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 1,001–1,100 of 1,338
SESC-YOLO: Enhanced YOLOV5 for Detecting Defects on Steel Surface
Kavitha, S., Baskaran, K. R., & Santhiya, K. (2023) · Algorithms for intelligent systems · doi:10.1007/978-981-99-4577-1_17 · Cited by 1
Efficient and Accurate Detector with Global Feature Aggregation for Steel Surface Defect Detection
Qian, K., Wang, Z., & Zou, L. (2023) · Lecture notes in computer science · doi:10.1007/978-981-99-6501-4_29 · Cited by 1
Wang, Y., Zhang, C., Li, H., Li, H., Diao, Q., Ren, X., Hao, X., Lin, B., & Yan, S. (2023) · Polymer Composites · doi:10.1002/pc.27952 · Cited by 1
Research on Surface Defect Detection of Steel Strip Based on Deep Learning
Qin, H., Xiao, Y., Wang, Y., et al. (2023) · International Conference on Computing, Communication, Perception and Quantum Technology (CCPQT) · doi:10.1109/ccpqt60491.2023.00058 · Cited by 1
“It achieved 79.4% mAP on the NEU-DET dataset, but the detection speed is only 14.1FPS, which cannot Meeting Industrial Needs; He et al. [11] proposed a strip steel surface defect detection model based on Faster-RCNN, which achieved 82.4% mAP on the NEU-DET data set, but the detection speed was…”
MethodInfluentialFuzzy Twin Support Vector Machine Based on Smooth Pinball Loss
Zheng, Z., Lü, P., Cai, H., et al. (2023) · International Annual Conference on Complex Systems and Intelligent Science (CSIS-IAC) · doi:10.1109/csis-iac60628.2023.10363948 · Cited by 1
Inception meets Swin Transformer: A Novel Approach for Metal Defect Recognition
Tang, D., & Zhao, Y. (2024) · Academic Journal of Science and Technology · doi:10.54097/5q6vkj91 · Cited by 2
“The NEU-CLS dataset[22], developed by Northeastern University, comprises of 1800 images of typical surface defects on hot rolled steel strips, with 300 images for each of the six defect types: cracking (Cr), inclusions (In), plaque (Pa), pitting (Ps), oxide (Rs), and scratches (Sc).”
MethodGCE-YOLOv5s Based Surface Defect Detection Algorithm for Strip Steel
Zhang, Y. X., & Wu, J. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10451921 · Cited by 1
“He et al. [9] constructed a system that uses a convolutional neural network (CNN) to extract defective features and fuse them to obtain final features.”
MethodIndustrial Image Anomaly Localization Method based on Reverse Knowledge Distillation
Zhang, T. (2024) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac59436.2024.10503620 · Cited by 1
A Study on the Man-Hour Prediction in Structural Steel Fabrication
Wei, Z., Li, Z., Niu, R., Jin, P., & Yu, Z. (2024) · Processes · doi:10.3390/pr12061068 · Cited by 2
Weighted Linear Loss Large Margin Distribution Machine for Pattern Classification
Liu, L., Chu, M., Gong, R., Liu, L., & Yang, Y. (2024) · Chinese Journal of Electronics · doi:10.23919/cje.2022.00.156 · Cited by 1
Localization and Classification of Defects on Natural Wood Surfaces
Sander, T., & Wöhler, C. (2024) · IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit58233.2024.10540767 · Cited by 1
“Current image classification methods excel at anomaly detection where the desired reference is well-defined, such as metal surfaces [1] or textiles [2].”
BackgroundA Novel Federated Transfer Learning Framework Based on Collaborative GAN for Smart Manufacturing
Li, S., Cui, Q., Li, X., Liao, Y., Zhao, X., & Tao, X. (2024) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc57260.2024.10570977 · Cited by 2
“Two industrial defect detection datasets (the steel plate defect dataset NEU-CLS-64 [16], Solar panel defect dataset Elpv [17]) and two public datasets (Mnist, Fashion mnist) are applied as candidate source datasets.”
MethodSurface Defect Detection Algorithm for Sagger Based on Improved YOLOv5s
Song, T., Zhang, Y., Chen, T., & Chen, J. (2024) · International Conference on Computer Information and Big Data Applications (CIBDA) · doi:10.1145/3671151.3671351 · Cited by 1
“Saggers are commonly used high-temperature resistant containers for storing materials and firing them in high-temperature kilns [ 2 ] .”
Application Study of YOLOv5 Algorithm on Automotive Wheel Surface Defect Detection
Xia, X., Zhang, Z., & Liu, F. (2024) · Chinese Control Conference (CCC) · doi:10.23919/ccc63176.2024.10662206 · Cited by 3
“He et al. [16] proposed an inspection sys-tem for steel plate defect detection, which used a baseline convolutional neural network (CNN) with multilevel feature fusion network (MFN) and region proposal network (RPN).”
MethodA Powerful Object Detection Network for Industrial Anomaly Detection
Ge, Y., & Meng, L. (2024) · International Conference on Industrial Artificial Intelligence (IAI) · doi:10.1109/iai63275.2024.10730509 · Cited by 1
“Industrial anomaly detection is a major task in maintaining operational efficiency and safety in a variety of industries, including manufacturing, automotive, energy and power, electronics and semiconductor industries [1], [2].”
BackgroundZeng, L., Zheng, F., Chang, X., Chen, J. A., & Wang, S. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad956b · Cited by 1
“In 2020, He et al improved the detection performance of the entire object detection network by fusing multi-level features to obtain more defect localization information, meeting the production requirements of strip steel in terms of both detection accuracy and speed [15].”
Ambiguous Boundary Uncertainty Reduction in Single Stage Detector Models
Bharti, D., Puneeth, B., & Venkatesh, K. S. (2024) · IEEE International Conference on Computer Vision and Machine Intelligence (CVMI) · doi:10.1109/cvmi61877.2024.10782711 · Cited by 1
“3 (a)-(d), we show an image from the NEU-DET dataset [15] where the Orange colored ground truth bounding box of the defect is ambiguously annotated by multiple annotators.”
Lightweight Neural Network Optimization for Rubber Ring Defect Detection
Gao, W., Huang, Z., & Hu, H. (2024) · Applied Sciences · doi:10.3390/app142411953 · Cited by 2
Rajaram, V., Ingle, Y., Rajayogeshwar, G., Adishesha, P., & Lawrence, K. D. (2025) · Lecture notes in mechanical engineering · doi:10.1007/978-981-97-6176-0_7 · Cited by 2
Semi-supervised Learning with GAN for Semantic Segmentation of Wood Defect Image
Zheng, K., Zheng, S., Xu, Z., et al. (2024) · China Automation Congress (CAC) · doi:10.1109/cac63892.2024.10865192 · Cited by 1
“For example, He et al. [1] proposed a CNN-based network to localize and classify defects on the surface of steel plates by introducing a multilevel feature fusion network.”
Steel surface defect detection based on bidirectional cross-scale fusion deep network
Xie, Z., & Jin, L. (2025) · Optical Review · doi:10.1007/s10043-025-00957-0 · Cited by 3
“We conduct experiments on NEU-DET dataset [2], which contains six types of metal surface defects: cracks (Cr), inclusions (In), patches (Pa), pits (Ps), rolled-in scale (Rs), and scratches (Sc).”
Fusion YOLOv8s and Dynamic Convolution Algorithm for Steel Surface Defect Detection
Huang, C., Cui, J., Li, Y., et al. (2025) · Symmetry · doi:10.3390/sym17050701 · Cited by 1
Li, J., Liu, J., & Fan, J. (2025) · Optics & Laser Technology · doi:10.1016/j.optlastec.2025.113654 · Cited by 11
A real-time surface defect detection system for industrial products with long-tailed distribution
He, X., & Qian, X. (2021) · IEEE Industrial Electronics and Applications Conference (IEACon) · doi:10.1109/ieacon51066.2021.9654741 · Cited by 4
Bearing Lubricant Corrosion Identification Through Transfer Learning
Bellizzi, R., Galary, J. T., & Heryudono, A. R. H. (2022) · Lecture notes in mechanical engineering · doi:10.1007/978-3-030-93639-6_15 · Cited by 1
Human-Machine Collaborative Classification Model for Industrial Product Defect
Liu, Y., Wang, K., & Cheng, X. (2021) · International Conference on Computational Intelligence and Security (CIS) · doi:10.1109/cis54983.2021.00038 · Cited by 1
DPANet: A Dynamic Convolutional Neural Network for Brake Disc Surface Defects Detection
Wang, S., Zhang, G., & Guan, B. (2022) · Chinese Control Conference (CCC) · doi:10.23919/ccc55666.2022.9901984 · Cited by 1
“proposed an end-to-end defect detection pipeline which fuses multi-scale features [18].”
BackgroundSAGE: Stealthy Attack GEneration for Cyber-Physical SystemsPreprint
Biehler, M., Zhong, Z., & Shi, J. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.09905 · Cited by 1
An Analysis of Defect Detection on Steel Strip Surface Using Modified Yolo V5Preprint
Deepti Raj, G., & Prabadevi, B. (2022) · Research Square · doi:10.21203/rs.3.rs-1815194/v1 · Cited by 1
Steel Surface Defect Classification Based on Legendre Multiwavelet Transform and SVMPreprint
zheng, X., Liu, W., & Huang, Y. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4469855 · Cited by 2
Twin support vector machine with two margin hyperplanes and weighted linear lossPreprint
Gong, R., Chu, M., Liu, L., & Liu, L. (2023) · Research Square · doi:10.21203/rs.3.rs-3699994/v1 · Cited by 1
Classification and Localization of Defects Using Single-Shot Multibox DetectorPreprint
Ihianle, I. K., Kaur, M., Chauhan, K. K., Aggarwal, N., Joshi, G., Vig, R., & Owa, K. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4673716 · Cited by 1
Ye, W., Ren, J., Liang, J., Liu, W., Yi, H., Zhang, A. A., & Lu, C. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4819840 · Cited by 1
de Souza, M. A. A. (2020) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.76.2020.tde-15052020-105711 · Cited by 1
Defect Detection of Production Surface Based on CNN
Sun, Y., Cai, Y., Li, Y., & Zhao, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-64243-3_30 · Cited by 1
Defect Detection Based on Fusion of Phase Congruency and Shear Wavelet
Li, R., Chen, Y., Yang, W., Lin, F., Gao, H., & Liang, G. (2020) · International Symposium on Autonomous Systems (ISAS) · doi:10.1109/isas49493.2020.9378880
DCGAN-Based Data Augmentation for Enhanced Performance of Convolution Neural Networks
Reser, C., & Reich, C. (2020) · Repository of Futwangen University of Applied Sciences (Furtwangen University) · Cited by 1
Research on Defect Classification and Detection Technology of Image Processing Collected by Computer
Luo, X., & Cai, G. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1952/2/022045
“When = 0, the Wiener filter is transformed into a standard inverse filter [6].”
MethodWelding Defect Recognition Technology and Application Based on Convolutional Neural Network
Xu, L., Xie, X., Li, X., & Hu, F. (2021) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc51323.2021.9498679
Siamese Basis Function Networks for Data-Efficient Defect Classification in Technical Domains
Schlagenhauf, T., Yildirim, F., & Brückner, B. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-26236-4_7 · Cited by 2
Smart Road Danger Detection and Warning
Yuan, Y. (2021) · eDiss (Georg-August-Universität Göttingen) · doi:10.53846/goediss-8965
Compact and Efficient Feature Representation for Defect in hot rolled strip steel:A postion paper
Su, J., Luo, Q., & Yang, C. (2022) · Asian Control Conference (ASCC) · doi:10.23919/ascc56756.2022.9828012
A Stable Lightweight Model for Metal Crack Detection Based on YOLOv5
Liao, J., Yang, L., Tan, H., & Zhou, F. (2022) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc55077.2022.9886426
“[15] used a baseline CNN to generate feature maps, and synthesized features through a multi-stage feature fusion network to achieve detailed localization of steel plate defects.”
MethodFaster RCNN based on Feature Fusion and its Application in Steel Surface Defect Detection
Xu, S., & Shao, Z. (2022) · Scientific Journal of Technology · doi:10.54691/sjt.v4i10.2400
“The effectiveness of the algorithm is verified through experiments on the NEU‐DET dataset.”
MethodInfluentialU-shaped Vision Transformer and Its Application in Gear Pitting Measurement
Wang, S., Qin, Y., Xi, D., et al. (2022) · Journal of Dynamics Monitoring and Diagnostics · doi:10.37965/jdmd.2022.130
Sun, C., Wan, Q., Li, Z., Gao, L., Li, X., & Gao, Y. (2022) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49997.2022.9926496
“Multiple Hierarchical Features are fused in an end-to-end way for steel surface defect detection [8].”
MethodAn Edge Computing based Defect Detection Algorithm for Malleable Iron
Bai, J., & Jiang, X. (2022) · 2022 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892043
“However, those two-stage based defect detection methods [5]–[9] have considerable accuracy, but the inference speed (0.4-33 FPS) on GPUs is far from reaching the real-time demands.”
BackgroundMethodInfluentialQuality Analysis of high-density polyethylene based on Intelligent Vision Detection
Jiang, J., Zhan, X., Liu, Y., Tang, C., Wang, J., & Liu, J. (2022) · International Conference on Industrial Artificial Intelligence (IAI) · doi:10.1109/iai55780.2022.9976537
“At present, the YOLO algorithm is widely used in small object detection [16] [17] and various scene recognition [18] [19] [20].”
MethodA Novel Defect Inspection Approach Based on Self-attention Convolutional Adversarial Auto-Encoder
Wang, J., Li, Y., & Han, Z. (2022) · International Conference on Robotics, Control and Automation Engineering (RCAE) · doi:10.1109/rcae56054.2022.9995893
“Defect inspection is a crucial step to guarantee the quality of industrial production, such as manual manufacturing [1], chemical industry [2], railway track [3], cement road and bridge construction [4], etc.”
BackgroundA Pipe Defect Localization Method for Robotic Repair Manipulation
Mao, D., Zheng, Y., Li, F., Fu, T., Li, D., Wang, Y., Song, R., & Li, Y. (2022) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio55434.2022.10011678
“[9] propose an end-to-end network to detect steel surface defects on NEU database [10].”
BackgroundSteel Defect Detection Based on Yolov5
Deng, W., & Ma, W. (2022) · doi:10.1145/3573942.3574109
On-Demand Multiclass Imaging for Sample Scarcity in Industrial Environments
Orti, J., Moreno-Noguer, F., & Puig, V. (2023) · doi:10.1145/3589572.3589573
Twin Margin Distribution Machine with Equality Constraints for Pattern ClassificationPreprint
Gong, R., Liu, L., Chu, M., & Liu, L. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4463275
Qin, H., Su, C., Mao, Y., et al. (2023) · International Conference on Intelligent Control, Measurement and Signal Processing (ICMSP) · doi:10.1109/icmsp58539.2023.10171023
Segmentation and Detection of Industrial Surface Defect Based on Deep Neural Network
Hou, Y. M., & Qian, S. (2023) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-2730-2_59
Steel Surface Defect Classification Based on Legendre Multiwavelet Transform and SVMPreprint
zheng, X., Liu, W., & Huang, Y. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4524941
Defect Diagnosis of Hot Rolling Steel Surfaces Based on Deep Learning
Fors, M. N., Younes, M. A., Darwish, S. H., & Kholief, E. A. (2023) · International Telecommunications Conference (ITC-Egypt) · doi:10.1109/itc-egypt58155.2023.10206408
“He et al.[7] provided an all-encompassing deep learning method for the problem of detecting steel surface defects.”
Xiong, J., An, J., Wang, X.-A., Ou, H., & Chen, X. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10240658
Improved Two-Stage Neural Network for Defect Detection
Zheng, J., Lei, Q., & Xu, Y. (2023) · Chinese Control Conference (CCC) · doi:10.23919/ccc58697.2023.10239929
Discover unknown fault categories through active query evidence model
Wang, M., Jiang, X., Wen, T., et al. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04965-y
“Simultaneously, He et al. [16] fused multi-level features into one feature that contains more fault information.”
BackgroundMethodAn Improved YOLOv5 with Structural Reparameterization for Surface Defect Detection
Han, Y., & Zheng, L. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44210-0_8
GH-QFL: Enhancing Industrial Defect Detection Through Hard Example Mining
Xiao, X., Du, Y., Yang, R., Hu, R., & Li, X. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-44207-0_20
Surface Defect Detection on Strip Steel Based on Hybrid Attention Mechanism and Yolov8Preprint
Zhang, Y., Shen, S., & Xu, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4588486
胡, 新., He, J., zhang, C., et al. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4611107
Research on Weld Detection Based on Weighted Feature Fusion Network
Wang, M.-J. J., Ma, X., Mu, C., et al. (2023) · International Conference on Digital Image Processing · doi:10.1145/3604078.3604113
“This experiment uses recall, Precision and mean Average Precision (mAP) rate as an evaluation index [12].”
MethodHo, C.-C., Liu, C.-H., Chen, M.-F., & Kao, M.-C. (2023) · IMEKO TC10 Conference on Measurement for Diagnostics, Optimisation and Control · doi:10.21014/tc10-2023.001 · Cited by 1
Strip Pickling Defect Detection Based on Improved YOLOv5s Algorithm
Zhu, X., Zhang, M., Liu, Y., Wan, X., Wang, X., & Zhou, P. (2023) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc58219.2023.10326882
Steel surface defect detection based on lightweight model
He, L., Huang, J., Li, X., & Guan, B. (2023) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac59482.2023.10401449
“In 2020, He et al. [6] proposed a multilevel feature fusion network (MFN), which merges several hierarchical features into a single feature.”
BackgroundSteel Surface Defect Detection Method Based on Improved YOLOv4-tiny
Li, J., Gu, Q., Chen, Y., et al. (2023) · International Conference on Image Processing, Computer Vision and Machine Learning (ICICML) · doi:10.1109/icicml60161.2023.10424749
“He et al [7] proposed a multilevel neural network (MFN) to fuse multiple hierarchical features to enrich the defect location details; Cheng et al [8] proposed a new deep neural network (DNN) with differential channel attention and adaptive spatial fusion with RetinaNet (DEA_RetinaNet) to improve…”
MethodMachine Intelligence for Detection of Dents and Scratches on Car Body
Bhatlawande, S. S., Patil, A. N., Nachan, A., et al. (2023) · OITS International Conference on Information Technology (OCIT) · doi:10.1109/ocit59427.2023.10430919
SISTEM INSPEKSI PERMUKAAN BAJA BERBASIS DEEP LEARNING MENGGUNAKAN METODE ANCHOR-FREE
Yuliyanto, S., Amani, N. F., Akhyar, F., & Usman, K. (2022) · Jurnal Ilmiah Teknik Mesin Elektro dan Komputer · doi:10.51903/juritek.v2i3.364 · Cited by 2
“Mean average precision (mAP) merupakan parameter yang digunakan untuk mengevaluasi kinerja model secara keseluruhan, yang merupakan nilai rata-rata dari Average Precision (AP) keseluruhan kelas [2], [5].”
BackgroundRDMS: Reverse Distillation with Multiple Students of Different Scales for Anomaly DetectionPreprint
Chen, Z., Lyu, C., Zhang, L., et al. (2024) · Research Square · doi:10.21203/rs.3.rs-3975230/v1
An Adaptive Margin Semi-supervisedLearning for Industrial Surface InspectionPreprint
Zheng, X., Zhou, L., Liu, Y., Xue, A., Kong, Y., & Wang, Y. (2024) · Research Square · doi:10.21203/rs.3.rs-3980581/v1
Gai, C., Shi, Y., Li, H., & zhao, D. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4768864
Industrial Defect Detection Based on a Two-Stage Lightweight Network with Mixed SupervisionPreprint
Liu, T.-L., Wang, Z., Dai, X., & Sun, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4772843
Iac: Iou-Aware Clustering for Anchor Configuration Determination in Efficient Defect DetectionPreprint
Zhao, Y., Su, H., Zhong, C., Zou, W., Guo, Y., & Liu, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4785165
EANet: Enhanced Attention-based Model for Surface Defect Detection
Liu, G. (2024) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac59436.2024.10503680
Improved YOLOv3 Method for Detecting Surface Defects in Cold Rolled Steel Strip
Xia, X., Li, X., Gao, Y., & Sun, H. (2023) · IEEE International Conference on Computer and Communications (ICCC) · doi:10.1109/iccc59590.2023.10507371
“The experimental dataset is adopted from NEU-DET [18-20], which collects six types of typical defects on the strip steel surface, 300 samples of each type of defects totaling 300 images, a total of 1800 grayscale images, and the original resolution of each image is 200 × 200 pixels.”
MethodResearch on Small Object Defect DetectionAlgorithms Based on Deep LearningPreprint
Li, J., Lu, Y., Li, M., Li, P., Wang, R., Qi, J., & Zuo, H. (2024) · Research Square · doi:10.21203/rs.3.rs-4342862/v1
KGC-YOLOv5: A YOLOv5-based Method for Steel Surface Defects Detection
Chen, Y., Li, Z., & Meng, Y. (2023) · International Conference on Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI) · doi:10.1109/cei60616.2023.10528149
“He et al. [6] proposed a model method based on CNN to generate regions of interest through multi-level feature fusion network and regional suggestion network to achieve end-to-end detection.”
MethodSteel defect detection based on multi-angle and multi-feature fusion network
Yu, F., & Zhang, J. (2024) · European Journal of Mathematics and Applications · doi:10.28919/ejma.2024.4.13
“He, Y et al. [6] proposed a multi-level feature fusion network (MFN).”
Zhang, W., Guo, Z., Xu, J., et al. (2024) · Learning and analytics in intelligent systems · doi:10.1007/978-3-031-56521-2_1
Enhanced Defect Classification With CNN’s And path Aggregation Network
Khedidja, M., Abbas, F., & Hemam, M. (2024) · International Conference on Image and Signal Processing and their Applications (ISPA) · doi:10.1109/ispa59904.2024.10536835
A Novel Approach for Steel Defects Detection Using Yolo-Ae: Iiot Enabled Defect Detection SystemPreprint
Biswas, S., Ganesh, A., & Banerjee, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4866209
A Steel Surface Defect Detection Algorithm Based on YOLOv7-Tiny
Zhang, Y. (2024) · International Conference on Advanced Algorithms and Control Engineering (ICAACE) · doi:10.1109/icaace61206.2024.10549295
“NEU-DET dataset is a public data set published by Northeastern University for detecting defects on steel surfaces [13].”
MethodKuo, S., Lin, P., Huang, X.-R., et al. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4880700
Yu, Y., Li, A., & Sun, A. (2024) · Chinese Control and Decision Conference (CCDC) · doi:10.1109/ccdc62350.2024.10587482
“In the domain of industrial product surface defect detection, quality inspection equipment, integrating machine vision and deep learning technology [1], [2], is gradually replacing manual visual inspection and traditional machine vision tools.”
BackgroundBai, G., Gu, J. J., Xing, Y. T., et al. (2024) · IEEE International Conference on Electronic Technology, Communication and Information (ICETCI) · doi:10.1109/icetci61221.2024.10594543
“He, Y., et al.[10]proposed a novel deep learning based defect detection system for steel plates.”
BackgroundWang, Q., Liu, D., Tian, H., Qin, Y., & Zhao, D. (2024) · Sensors · doi:10.3390/s24154798
“In this section, the Handwritten Digit Recognition CVL database [29] and the North-eastern University (NEU) surface defect database [30,31] are used for experimental comparison.”
MethodHao, Q., Gan, Q., Liu, Z., Chen, J., Shen, Q., Qian, C., & Liu, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5588-2_41 · Cited by 5
Huang, L. P., Shen, Q., Zheng, Y., et al. (2024) · doi:10.1109/ijcnn60899.2024.10651452
“This dataset [27] collected 1800 images with the surface defects of the hot-rolled steel strip, which is provided by the researchers of Northeastern University (NEU) of China.”
MethodZhang, J., Li, D., Wei, C., Wang, X., & Peng, G. (2024) · IEEE International Conference on Electronic Information and Communication Technology (ICEICT) · doi:10.1109/iceict61637.2024.10671349
“…industry, addressing various issues mentioned in the existing literature, such as the limitations of image processing technology in automatic quality inspection [5] and the challenges of fault detection methods based on image processing and deep learning in diverse applications [6], [7].”
BackgroundAutomatic iterative diversity improvement for defect data generation
Pi, X., Xie, Y., Zhang, Y., Wang, X., & Ren, F. (2024) · doi:10.1145/3686812.3686819
Adaptive Dual Attention Fusion Network for RGB-D Surface Defect Detection
Jiang, X., Liu, J., Yan, F., Lu, Y., Jin, S., Liu, H., & Xu, M. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-8692-3_28
Gda-Detr: A Global Dynamic Aware Detection Transformer for Fresnel Lens Defect InspectionPreprint
Pang, S., Chen, Z., Zhu, X., Wang, X., Xing, Y., Zhao, Y., Xu, F., & Li, G. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5038209
Ouyang, R., Wang, Z., Zhao, W., Gao, S., Guo, X., & Yu, J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.5038204
Adaptive Shape Imitation and Selective Semantic Guidance for Industrial Surface Defect DetectionPreprint
Liang, X., Li, Y., Wang, X., et al. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5088043
DCKD: Distribution-Corrected Knowledge Distillation for Enhanced Industrial Defect Detection
Du, W., & Zhou, H. (2025) · IEEE Access · doi:10.1109/access.2025.3533479
“In fast-paced industries like manufacturing and electronics, the demand for high production standards has led to the widespread adoption of automated defect detection systems powered by deep learning [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11], [12].”
Intelligent Detection of Industrial Defect Images
Liu, T., Bao, J., Zheng, Y., et al. (2025) · Springer series in advanced manufacturing · doi:10.1007/978-3-031-81477-8_6
A Computer Vision Model Utilizing Autoencoders for Surface Defect Recognition
Pal, S., Bhattacharyya, R., Nandi, S., & Saha, S. (2025) · Communications in computer and information science · doi:10.1007/978-3-031-81339-9_9
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.