A Semi-Supervised Inspection Approach of Textured Surface Defects under Limited Labeled Samples
Open accessAbstract
Defect inspection is a key step in guaranteeing the surface quality of industrial products. Based on deep learning (DL) techniques, related methods are highly effective in defect classification tasks via a supervision process. However, collecting and labeling many defect samples are usually harsh and time-consuming processes, limiting the application of these supervised classifiers on various textured surfaces. This study proposes a semi-supervised framework, based on a generative adversarial network (GAN) and a convolutional neural network (CNN), to classify defects of a textured surface, while a novel label assignment scheme is proposed to integrate unlabeled samples into semi-supervised learning to enhance the overall performance of the system. In this framework, a customized GAN uses limited labeled samples to generate unlabeled ones, while the proposed label assignment scheme makes the generated data follow different label distributions in such a way that they can participate in training with labeled data. Finally, a CNN is proposed for semi-supervised training and the category identification of each defect sample. Experimental results show the effectiveness and robustness of the proposed framework even if original samples are limited. We verify our approach on four different surface defect datasets, achieving consistently competitive performances.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 actual steel production, high-quality datasets for training machine learning algorithms are very difficult to obtain because defects are small probability events and obtaining many samples with various defect types is difficult.
“In the actual production environment, it is very difficult to obtain high quality datasets for training machine learning related algorithms because defects in steel production are originally small probability events, and it is very difficult to obtain many samples with various types of defects”
From Steel Surface Defect Recognition: A Survey (2022) · cites this paper as [5]
The Introduction says defect samples are hard to collect in large numbers and attributes the difficulty of collecting defect data to the rare occurrence of defects. It discusses industrial textured surfaces, including metal, but does not specifically establish this for steel production or say that obtaining samples across various defect types is difficult. Page numbers are unavailable in our copy. (LLM, conf=0.84)
Experimental — accuracy not yet measuredLabeling steel surface defect data is costly and labor intensive.
“the labeling of the data is also costly and labor intensive [4][5][6][7].”
From Steel Surface Defect Recognition: A Survey (2022) · cites this paper as [5]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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 · see citing works
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 · see citing works
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 74,248 · see citing works
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138 · see citing works
Unsupervised representation learning with deep convolutional generative adversarial networks
Radford, A., Metz, L., & Chintala, S. (2015) · arXiv · doi:10.48550/arxiv.1511.06434 · Cited by 12,235 · see citing works
Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation
Papandreou, G., Chen, L.-C., Murphy, K. P., & Yuille, A. (2015) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.203 · Cited by 1,041 · see citing works
Song, K., & Yan, Y. (2013) · Applied Surface Science · doi:10.1016/j.apsusc.2013.09.002 · Cited by 1,026 · see citing works
Autoencoding beyond pixels using a learned similarity metricPreprint
Larsen, A., Sønderby, S. K., Larochelle, H., & Winther, O. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1512.09300 · Cited by 712 · see citing works
Semi-Supervised Learning with Generative Adversarial NetworksPreprint
Odena, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.01583 · Cited by 539 · see citing works
Deep learning based image recognition for crack and leakage defects of metro shield tunnel
Huang, H., Li, Q.-T., & Zhang, D. (2018) · Tunnelling and Underground Space Technology · doi:10.1016/j.tust.2018.04.002 · Cited by 495 · see citing works
A Generic Deep-Learning-Based Approach for Automated Surface Inspection
Ren, R., Hung, T., & Tan, K. C. (2018) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2017.2668395 · Cited by 485 · see citing works
Semi-Supervised Deep Learning Using Pseudo Labels for Hyperspectral Image Classification
Wu, H., & Prasad, S. (2017) · IEEE Transactions on Image Processing · doi:10.1109/tip.2017.2772836 · Cited by 466 · see citing works
Automatic fruit classification using deep learning for industrial applications
Hossain, M. S., Al-Hammadi, M., & Muhammad, G. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2875149 · Cited by 347 · see citing works
Surface defect classification of steels with a new semi-supervised learning method
Di, H., Ke, X., Peng, Z., & Dongdong, Z. (2019) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2019.01.011 · Cited by 241 · see citing works
Deep Convolutional Computation Model for Feature Learning on Big Data in Internet of Things
Li, P., Chen, Z., Yang, L. T., Zhang, Q., & Deen, M. J. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2739340 · Cited by 199 · see citing works
Generalized Completed Local Binary Patterns for Time-Efficient Steel Surface Defect Classification
Luo, Q., Sun, Y., Li, P., Simpson, O., Tian, L., & He, Y. (2019) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2852918 · Cited by 178 · see citing works
Self-citationA Coarse-to-Fine Model for Rail Surface Defect Detection
Yu, H., Li, Q., Tan, Y., Gan, J., Wang, J., Geng, Y., & Jia, L. (2018) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2018.2853958 · Cited by 174 · see citing works
Wood inspection with non-supervised clustering
Sílven, O., Niskanen, M., & Kauppinen, H. (2003) · Machine Vision and Applications · doi:10.1007/s00138-002-0084-z · Cited by 165 · see citing works
A Simple Guidance Template-Based Defect Detection Method for Strip Steel Surfaces
Wang, H., Zhang, J., Tian, Y., Chen, H., Sun, H., & Liu, K. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2887145 · Cited by 153 · see citing works
Classification of surface defects on steel sheet using convolutional neural networks
Zhou, S., Chen, Y., Zhang, D., Xie, J., & Zhou, Y. (2017) · Materiali in tehnologije · doi:10.17222/mit.2015.335 · Cited by 130 · see citing works
Deep learning-based fabric defect detection: A review
Kahraman, Y., & Durmuşoğlu, A. (2022) · Textile Research Journal · doi:10.1177/00405175221130773 · Cited by 117 · see citing works
Song, K., Wang, J., Bao, Y., Huang, L., & Yan, Y. (2022) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2022.3215909 · Cited by 115 · see citing works
Transfer-Learning-Based Online Mura Defect Classification
Yang, H. S., Mei, S., Song, K., Tao, B., & Yin, Z. (2017) · IEEE Transactions on Semiconductor Manufacturing · doi:10.1109/tsm.2017.2777499 · Cited by 108 · see citing works
Zhang, Z., Wen, G., & Chen, S. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2775218 · Cited by 103 · see citing works
Ambiguous Surface Defect Image Classification of AMOLED Displays in Smartphones
Park, Y., & Kweon, I. S. (2016) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2016.2522191 · Cited by 79 · see citing works
Convolutional networks for voting-based anomaly classification in metal surface inspection
Natarajan, V., Hung, T.-Y., Vaikundam, S., & Chia, L.-T. (2017) · 2017 IEEE International Conference on Industrial Technology (ICIT) · doi:10.1109/icit.2017.7915495 · Cited by 79 · see citing works
Fine-Grained Material Classification Using Micro-geometry and Reflectance
Kampouris, C., Zafeiriou, S. P., Ghosh, A., & Malassiotis, S. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46454-1_47 · Cited by 64 · see citing works
Verifying edges for visual inspection purposes
Wen, W., & Xia, A. (1999) · Pattern Recognition Letters · doi:10.1016/s0167-8655(98)00150-0 · Cited by 48 · see citing works
Classification of Defective Fabrics Using Capsule Networks
Kahraman, Y., & Durmuşoğlu, A. (2022) · Applied Sciences · doi:10.3390/app12105285 · Cited by 19 · see citing works
Liu, C., Su, K., Yang, L., Li, J., & Guo, J. (2022) · Coatings · doi:10.3390/coatings12050614 · Cited by 2 · see citing works
Flagged first, then by citations
Research works printed but not linked: 1
- Huang, Y.; Qiu, C.; Guo, Y. Saliency of magnetic tile surface defects. In Proceedings of the 14th IEEE International Conference on Auto-Mation and Engineering, Munich, Germany, 18-22 June 2018.
Cited by
Sorted by citations
Steel Surface Defect Recognition: A Survey
Wen, X., Shan, J., He, Y., & Song, K. (2022) · Coatings · doi:10.3390/coatings13010017 · Cited by 191 · see citing works
Self-citationMulti-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 33 · see citing works
Sun, Q., Xu, K., Liu, H., & Wang, J. (2023) · Optics and Lasers in Engineering · doi:10.1016/j.optlaseng.2023.107674 · Cited by 30 · see citing works
A Survey on Surface Defect Inspection Based on Generative Models in Manufacturing
He, Y., Li, S., Wen, X., & Xu, J. (2024) · Applied Sciences · doi:10.3390/app14156774 · Cited by 28 · see citing works
Self-citationZhang, Y., Lan, R., Li, X., Fang, J., Ping, Z., Liu, W., & Wang, Z. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3395316 · Cited by 20 · see citing works
A High-Quality Sample Generation Method for Improving Steel Surface Defect Inspection
He, Y., Li, S., Wen, X., & Xu, J. (2024) · Sensors · doi:10.3390/s24082642 · Cited by 10 · see citing works
Self-citationWaste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal ProductionPreprint
Shahin, M., Chen, F. F., Hosseinzadeh, A., & Maghanaki, M. (2023) · Research Square · doi:10.21203/rs.3.rs-2782987/v1 · Cited by 5 · see citing works
Surface Defect Detection of Aluminum Profiles Based on Multiscale and Self-Attention Mechanisms
Shao, Y., Fan, S., Zhao, Q., Zhang, L., & Sun, H. (2024) · Sensors · doi:10.3390/s24092914 · Cited by 4 · see citing works
Wen, X., Zhao, W., Yu, Z., Zhao, J., & Song, K. (2023) · Coatings · doi:10.3390/coatings13071171 · Cited by 3 · see citing works
Self-citationPerformance evaluation of CNN models for steel surface defect detection in lean manufacturing
Hosseinzadeh, A., Shahin, M., Lopez, E. C., Chen, F. F., & Maghanaki, M. (2025) · Manufacturing Letters · doi:10.1016/j.mfglet.2025.06.146 · Cited by 3 · see citing works
AM-CFDN: semi-supervised anomaly measure-based coal flow foreign object detection network
Li, W., Yu, Y., Wang, C., Zhang, X., Duan, J., & Bai, L. (2024) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-024-02433-8 · Cited by 3 · see citing works
Solid Surfaces, Defects and Detection
Song, K. (2024) · Coatings · doi:10.3390/coatings14121575 · Cited by 1 · see citing works
Xia, P., Wang, S., Ni, Y., Mei, Z., & Li, J. (2024) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn63567.2024.00161
Chen, K., Dou, Y., & Zhang, Y. (2026) · IEEE International Conference on Power, Electronics and Green Energy (ICPEGE) · doi:10.1109/icpege67691.2026.11451533
- Authors
- He, Y., Wen, X., & Xu, J.
- Affiliations
- Shenyang University of Technology (CN)
- Corresponding author
- He, Yu
- Venue
- Coatings
- Publisher
- MDPI AG
- Published
- 2022-11-09
- Volume
- 12
- Issue
- 11
- Pages
- 1707
- ISSN
- 2079-6412 (ISSN-L)
- OpenAlex
- W4308866885
- Cited by
- 14
- References
- 31
- Citations by year
- 2026: 1 · 2025: 1 · 2024: 7 · 2023: 4 · 2022: 1
- FWCI
- 1.49
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Coatings (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- SUT Youth Scientific Research Ability Cultivation Project (200005796)
- 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 › Engineering › Mechanical Engineering › Non-Destructive Testing Techniques
- Keywords
- surface defect detection, textured surfaces, semi-supervised learning, generative adversarial networks, limited labeled data, synthetic data generation, convolutional neural networks, defect classification
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
