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 101–200 of 1,338
Wang, C., & Xiao, Z. (2021) · Agronomy · doi:10.3390/agronomy11081500 · Cited by 66
“Use cases have been mainly seen in manufacturing [13,14].”
MethodDeep Learning and Machine Vision-Based Inspection of Rail Surface Defects
Yang, H., Wang, Y., Hu, J., He, J., Yao, Z., & Bi, Q. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3138498 · Cited by 64
“He et al. [15] presented a multilevel feature fusion network for steel plate defect detection.”
BackgroundA Light-Weight Deep-Learning Model with Multi-Scale Features for Steel Surface Defect Classification
Liu, Y., Yuan, Y., Balta, C., & Liu, J. (2020) · Materials · doi:10.3390/ma13204629 · Cited by 65
“Deep learning models, mostly in the form of Convolutional Neural Networks (CNNs), have been widely used for image classification [4], object detection [20], and text understanding [23].”
BackgroundMD-YOLO: Surface Defect Detector for Industrial Complex Environments
Zheng, H., Chen, X., Cheng, H., Du, Y., & Jiang, Z. (2024) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2024.108170 · Cited by 75
One-Shot Recognition of Manufacturing Defects in Steel Surfaces
Deshpande, A. M., Minai, A. A., & Kumar, M. (2020) · Procedia Manufacturing · doi:10.1016/j.promfg.2020.05.146 · Cited by 89
“explanation of contrastive loss, authors request the readers to refer the paper [9]. 4. Dataset We trained our model of the Siamese network using Northeastern University (NEU) surface defect database2[39,13,12]. This database consists of six classes of surface defects on hotrolled steel strip, viz., rolled-in scale (R…”
MethodMask2Defect: A Prior Knowledge-Based Data Augmentation Method for Metal Surface Defect Inspection
Yang, B., Liu, Z., Duan, G., & Tan, J. (2021) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2021.3126098 · Cited by 66
Yao, H., Yu, W., & Wang, X. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3204368 · Cited by 69
“Subsequently, pattern recognition methods are employed to perform in-depth analyses, such as visual classification [6], [7], object detection [8], and segmentation [9], [10].”
MethodWu, L., Zhang, L., & Zhou, Q. (2022) · IEEE Access · doi:10.1109/access.2022.3198994 · Cited by 60
“With the development of electronic equipment and communication technology, printed circuit boards are widely used in household appliances [1], industrial equipment [2] and military facilities [3], [4].”
BackgroundWu, Q., Qin, X., Dong, K., Shi, A., & Hu, Z. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.118966 · Cited by 69
A detection network for small defects of steel surface based on YOLOv7
Gao, S., Chu, M., & Zhang, L. (2024) · Digital Signal Processing · doi:10.1016/j.dsp.2024.104484 · Cited by 67
Cheng, Y., Cao, Y., Yao, H., Luo, W., Jiang, C., Zhang, H., & Shen, W. (2025) · Journal of Manufacturing Systems · doi:10.1016/j.jmsy.2025.11.022 · Cited by 104
Tang, M. X., Li, Y., Yao, W., Hou, L., Sun, Q., & Chen, J. (2021) · Measurement Science and Technology · doi:10.1088/1361-6501/ac0ca8 · Cited by 61
“The data that support the findings of this study are openly available at the following URL/DOI: http://faculty.neu.edu.cn/ yunhyan/NEU_surface_defect_database.html [20].”
InfluentialA novel MAS-GAN-based data synthesis method for object surface defect detection
Zhang, H., Pan, D., Liu, J., & Jiang, Z. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.05.021 · Cited by 64
Multisensor Image Fusion for Automated Detection of Defects in Printed Circuit Boards
Li, M., Yao, N., Liu, S., Li, S., Zhao, Y., & Kong, S. G. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3106057 · Cited by 57
Zhong, H., Fu, D., Xiao, L., Zhao, F., Liu, J., Hu, Y., & Wu, B. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102437 · Cited by 64
AFF-Net: A Strip Steel Surface Defect Detection Network via Adaptive Focusing Features
Du, Y., Chen, H., Fu, Y., Zhu, J., & Zeng, H. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3398131 · Cited by 74
“The presence of surface defects on strip steel, such as inclusions, crazing, patches, and scratches, critically impacts its quality [3], [4].”
BackgroundMethodA Review of Metal Surface Defect Detection Technologies in Industrial Applications
Qiao, Q., Hu, H., Ahmad, A. A., & Wang, K. (2025) · IEEE Access · doi:10.1109/access.2025.3544578 · Cited by 79
“For example, a quick initial inspection followed by a more detailed analysis of potentially defective areas can balance speed and accuracy [147].”
EFS-YOLO: a lightweight network based on steel strip surface defect detection
Chen, B., Wei, M., Liu, J., Li, H., Dai, C., Liu, J., & Ji, Z. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad66fe · Cited by 61
Zhao, L., Zhang, Y., & Cui, Y. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3172132 · Cited by 54
Progressive refined redistribution pyramid network for defect detection in complex scenarios
Yu, X., Lyu, W., Wang, C., Guo, Q., Zhou, D., & Xu, W. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110176 · Cited by 55
LFRNet: Localizing, Focus, and Refinement Network for Salient Object Detection of Surface Defects
Wan, B., Zhou, X., Zheng, B., Yin, H., Zhu, Z., Wang, H., Sun, Y., Zhang, J., & Yan, C. C. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3250302 · Cited by 72
“In addition, He et al. [24] regarded the defect as a composite task consisting of 1557-9662 © 2023 IEEE.”
BackgroundLi, S., Kong, F., Wang, R., Luo, T., & Shi, Z. (2023) · Measurement · doi:10.1016/j.measurement.2023.113359 · Cited by 62
Li, P., Tao, H., Zhou, H., Zhou, P., & Deng, Y. (2024) · Multimedia Systems · doi:10.1007/s00530-024-01643-y · Cited by 57
“The GC10-DET dataset [47 ] is specifically designed for industrial surface defect detection, with defect samples originating from the surface of cold-rolled steel plates, covering 10 different types of defects (Waist folding, Rolled pit, Crease, Silk spot, Oil spot, Welding line, Water spot,…”
An Improved Faster R-CNN for Steel Surface Defect Detection
Shi, X., Zhou, S., Tai, Y., Wang, J., Wu, S., Liu, J., Xu, K., Peng, T., & Zhang, Z. (2022) · IEEE International Workshop on Multimedia Signal Processing (MMSP) · doi:10.1109/mmsp55362.2022.9949350 · Cited by 64
“Second, we insert Convolutional Block Attention Module (CBAM) [13] after region of interest (RoI) align layer in order to focus on important features and suppress unnecessary ones, boosting representation power of network.”
MethodResearch on Steel Surface Defect Detection Based on YOLOv5 with Attention Mechanism
Shi, J., Yang, J., & Zhang, Y. (2022) · Electronics · doi:10.3390/electronics11223735 · Cited by 61
ALADA: A lite automatic data augmentation framework for industrial defect detection
Wang, Y., Chung, S., Khan, W. A., Wang, T., & Xu, D. J. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.102205 · Cited by 52
Liu, Z., Yang, B., Duan, G., & Tan, J. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3001695 · Cited by 57
“He et al. [22] addressed the problems of defect classification and localization.”
BackgroundDefect identification for oil and gas pipeline safety based on autonomous deep learning network
Zhang, M., Guo, Y., Xie, Q., et al. (2022) · Computer Communications · doi:10.1016/j.comcom.2022.08.001 · Cited by 50
Zhang, D., Song, K., Xu, J., Dong, H., & Yan, Y. (2021) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108334 · Cited by 51
Self-citationReal Time Power Equipment Meter Recognition Based on Deep Learning
Fan, Z., Shi, L., Xi, C., Wang, H., Wang, S., & Wu, G. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3191709 · Cited by 61
Edge-glued wooden panel defect detection using deep learning
Chen, L.-C., Pardeshi, M. S., Lo, W., Sheu, R., Pai, K.-C., Chen, C.-Y., Tsai, P.-Y., & Tsai, Y.-T. (2022) · Wood Science and Technology · doi:10.1007/s00226-021-01316-3 · Cited by 52
“Wood defect identification and location by using convolutional neural networks is presented by He et al. (2019a).”
MethodBoudiaf, A., Benlahmidi, S., Harrar, K., & Zaghdoudi, R. (2022) · Journal of Failure Analysis and Prevention · doi:10.1007/s11668-022-01344-6 · Cited by 55
“This dataset contains six different classes (kinds) of typical surface defects which are: rolled-in scale (RS), patches (Pa), crazing (Cr), pitted surface (PS), inclusion (In), and scratches (Sc) [25, 26].”
BackgroundPeng, Y., Xia, F., Zhang, C., & Mao, J. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3370330 · Cited by 56
Steel surface defect detection and segmentation using deep neural networks
Ashrafi, S., Teymouri, S., Etaati, S., Khoramdel, J., Borhani, Y., & Najafi, E. (2025) · Results in Engineering · doi:10.1016/j.rineng.2025.103972 · Cited by 66
Lin, D., Li, Y., Prasad, S., Nwe, T. L., Dong, S., & Oo, Z. M. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107272 · Cited by 51
Attentive Boundary-Aware Fusion for Defect Semantic Segmentation Using Transformer
Yeung, C.-C., & Lam, K. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3271723 · Cited by 50
“Region-level defect detection aims to recognize and locate the defects in an image through bounding boxes [16], [17], [18].”
BackgroundSurface Defect Detection Using YOLO Network
Hatab, M., Malekmohamadi, H., & Amira, A. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-55180-3_37 · Cited by 56
“The images are obtained from the Northeastern University (NEU) surface database [20], [21], [22] which contains six types of defects (rolled-in scale (Rs), patches (Pa), crazing (Cr), pitted surface (Ps), inclusion (In) and scratches (Sc)) with 300 images for each defect (1800 total).”
MethodDefectNet: Toward Fast and Effective Defect Detection
Li, F., Li, F., & Xi, Q. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3067221 · Cited by 45
“At present, many research studies have applied these object detection algorithms based on CNN to other application scenarios, such as fabric defect detection [7], mobile phone screen surface defect detection [8], and metallic surface defect detection [9], [16].”
BackgroundSehar, U., & Naseem, M. L. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12821-3 · Cited by 60
Sun, X., Jia, X., Liang, Y., Wang, M., Wang, M., & Chi, X. (2022) · IEEE Access · doi:10.1109/access.2022.3204683 · Cited by 50
“Among 37 them, convolutional neural networks are widely used in 38 image classification, object detection, semantic segmenta-39 tion and other tasks due to their powerful image feature 40 extraction ability [5], [6], [7], [8].”
MethodCASDD: Automatic Surface Defect Detection Using a Complementary Adversarial Network
Tian, S., Huang, P., Ma, H., Wang, J., Zhou, X., Zhang, S., Zhou, J., Huang, R., & Li, Y. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3202179 · Cited by 50
“The NEU surface defect database [3] is a publicly available database, which provides the defect images and the corresponding pixel binary images for the hot-rolled steel strip SDD.”
BackgroundMethodWang, Q., Yang, R., Wu, C., & Liu, Y. (2021) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2021.03.053 · Cited by 47
Lightweight strip steel defect detection algorithm based on improved YOLOv7
Lǚ, J., Yu, M., & Liu, J. (2024) · Scientific Reports · doi:10.1038/s41598-024-64080-x · Cited by 54
“The experiments in this paper utilized the NEU-DET dataset, which consists of surface defects on strip steel and was released by Northeastern University 38 .”
MethodFast and Precise Positioning in PCBs Using Deep Neural Network Regression
Tsai, D., & Chou, Y.-H. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2019.2957866 · Cited by 47
“It has been applied to a variety of manufacturing industries, such as printed circuit board (PCB) (see [1], [2]) and steels (see [3], [4]).”
BackgroundAn Effective Framework of Automated Visual Surface Defect Detection for Metal Parts
Qiu, K., Luo, T., & Wang, P. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3095410 · Cited by 46
Attention mechanism and texture contextual information for steel plate defects detection
Zhang, C., Cui, J., Wu, J., & Zhang, X. (2023) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02149-6 · Cited by 46
“A specific physical proposal (He et al., 2019a, 2019b) has been suggested to recognize the form of defects and analyze their causes based on eight typical defects in hot and cold conditions.”
Fu, Q., Liu, J., Zhang, X., et al. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3298424 · Cited by 42
“The CNN-based automatic defect detection paradigms are generally divided into segmentation-based approaches (e.g., [9]) and detection-based approaches (e.g., [10]).”
MethodEC-YOLO: Effectual Detection Model for Steel Strip Surface Defects Based on YOLO-V5
Cheng, Z., Gao, L., Wang, Y., Deng, Z., & Tao, Y. (2024) · IEEE Access · doi:10.1109/access.2024.3391353 · Cited by 53
“The NEU-DET dataset, a collection of surface defects in hot-rolled strip steel, was published by Northeastern University [48].”
MethodDeep Multimodel Cascade Method Based on CNN and Random Forest for Pharmaceutical Particle Detection
Zhang, H., Zhao, M., Liu, L., Zhong, H., Liang, Z., Yang, Y., Zhou, X., Wu, Q. M. J., & Wang, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.2973843 · Cited by 43
“For example, visual detection is commonly used for detection in fabric, semiconductor wafers, railheads [7], steel plate defect inspection [8], concrete materials crack detection [9], and so on.”
MethodTruingDet: Towards high-quality visual automatic defect inspection for mental surface
Liu, Z., Tang, R., Duan, G., & Tan, J. (2020) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2020.106423 · Cited by 44
Chen, R., Cai, D., Hu, X., Zhan, Z., & Wang, S. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3109723 · Cited by 49
Xi, D., Qin, Y., & Wang, S. (2021) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-021-01876-y · Cited by 48
“…FCN (Shelhamer et al., 2017), SegNet (Badrinarayanan et al., 2017), Deeplab (Chen et al., 2018a), RefineNet (Lin et al., 2020), DenseA-SPP (Yang et al., 2018), U-Net (Ronneberger et al., 2015), Mask R-CNN (He et al., 2020b), and Deeplabv3 + (Chen etal.,2018b),havebeenproposedforsemanticsegmentation.”
MethodResearch on intelligent detection of coal gangue based on deep learning
Zhang, Y., Wang, J., Yu, Z., et al. (2022) · Measurement · doi:10.1016/j.measurement.2022.111415 · Cited by 42
Sharma, M., Lim, J., & Lee, H. (2022) · Applied Sciences · doi:10.3390/app12126004 · Cited by 49
“In the paper [25], the author proposed a defect detection system DDN consisting of residual neural network (ResNet) 50 [26] as a base model for classification.”
MethodYuan, Y., Yuan, Y., Baker, T., Kolbe, L. M., & Hogrefe, D. (2021) · Future Generation Computer Systems · doi:10.1016/j.future.2021.06.035 · Cited by 42
“The authors of [18] introduced a multilevel-feature fusion network (MFN), which fused multilevel hierarchical features from di erent layers of the CNN backbone into the same dimension for defect recognition.”
BackgroundA Survey of Vision-Based Methods for Surface Defects’ Detection and Classification in Steel Products
Ibrahim, A. A. M. S., & Tapamo, J. (2024) · Informatics · doi:10.3390/informatics11020025 · Cited by 70
Han, L., Li, N., Li, J., Gao, B., & Niu, D. (2025) · Measurement · doi:10.1016/j.measurement.2025.117019 · Cited by 52
VaB-AL: Incorporating Class Imbalance and Difficulty with Variational Bayes for Active Learning
Choi, J., Yi, K. M., Kim, J., Choo, J., Kim, B., Chang, J.-Y., Gwon, Y., & Chang, H. J. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00668 · Cited by 60
A new genetic algorithm based evolutionary neural architecture search for image classification
Wen, L., Gao, L., Li, X., & Li, H. (2022) · Swarm and Evolutionary Computation · doi:10.1016/j.swevo.2022.101191 · Cited by 50
An End-to-End Defect Detection Method for Mobile Phone Light Guide Plate via Multitask Learning
Li, Y., & Li, J. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3053987 · Cited by 51
“He et al. [10] proposed defect detection of steel plate based on multilevel feature fusion network and region proposal network.”
BackgroundSurvey on industrial defect detection with deep learning
罗, 东., 蔡, 雨., 杨, 子., 章, 哲., 周, 瑜., & 白, 翔. (2022) · Scientia Sinica Informationis · doi:10.1360/ssi-2021-0336 · Cited by 50
Luo, Q., Su, J., Yang, C., Gui, W., Sílven, O., & Liu, L. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3165270 · Cited by 55
“Therefore, it has been widely used as a preprocessing operation in the tasks of defect segmentation [5], defect classification [6], defect recognition [7].”
MethodSchmedemann, O., Baaß, M., Schoepflin, D., & Schüppstuhl, T. (2022) · Procedia CIRP · doi:10.1016/j.procir.2022.05.115 · Cited by 55
Digital Twin Driven End-Face Defect Control Method for Hot-Rolled Coil With Cloud-Edge Collaboration
Xiang, F., Shun, Z., Zuo, Y. N., & Tao, F. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3188508 · Cited by 40
A lightweight algorithm for steel surface defect detection using improved YOLOv8
Ma, S., Zhao, X. J., Wan, L., Zhang, Y., & Gao, H. (2025) · Scientific Reports · doi:10.1038/s41598-025-93469-5 · Cited by 49
Diversifying Tire-Defect Image Generation Based on Generative Adversarial Network
Zhang, Y., Wang, Y., Jiang, Z., Liao, F., Li, Z., Tan, D., Chen, J., & Lu, J. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3160542 · Cited by 46
Lema, D. G., Pedrayes, O. D., Usamentiaga, R., Venegas, P., & Garcia, D. F. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3169484 · Cited by 44
Farady, I., Lin, C.-Y., & Chang, M.-C. (2023) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-023-02109-0 · Cited by 41
“We perform experiments on three challenging, real-world industrial steel surface defect datasets to evaluate the proposed method: (1) the Automatic Optical Inspection (AOI) steel defect dataset 1 , (2) the Magnetic Tile (MT) surface defect dataset [42], and (3) the NEU defect dataset [43].”
Chen, F., Deng, M., Gao, H., Yang, X., & Zhang, D. (2024) · IET Image Processing · doi:10.1049/ipr2.13073 · Cited by 48
CABF-YOLO: a precise and efficient deep learning method for defect detection on strip steel surface
Zhou, Q., & Wang, H. (2024) · Pattern Analysis and Applications · doi:10.1007/s10044-024-01252-5 · Cited by 39
“He et al. [23] utilized CNNs and a multilevel feature fusion network (MFN) to construct a deep learning-based defect detection system for strip steel surface.”
Large scale foundation models for intelligent manufacturing applications: a survey
Zhang, H., Semujju, S. D., Wang, Z., Lv, X., Xu, K., Wu, L., Jia, Y., Wu, J., Liang, W., Zhuang, R., et al. (2025) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-024-02536-7 · Cited by 83
“…of deep learning, including insufficient data labeling, data fluctuations, excessively complex process objects, and noise interference, etc. [80], [129], [131], [139], [284] Lack of interpretability Interpretability referred to the ability to understand and explain the decisions made by a deep…”
TAS 2 -Net: Triple-Attention Semantic Segmentation Network for Small Surface Defect Detection
Liu, T., & He, Z. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3142023 · Cited by 57
“3142023 still many factories employing workers to perform detection manually [2], which are low efficiency, time-consuming, and”
BackgroundEFC-YOLO: An Efficient Surface-Defect-Detection Algorithm for Steel Strips
Li, Y., Xu, S., Zhu, Z., Wang, P., Li, K., He, Q., & Zheng, Q. (2023) · Sensors · doi:10.3390/s23177619 · Cited by 40
“Therefore, this paper uses the YOLOv7 algorithm as the baseline to conduct experiments on the NEU surface defect database (NEU-DET) [19] to evaluate the model.”
BackgroundMethodTD-Net:tiny defect detection network for industrial products
Shao, R., Zhou, M., Li, M., Han, D., & Li, G. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01362-x · Cited by 47
“We conducted experiments on NEU–DET [33], GC10-DET [34] and Peking University PCB defect data sets [35] to verify the effectiveness of the proposed method.”
YOLOv8-QR: An improved YOLOv8 model via attention mechanism for object detection of QR code defects
Zhao, L., Liu, J., Ren, Y., Lin, C., Liu, J., Abbas, Z., Islam, M. S., & Xiao, G. (2024) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2024.109376 · Cited by 38
Lv, S., Liang, T., Zhang, K., Jiang, S., Ouyang, B., Li, Q., & Li, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125727 · Cited by 45
Unified detection method of aluminium profile surface defects: Common and rare defect categories
Zhang, D., Song, K., Xu, J., He, Y., & Yan, Y. (2019) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2019.105936 · Cited by 37
Self-citationLi, K., Wang, X., & Ji, L. (2019) · International Conference on Artificial Intelligence and Advanced Manufacture (AIAM) · doi:10.1109/aiam48774.2019.00136 · Cited by 37
“Northeastern University (NEU) surface dataset [18] we used collected six kinds of typical surface defects of the hot-rolled steel strip.”
MethodMultipath Fusion Mask R-CNN With Double Attention and Its Application Into Gear Pitting Detection
Xi, D., Qin, Y., Luo, J., Pu, H., & Wang, Z. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3049276 · Cited by 39
A new Feature-Fusion method based on training dataset prototype for surface defect recognition
Wang, Y., Li, X., Gao, Y., Wang, L., & Gao, L. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101392 · Cited by 36
Segmentation of Track Surface Defects Based on Machine Vision and Neural Networks
Yang, H., Wang, Y., Hu, J., He, J., Yao, Z., & Bi, Q. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3133280 · Cited by 39
A Graph Guided Convolutional Neural Network for Surface Defect Recognition
Wang, Y., Gao, L., Gao, Y., & Li, X. (2022) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2022.3140784 · Cited by 39
“In the first category, some traditional CNN-based methods are compared, including Decaf [42], DCNN [29], Hier (Hierarchical CNN) [43], MFN [44], Fusion (Multi-fusion) [45], which are state-of-the-art methods in this area.”
MethodMulti-scale multi-modal fusion for object detection in autonomous driving based on selective kernel
Gao, X., Zhang, G., & Xiong, Y. (2022) · Measurement · doi:10.1016/j.measurement.2022.111001 · Cited by 39
An end‐to‐end steel surface defect detection approach via Swin transformer
Tang, B., Song, Z., Sun, W. M., & Wang, X. (2022) · IET Image Processing · doi:10.1049/ipr2.12715 · Cited by 41
An imbalanced small sample slab defect recognition method based on image generation
Fu, T., Li, P., & Liu, S. (2024) · Journal of Manufacturing Processes · doi:10.1016/j.jmapro.2024.03.028 · Cited by 46
DDSNet: Deep Dual-Branch Networks for Surface Defect Segmentation
Yin, Z., Qin, L., Han, G., Shi, X., Zhang, F., Xu, G., & Bi, Y. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3427806 · Cited by 50
“Region-level defect detection can only roughly locate the position of the defects through the bounding box and cannot recognize the size of the defects [11], [12], [13], [14].”
BackgroundA steel surface defect detection method based on improved RetinaNet
Yang, Z., & Liu, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-88527-x · Cited by 46
Track Defect Detection for High-Speed Maglev Trains via Deep Learning
He, Y., Wu, J., Zheng, Y., Zhang, Y., & Hong, X. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3151165 · Cited by 35
Self-citationDrone Footage Wind Turbine Surface Damage Detection
Foster, A., Best, O., Gianni, M., Khan, A., Collins, K. M., & Sharma, S. K. (2022) · Multidimensional Signal Processing Workshop · doi:10.1109/ivmsp54334.2022.9816220 · Cited by 44
“To ensure a fair comparison, the CNNs architectures mentioned in Section III have been initially fine tuned on the NEU-DET dataset [29].”
MA-YOLO: A Method for Detecting Surface Defects of Aluminum Profiles With Attention Guidance
Jiang, L., Yuan, B., Wang, Y., Ma, Y., Du, J., Wang, F., & Guo, J. (2023) · IEEE Access · doi:10.1109/access.2023.3291598 · Cited by 38
Strip steel surface defect detection based on lightweight YOLOv5
Zhang, Y., Shen, S., & Xu, S. (2023) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2023.1263739 · Cited by 38
Zhang, M., Guo, Y., Xie, Q., et al. (2022) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2022.3225059 · Cited by 33
“Up to now, there have been non-destructive evaluation approaches in the pipeline involving X-ray inspection, ultrasonic inspection, metal magnetic memory detection, and magnetic flux leakage (MFL) method [4], [5], among which the MFL method is particularly outstanding due to its convenient recognition, localization [6…”
MethodMulti-Scale Lightweight Neural Network for Steel Surface Defect Detection
Shao, Y., Fan, S., Sun, H., Tan, Z., Cai, Y., Zhang, C. Y., & Zhang, L. (2023) · Coatings · doi:10.3390/coatings13071202 · Cited by 35
“To replace manual operations, it is desired that machines can automatically detect steel surface defects using computer vision technology [2].”
TD-YOLOA: An Efficient YOLO Network With Attention Mechanism for Tire Defect Detection
Peng, C., Li, X., & Wang, Y. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3312753 · Cited by 47
“Defect detection is a downstream task of object detection, which combines defect classification and location [3], [4], [5].”
REDef-DETR: real-time and efficient DETR for industrial surface defect detection
Li, D., Jiang, C., & Liang, T. (2024) · Measurement Science and Technology · doi:10.1088/1361-6501/ad60ea · Cited by 39
“In this paper, the generalization performance of the model is verified by two surface defect detection datasets, NET-DET [21] and PCB-DET.”
Huang, J., Zhang, X., Jia, L., & Zhou, Y. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110214 · Cited by 41
Song, Y., Liu, Z., Wang, J., Tang, R., Duan, G., & Tan, J. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3096284 · Cited by 38
Wang, J., & Lee, S. (2021) · Applied Sciences · doi:10.3390/app11156721 · Cited by 41
A detection method of spangle defects on zinc-coated steel surfaces based on improved YOLO-v5
Xiao, D., Xie, F. T., Gao, Y., Li, Z. N., & Xie, H. (2023) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-023-11963-4 · Cited by 38
“[5] proposed a multilevel feature fusion network, which uses region extraction method to generate regions of interest based on multilevel features, and finally predicts the type and location of defects through a classifier and a bounding box regressor.”
MethodLeontaris, L., Mitsiaki, A., Charalampous, P., Dimitriou, N., Leivaditou, E., Karamanidis, A., Margetis, G., Apostolakis, K. C., Pantoja, S., Stephanidis, C., et al. (2023) · Computers in Industry · doi:10.1016/j.compind.2023.103919 · Cited by 38
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.