Skip to main content
Springer Nature Link
Log in

Visual detection for mobile phone surface defects based on semisupervised learning

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

This paper presents Fix-YOLOX (Fixmatch-You Only Look Once X), a semisupervised target detection model that uses a small amount of annotated data for fully supervised training, and adds a semisupervised training module using both pseudolabelling and consistent regularization to prevent overfitting in fully supervised training by using unlabelled data. Additionally, the generalization of the model and its fault tolerance to labelled data are improved. The experimental results show that the proposed semisupervised visual detection algorithm, Fix-YOLOX, can substantially reduce the amount of data annotation required for the target detection task while effectively overcoming the problem caused by annotated data with uneven quality. The YOLOX model achieves 91.95% accuracy with 50% annotated data and an average detection time of 10.4 ms per image/frame, which is consistent with the detection time of original YOLOX. Therefore, the model has good real-time performance and generalizability.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

Data availability

The data that support the findings of this study are available on request from the corresponding author upon reasonable request. The data are not publicly available due to their containing information that could compromise the privacy of research participants.

References

  1. AlBahar A, Kim I, Yue X (2022) A robust asymmetric kernel function for bayesian optimization, with application to image defect detection in manufacturing systems[J]. IEEE Trans Autom Sci Eng 19(4):3222–3233

    Article  Google Scholar 

  2. Zhu H, Huang J, Liu H, Zhou Q, Zhu J, Li B (2022) Deep-learning-enabled automatic optical inspection for module-level defects in LCD[J]. IEEE Internet Things J 9(2):1122–1135

    Article  Google Scholar 

  3. Ni X, Liu H, Ma Z, Wang C, Liu J (2022) Detection for rail surface defects via partitioned edge feature[J]. IEEE Trans Intell Transp Syst 23(6):5806–5822

    Article  Google Scholar 

  4. Huo S, Zhang B, Muddassir M, Chik DTW, Navarro-Alarcon D (2022) A sensor-based robotic line scan system with adaptive ROI for inspection of defects over convex free-form specular surfaces[J]. IEEE Sensors J 22(3):2782–2792

    Article  Google Scholar 

  5. Wang W, Mi C, Ziheng Wu, Kun Lu, Long H, Pan B, Li D, Zhang J, Chen P, Wang B (2022) A real-time steel surface defect detection approach with high accuracy[J]. IEEE Trans Instrum Meas 71:5005610–5005610

    Google Scholar 

  6. Zhang H, Song Y, Chen Y, Zhong H, Liu Li, Wang Y, ThangarajahAkilan QM, Jonathan Wu (2020) MRSDI-CNN: Multi-Model Rail Surface Defect Inspection System Based on Convolutional Neural Networks[J]. IEEE Transactions Intell Transport Systems 23(8):11162–11177

    Article  Google Scholar 

  7. Wang H, Li Z, Wang H (2022) Few-shot steel surface defect detection[J]. IEEE Trans Instrum Meas 71:5003912–5003912

    Google Scholar 

  8. Gao X, Wu X, Xu P et al (2020) Semi-supervised texture filtering with shallow to deep understanding[J]. IEEE Trans Image Process 29:7537–7548

    Article  Google Scholar 

  9. Luan CH, Cui RY, Sun L et al (2020) A siamese network utilizing image structural differences for cross-category defect detection[C]. 2020 IEEE International Conference on Image Processing (ICIP). IEEE, 778–782

  10. Wang T, Zhang C, Ding RW et al (2021) Mobile phone surface defect detection based on improved Faster R-CNN[C]. 25th International Conference on Pattern Recognition (ICPR). IEEE, 9371–9377

  11. Yang XY, Dong FY, Liang F et al (2021) Chip defect detection based on deep learning method[C]. 2021 IEEE International Conference on Power Electronics, Computer Applications (ICPECA). IEEE, 215–219

  12. Liu T, He Z (2022) TAS2-Net: Triple-attention semantic segmentation network for small surface defect detection[J]. IEEE Trans Instrum Meas 71:5004512–5004512

    Google Scholar 

  13. Haoyuan LYU, Lu YU, Xingyu Z et al (2021) Review of semi-supervised deep learning image classification methods[J]. J Frontiers Comp Sci Technol 15(6):1038

    Google Scholar 

  14. Luo J, Yang Z, Li S, Yilin Wu (2021) FPCB surface defect detection: a decoupled two-stage object detection framework[J]. IEEE Trans Instrum Meas 70:5012311–5012311

    Article  Google Scholar 

  15. Liu Y, Zhang B, Wang B et al (2020) Semi-supervised semantic segmentation of remote sensing images based on generative adversarial network[J]. J Infrared Millimeter Waves 39(4):473–482

    Google Scholar 

  16. Li Y, Yang M, Hua J, Zeda Xu, Wang J, Fang X (2022) A channel attention-based method for micro-motor armature surface defect detection[J]. IEEE Sens J 22(9):8672–8684

    Article  Google Scholar 

  17. Zeng N, Peishu Wu, Wang Z, Li H, Liu W, Liu X (2022) A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection[J]. IEEE Trans Instrum Meas 71:3507014–3507014

    Article  Google Scholar 

  18. Wang C, Zhou Z, Chen Z (2022) An enhanced YOLOv4 model with self-dependent attentive fusion and component randomized mosaic augmentation for metal Surface defect detection[J]. IEEE Access 10:97758–97766

    Article  Google Scholar 

  19. Usamentiaga R, Lema DG, Pedrayes OD, Garcia DF (2022) Automated surface defect detection in metals: A comparative review of object detection and semantic segmentation using deep learning[J]. IEEE Trans Ind Appl 58(3):4203–4213

    Article  Google Scholar 

  20. Sun M, Lu C, Han Y et al (2021) Surface defect detection of attention-fusion mechanism under weak supervision learning[J]. J Computer-Aided Design Comp Graphics 33(6):920–928

    Article  Google Scholar 

  21. Fang J, Tan X, Wang Y (2021) ACRM: attention cascade R-CNN with Mix-NMS for metallic surface defect detection[C]. 25th international conference on pattern recognition (ICPR). IEEE, 423–430

  22. Sohn K, Berthelot D, Carlini N et al (2020) Fixmatch: Simplifying semi-supervised learning with consistency and confidence[J]. Adv Neural Inf Process Syst 33:596–608

    Google Scholar 

  23. Ge Z, Liu S, Wang F et al (2021) Yolox: exceeding yolo series in 2021[J]. arXiv preprint arXiv:2107.08430

  24. ultralytics. yolov5. Available online: https://github.com/ultralytics/yolov5. 2022.12

  25. He K, Fan H, Wu Y et al (2020) Momentum contrast for unsupervised visual representation learning[C]. Proc IEEE/CVF Conf Comput Vis Pattern Recognit. IEEE, 9726–9735. https://doi.org/10.1109/CVPR42600.2020.00975

  26. Yuan T, Wan F, Fu M et al (2021) Multiple instance active learning for object detection[C]. Proc of the IEEE/CVF Conf Comput Vis Pattern Recognit 5330–5339

Download references

Acknowledgements

This research was financially supported by The Major Scientific Research Project for Universities of Guangdong Province (2020ZDZX3058, 2023ZDZX1038); Guangdong Provincial Special Funds Project for Discipline Construction (No. 2013 WYXM0122); Science and Technology Projects of Zhuhai in the field of social development (2220004000066); Key Laboratory of Intelligent Multimedia Technology (201762005); Course Teaching and Research Section of Guangdong Province (104); Research Project for Undergraduate Universities Online Open Course Guidance Committee of Guangdong Province (2022ZXKC534); and Higher Education Teaching Reform Project of Guangdong Province (655).

Funding

The Major Scientific Research Project for Universities of Guangdong Province,(2020ZDZX3058, 2023ZDZX1038); Guangdong Provincial Special Funds Project for Discipline Construction (No. 2013 WYXM0122); Science and Technology Projects of Zhuhai in the field of social development (2220004000066); Key Laboratory of Intelligent Multimedia Technology (201762005); Course Teaching and Research Section of Guangdong Province (104); Research Project for Undergraduate Universities Online Open Course Guidance Committee of Guangdong Province (2022ZXKC534); and Higher Education Teaching Reform Project of Guangdong Province (655),ge yang

Author information

Authors and Affiliations

  1. Research Center for Intelligent Engineering and Educational Application, Key Laboratory of Intelligent Multimedia Technology, Beijing Normal University, Zhuhai, 519087, China

    Ge Yang & Qifeng Zhou

Authors
  1. Ge Yang
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Qifeng Zhou
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Ge Yang.

Ethics declarations

Conflicts of interest

We declare that we have no financial and personal relationships with other people or organizations that can inappropriately influence our work. There is no professional or other personal interest of any nature in any product, service and/or company that could be construed as influencing the position presented in, or the review of, the entitled manuscript.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Yang, G., Zhou, Q. Visual detection for mobile phone surface defects based on semisupervised learning. Multimed Tools Appl 83, 76367–76387 (2024). https://doi.org/10.1007/s11042-024-18384-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-024-18384-9

Keywords