [28] are used for training and validation to prove the effectiveness of the improved model.”
Zhu, L., & Long, W. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08433-5 · Cited by 1
Xiao, Y., Chen, X., Xie, L., Chen, S., Xiao, X., & Peng, L. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.132025 · Cited by 1
Zhang, T., Wang, W., Ji, H., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6481569
Enhanced visual state space model for real-time wafer defect detection
Sun, R., Zhao, D., Meng, J., et al. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.114590
A deep learning-based approach for RGB Micro-LED defect detection using microscopic vision
Tan, X., Xie, Z., & Chen, M. (2026) · Optics & Laser Technology · doi:10.1016/j.optlastec.2026.115179
Fan, X., Fan, X., Yang, C., et al. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115162
Xiao, W. (2026) · International Conference on Communication Networks and Machine Learning (CNML) · doi:10.1109/cnml68938.2026.11452423 · Cited by 1
“During the hot-rolling process, steel strips are susceptible to various surface defects including cracks, pitting, scratches, inclusions, and rolled-in scale [1].”
Zheng, Z., Wen, Y., & Tao, H. (2026) · Research Square · doi:10.21203/rs.3.rs-9303085/v1
Fast Nonparallel Support Vector Machine with the Margin Hyper-planes and Its Iterative Solver
Liu, L., Yang, Y., Li, P., et al. (2026) · Chinese Journal of Electronics · doi:10.23919/cje.2025.00.007
Enhanced YOLOv8s with Multi-Teacher Distillation for Steel Cord Ply Defect Detection
Huang, P., Xie, Z., Long, R., et al. (2026) · Applied Sciences · doi:10.3390/app16083795
Li, X., Wu, Q., Zhu, F., Huang, P., & Gu, Y. (2026) · Quality and Reliability Engineering International · doi:10.1002/qre.70218
Multi-scale texture information enhancement network for aero-engine blade damage detection
Shi, H., Cao, S., Zuo, H., Lin, C., & Shi, H. (2026) · Measurement · doi:10.1016/j.measurement.2026.121497
Liu, Z., Li, K., Chen, Y., & Wang, D. (2026) · Advances in Mechanical Engineering · doi:10.1177/16878132261442325
Liping, 杨. Y., Jingjing, 吴. W., & Yiming, 张. Z. (2026) · Laser & Optoelectronics Progress · doi:10.3788/lop252026
Resource-constrained energy-latency-aware adaptive model partition approach for edge intelligence
Cao, Y., Fan, H., Tang, B., et al. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08522-5
FREDNET: A Frequency and Decomposed-Spatial Network for Industrial Defect Signal Detection
Zhou, H., Lai, T., Hao, C., Yue, W., Yue, S., & Zhang, H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462834
EFI-YOLO: An enhanced framework for industrial object detection
Zhao, K., Miao, X., Huang, C., & Li, J. (2026) · Journal of Visual Communication and Image Representation · doi:10.1016/j.jvcir.2026.104796
A Wavelet-Based Efficient Defect Detection Model for Resource-Constrained Devices
Xiao, W., Wang, Y., Chen, Z., et al. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11486607
“Datasets: This study uses two publicly available steel surface defect datasets, NEU-DET [13] and GC10-DET [14], to evaluate the performance of the proposed model.”
Zhan, C., Yu, H., Wu, R., et al. (2026) · Electronics · doi:10.3390/electronics15091900
Infrared video imaging for in-line evaluation of oxide descaler performance on steel strips
Karl, R., Angove, J., Valloton, J., et al. (2026) · Ironmaking & Steelmaking Processes Products and Applications · doi:10.1177/03019233261437426
Liu, Y., Wei, X., Chen, M., Liu, G., Zhao, C., Zhang, M., Guo, Y., Zhao, P., & An, R. (2026) · IET Image Processing · doi:10.1049/ipr2.70382
MINOR SURFACE DEFECT DETECTION IN AGRICULTURAL MACHINERY USING AN OPTIMIZED YOLOv11N ARCHITECTURE
Min, L. I., Shuai, Y. U. A. N., & Wenhong, T. A. N. G. (2026) · INMATEH Agricultural Engineering · doi:10.35633/inmateh-78-10
LA-YOLO: A Lightweight Architecture for Real-Time Surface Defect Detection
Huang, J., Zhu, J., & Huang, X. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-8315-7_26
Micro Surface Defect Inspection of Aero-Engine Blades via Dynamic Cross-Scale Semantic Aggregation
Li, K., Jiang, S., Lin, Y., Zhou, J., Qu, H., Meng, X., Wang, Y., & Liu, M. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3683515 · Cited by 1
“3) Extensive experiments on both our AEBD and the public NEU-DET dataset [10] demonstrate that DCSA-Net achieves superior generalization and precision (e.g., a 97.3% mAP 50 on AEBD), significantly outperforming state-of-the-art (SOTA) methods.”
InfluentialWang, H., Li, N., Ni, Z., Yi, J., Zhu, T., Liu, Y., & Yan, Y. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2026.2669839
Self-citationJiang, P.-G., Tu, M.-T., Liu, L.-Y., et al. (2026) · JOM · doi:10.1007/s11837-026-08367-6
Li, X., Cai, J., Liu, T., Wang, F., Zheng, X., & Wang, M. (2026) · Animals · doi:10.3390/ani16101468
“In recent years, with the advancement of deep learning techniques in computer vision [3–5], numerous studies have focused on developing efficient pig face recognition systems to meet practical application needs in complex farming environments.”
Designing an Intelligent Defect Detection Process by Convolutional Neural Networks
Kanani, A., & Azizipour, M. J. (2026) · Journal of Electrical and Computer Engineering · doi:10.1155/jece/7056058
MSA-YOLO: Multi-scale Adaptive Network for surface defect detection of cylindrical lithium battery
Wei, L., Lu, J., & Li, J. (2026) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2026.2671365
SIOWGAN: a single-image-based diverse virtual sample generation method for surface defect detection
Jian, Z., Liu, S., Liu, J., Huang, J., & Liang, Y. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae6d1c
“We evaluate our method on the NEU-DET metal surface defect dataset [28] and the TILDA fabric defect dataset [29].”
Zhao, Z., Liu, J., Zhang, H., Zuo, F., Shen, X., & Ren, H. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3691867
“To assess the generalizability in other defect detection scenarios, we evaluate the proposed method on steel surface defect dataset NEU-DET [39] and no-service rail defect dataset NRSD [2].”
Qiao, H., Wang, J., & Zhang, S. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae6f8b
CAE-YOLO: An Improved Detection Algorithm for Steel Surface Defects
Xiao, N. (2026) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aetcse69203.2026.11503970
“The NEU-DET steel surface defect dataset [13] was utilized, containing 1,800 grayscale images across six defect categories: crazing, inclusions, patches, pitted surfaces, rolled-in scale, and scratches.”
Luo, W., Liang, C., He, J., Yun, D., & Han, J. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae701a
“Edge information is critical for precise defect boundary localization [20, 38].”
He, J., & Wang, J. (2026) · Applied Sciences · doi:10.3390/app16105155
Zhang, X., Zhang, L., Liu, M., Ge, M., & Ling, L. (2026) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2026.101134
A 3D Scanning-Based Method for Surface Defect Detection in Galvanized Scaffolding
Shao, F., Tuli, T. B., Schreiber, F., & Manns, M. (2026) · Lecture notes in mechanical engineering · doi:10.1007/978-3-032-16889-4_59
A Force Controlled Pose Adaptation Method for Robot Based Defect Removal
Shao, F., Tuli, T. B., Schreiber, F., & Manns, M. (2026) · Lecture notes in mechanical engineering · doi:10.1007/978-3-032-16889-4_61
彭, 金., & Xu, Z. (2026) · International Conference on Mechatronics Technology and Intelligent Manufacturing (ICMTIM) · doi:10.1109/icmtim69588.2026.11525528
SES-Net: Semantic-edge synergistic network for industrial small defect detection
Liu, Z., Xia, L., Han, K., Chen, J., Zhu, J., Gan, S., Wang, L., Hu, X., Zhang, J., Li, Q. P., et al. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114067
Zhou, Y.-S., Zhang, C.-L., Liu, Y., et al. (2026) · Measurement science and technology · doi:10.1088/1361-6501/ae7465
“The NEU-DET dataset [57] was released by Northeastern University as an industrial benchmark dataset for hot-rolled steel strip surface defect recognition and localization.”
Wan, Q., Xiao, S., He, W., Sun, Q., Wang, J., & Yu, M. (2026) · Journal of Engineering and Applied Science · doi:10.1186/s44147-026-01065-9
“After years of development and accumulation, many classic models and methods have emerged in the field of CSR, such as Long Short-Term Memory (LSTM) [15], Classification Priority Network (CPN) [16], Multilevel Feature Fusion Network (MFN) [17, 18], and Semi-Supervised Learning (SSL) [19].”
Ma, C., Yu, Q., & Ma, S. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae7620
“This method is not only inefficient and labor-intensive but also susceptible to subjective factors from inspectors, leading to missed and false detections [3].”
Ma, N., & Chen, Y. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae761d
“The NEU-DET dataset [41] is a hot-rolled steel strip surface defect dataset released by Northeastern University (NEU).”
Adaptive Lightweight Convolution-Based Algorithm for Strip Steel Surface Defect Detection
Huang, H. (2026) · International Conference on Intelligent Computing and Signal Processing (ICSP) · doi:10.1109/icsp69961.2026.11540774
“The experiments are conducted on the NEU-DET dataset [20] for strip steel surface defects.”
Xie, F., Liu, Z., Wu, D., Yuan, J., Tang, D., Zhang, P., & Yu, Z. (2026) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2026.05.079 · Cited by 1
Xiang, Z., Yayong, W., Chen, Z., et al. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115632
Shape-aware defect detection network
Zhao, Y., Su, H., Ma, H., Zou, W., Li, X., Cheng, N., & Liu, S. (2026) · Pattern Recognition · doi:10.1016/j.patcog.2026.114208 · Cited by 1
Came-yolov11: a lightweight multi-scale surface defect detection method for ceramic insulators
Tian, X., Ma, C., & Fu, S. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae7bb1
“The proposed method is also tested on other typical surface defect scenarios to further evaluate generalization capability, where the proposed model is processed under two public datasets, i.e. the Northeastern University Surface Defect Database (NEU-DET) [32] and the fabric defect detection [33].”
Saha, S., Hossain, S. S., Mubashir, M. A., Khan, M. T. I., Reja, M. I., & Akhtar, J. (2026) · IEEE International Conference on Quantum Photonics, Artificial Intelligence & Networking (QPAIN) · doi:10.1109/qpain69676.2026.11546442
“Large-scale efforts such as the Quantum Point Defect (QPOD) database now provide systematic catalogs of formation energies, charge transitions, and optical signatures, accelerating the identification of defect configurations relevant for quantum technologies [16].”
Huang, D., guo, G., Yang, J., Wang, D., & 廖琳琳 (2026) · Research Square · doi:10.21203/rs.3.rs-8234620/v1
Cao, J., Sun, Z., Ding, J., et al. (2026) · Metals · doi:10.3390/met16060657
“However, manual inspection is inherently subjective, and many NDT methods depend on dedicated instruments and are not well suited to continuous online monitoring under production conditions [12].”
Liu, K., Huang, D., Li, Z., & Luo, W. (2026) · Journal of Power Sources · doi:10.1016/j.jpowsour.2026.240738
Yuan, M., Zhao, X., Shen, R., Yang, Z., & Wang, G. (2026) · Measurement Science and Technology · doi:10.1088/1361-6501/ae7ea3
“He et al [18] and Wei et al [19] successfully resolved the misalignment issue caused by feature quantization through the optimization of multi-level feature fusion and region of interest pooling, thereby significantly enhancing the detection rate of minute defects.”
Li, H., Liu, C.-N., Sun, Q., Cao, X., & Xu, K. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.115793
CNS-YOLOv8: An Improved YOLOv8-Based Defect Detection Method
Geng, R., Jiang, Y., Li, J., Wu, K., Yang, Y., Li, Z. Y., & Chang, Y. (2026) · Electronics · doi:10.3390/electronics15122730
An Improved YOLO with Multi-Scale Attention for Lightweight Steel Surface Defect Detection
Li-xia, W., Wu, X., Tong, X., et al. (2026) · doi:10.1109/aiita69518.2026.11567102
“…[2] achieve high accuracy but fail to meet the real-time demands of production lines; the YOLO series [3]–[5], as representative single-stage algorithms, balances detection speed and accuracy with ease of embedded deployment, and has been widely applied to steel surface defect detection tasks [6].”
DND-DETR: Haar Wavelet-Guided Steel Defect Detection with Wasserstein Constraint
Liu, G., Liu, N., Zhao, Z., et al. (2026) · doi:10.1109/icaisisas68969.2026.11567732
“Experiments were conducted on the NEU-DET dataset [20], which contains 1800 images spanning six common categories of hot-rolled steel strip surface defects: crazing, inclusion, patches, pitted surface, rolled-in scale, and scratches.”
Steel Surface Defect Detection Method Based on an Improved YOLOv11s
Xue, Q., Hu, Y., & Li, C. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11559990
“Experimental results on the NEU-DET dataset [9] show that the improved method increases mAP@0.5 and mAP@0.5:0.95 by 2.2% and 3.2%, respectively, with negligible additional overhead.”
InfluentialSemi-Supervised Steel Surface Defect Detection Method Based on Improved Yolov8
Zhang, M., Ren, Y., Qin, H., Zhang, H., Sun, Y., & Hu, Z. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11559743
“He et al. [11] used an improved convolutional neural network and proposed a multi-level feature fusion network to combine multiple hierarchical features into one feature to improve the performance of steel detection.”
Kandel, N., Wu, P., Yu, Y., et al. (2026) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc69976.2026.11559775
“The experiment utilizes the NEU-DET [14] dataset, a publicly accessible dataset designed for steel surface defect detection.”
Khan, M. A., Roy, S., Bandopadhyay, K., et al. (2026) · IEEE Sensors Letters · doi:10.1109/lsens.2026.3708183
“Digital Object Identifier 10.1109/LSENS.2026.3708183 in degraded, distorted, and varying clarity making underwater crack detection, single or multiple, and extremely challenging [13].”
InfluentialSFViT: A compact squeeze-and-fusion vision transformer for efficient visual perception
Wu, R., Liu, J., Wang, Y., Li, D., & Chen, D. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00931-z
“Different from large-scale ImageNet classification, NEU-CLS is a relatively small-scale industrial dataset.”
InfluentialLDS-Net: a lightweight detection network for real-time steel surface-defect detection
Xue, C., & Wang, J. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01927-8 · Cited by 1
“This study used two publicly available datasets of steel surface defects: NEU-DET [40] and GC10-DET [41].”
Geng, D., Wang, Y., & Li, S. (2026) · Engineering Research Express · doi:10.1088/2631-8695/ae86ba
“To validate the effectiveness and generalization capability of the proposed model, two publicly available industrial defect detection datasets are employed in this study, namely NEU-DET [31] and PKU-PCB [32], which are used for steel surface defect detection and PCB defect detection, respectively.”
DyFA-YOLO: Towards Robust and Efficient Industrial Defect Detection
He, J., & Wang, H. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11582491
“To evaluate our method for industrial defect detection, we used three datasets: NEU-DET [14], GC10-DET [15], and DsPCBSD+ [16].”
Yu, X., Chen, X., Wang, D., et al. (2026) · Journal of King Saud University - Computer and Information Sciences · doi:10.1007/s44443-026-00985-z
“To evaluate the generalization capability of FSC-GAN beyond the Alibaba Tianchi tile defect dataset, we conduct additional experiments on the NEU-DET steel surface defect dataset (He et al. 2020).”
Self-citationMCM-YOLO: A Lightweight Conflict Mitigation Network for Industrial Metal Surface Defect Detection
Zhang, S., He, K., Xu, J. Q., Sha, H., & Chen, Z. L. (2026) · Sensors · doi:10.3390/s26144349
“To evaluate MCM-YOLO for industrial metal surface defect detection and assess its performance on different public benchmarks, this article conducts experiments on two representative public datasets, namely, NEU-DET [37] and GC-10 [38].”
Wang, L., Ma, Y., Gong, T., & Li, Q. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-03199-x
Metal surface defect detection model based on multi-scale feature fusion and attention mechanism
Ni, R., CHEN, H., Xu, S., Liang, X., Xia, Y., & He, M. (2026) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2026.115674 · Cited by 1
Li, C., He, Y., Sun, W., Li, Z., Wang, H., & Yan, C. (2026) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2026.3712876
“Water droplets typically occupy only a small portion of the image area, making them susceptible to feature degradation when processed through deep networks [15], [16].”
Self-citationWang, T., & Zou, K. (2026) · Eng—Advances in Engineering · doi:10.3390/eng7070344
“The NEU-DET dataset [36] contains six representative categories of steel surface defects: Crazing (Cr), Inclusion (In), Patches (Pa), Pitted Surface (Pi), Scratches (Sc), and Rolled-in Scale (Rs).”
Chai, Y., & Yang, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3507-0_47
LGCG-Net: Sequential Local-Global Refinement for Imbalanced Industrial Defect Classification
Zhou, H., Chen, J., & Yang, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-3429-5_49
SIDF-YOLO: focusing on small targets for real-time insulator defect detection
Chen, D., Jian, Z., Xiang, S., Li, M., & Wang, X. (2026) · Journal of Real-Time Image Processing · doi:10.1007/s11554-026-01940-x
“To comprehensively evaluate the generalization ability of SIDF-YOLO across diverse domains, comparative experiments were conducted on two distinct public datasets: VisDrone and NEU-DET [41].”
SceneGate: A Scene-Adaptive Inference Bridge for Real-Time Open-Vocabulary Detection
Meng, X., & Ma, Y. (2026) · Communications in computer and information science · doi:10.1007/978-981-92-3531-5_36
DiffCL: Diffusion contrastive learning for strip steel surface defect classification
Chen, J., Zhu, X., Hu, H., Han, K., Liu, Y., Li, Q., & Liu, Z. (2026) · Expert Systems with Applications · doi:10.1016/j.eswa.2026.133699
Research on Steel Plate Surface Defect Detection Method Based on Faster R-CNN
Zhang, Y., Wu, W., Jia, D., et al. (2026) · doi:10.1109/icaide69370.2026.11604537
“In this study, the open-source NEU-DET dataset from Northeastern University is adopted for model training, which contains six types of defects: cracks, inclusions, patches, pitting, rolled-in scales, and scratches [7], as shown in Figure 2.”
SPF-YOLO: A Synergistic Perception and Fusion YOLO Architecture for Defect Detection
Zhang, D., & Wang, J. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3712718
Huang, D., guo, G., Yang, J., & Wang, D. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7164360
Li, J., Xiong, W., Lu, J., Gu, P., He, Y., Chen, J., & Dong, X. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-026-11552-z
Self-citationRethinking Efficiency: A Structural Compression Framework for Domain-Specific Visual RecognitionPreprint
Abazi, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7160880
AG-DPF: adaptive gating-based dual-prototype fusion framework for metal anomaly detection
Chen, C. Y. J., Li, Y., Chen, M., Zhang, H., Dong, Z. L. W., & Wei, S. (2026) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-026-02932-1
Zhang, T., Wang, W., Ji, H.-B., et al. (2026) · Fusion engineering and design · doi:10.1016/j.fusengdes.2026.115980
SCD-YOLO: A Detail-Enhanced Network for Strip Steel Surface Defect Detection
Jiang, J., & Su, Y. (2026) · Open Journal of Applied Sciences · doi:10.4236/ojapps.2026.167145
RCSNet: A recalibration-driven cross-scale collaborative network for steel surface defect detection
Li, L., Lu, S., Ren, Z., Tang, C., & Liang, Y. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.134684 · Cited by 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.