Skip to main content
SpringerLink
Log in

Detecting Anomalous Solder Joints in Multi-sliced PCB X-ray Images: A Deep Learning Based Approach

  • Original Research
  • Published:
SN Computer Science Aims and scope Submit manuscript

Abstract

As the components become smaller and packing becomes denser, printed circuit boards (PCB) become more prone to mistakes during the assembling. Therefore, solder joint defect detection is of vital importance. X-ray inspection plays a dominant role as it can detect surface defects and the defects hidden inside the solder joint. However, it is a labour intensive process to inspect the X-ray images. Hence by having artificial intelligence (AI) to automate the inspection process is desired. Nonetheless, there are challenges to train an AI module for such applications, as during the production line, normal and defect solder joints are very imbalanced, and there are likely novel types of defected solder joints in the incoming dataset that is unseen in the training dataset. In this paper, an outlier exposure based defect solder joint detection method is proposed to mitigate the above problems. The proposed method is dedicated designed for high dimensional multi-sliced X-ray image dataset. Our method is validated on a very large real-world dataset and shows that it has on-par performance over the current state-of-art methods in terms of test accuracy of 74.66% with 0.85 recall and 0.29 false positive rate while maintaining 70% reduction in the number of parameters. While handling X-ray images with variable number of image slices in contrast to the methods present in the literature.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

Data availability

The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.

Notes

  1. https://github.com/hirunima/outlier_exposure

References

  1. Chalapathy R, Menon AK, Chawla S. Robust, deep and inductive anomaly detection. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases. Berlin: Springer; 2017. p. 36–51.

    Chapter  Google Scholar 

  2. Erfani SM, Rajasegarar S, Karunasekera S, Leckie C. High-dimensional and large-scale anomaly detection using a linear one-class svm with deep learning. Pattern Recogn. 2016;58:121–34.

    Article  Google Scholar 

  3. Fort S, Ren J, Lakshminarayanan B. Exploring the limits of out-of-distribution detection. In: Advances in Neural Information Processing Systems 2021

  4. Gao H, Jin W, Yang X, Kaynak O. A line-based-clustering approach for ball grid array component inspection in surface-mount technology. IEEE Trans Industr Electron. 2016;64(4):3030–8.

    Article  Google Scholar 

  5. Hendrycks D, Gimpel K. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: International Conference on Learning Representations 2017.

  6. Hendrycks D, Mazeika M, Dietterich T. Deep anomaly detection with outlier exposure. In: International Conference on Learning Representations 2019.

  7. Kemmler M, Rodner E, Wacker ES, Denzler J. One-class classification with gaussian processes. Pattern Recogn. 2013;46(12):3507–18.

    Article  Google Scholar 

  8. Khan SS, Madden MG. One-class classification: taxonomy of study and review of techniques. Knowl Eng Rev. 2014;29(3):345–74.

    Article  Google Scholar 

  9. Kolesnikov A, Dosovitskiy A, Weissenborn D, Heigold G, Uszkoreit J, Beyer L, Minderer M, Dehghani M, Houlsby N, Gelly S, Unterthiner T, Zhai X. An image is worth 16x16 words: Transformers for image recognition at scale 2021.

  10. Koner R, Sinhamahapatra P, Roscher K, Günnemann S, Tresp V. Oodformer: Out-of-distribution detection transformer. arXiv preprint arXiv:2107.08976 2021.

  11. Krizhevsky A, Hinton G, et al. Learning multiple layers of features from tiny images 2009.

  12. Lee K, Lee H, Lee K, Shin J. Training confidence-calibrated classifiers for detecting out-of-distribution samples. In: International Conference on Learning Representations 2018.

  13. Liang S, Li Y, Srikant R. Enhancing the reliability of out-of-distribution image detection in neural networks. In: International Conference on Learning Representations 2017.

  14. Lin BJ, Tsan TC, Tung TC, Lee YH, Fuh CS. Use 3d convolutional neural network to inspect solder ball defects. In: Cheng L, Leung ACS, Ozawa S, editors. Neural information processing. Cham: Springer International Publishing; 2018. p. 263–74.

    Chapter  Google Scholar 

  15. Lin CH, Wang SH, Lin CJ. Using convolutional neural networks for character verification on integrated circuit components of printed circuit boards. Appl Intell. 2019;49(11):4022–32.

    Article  Google Scholar 

  16. Lu X, He Z, Su L, Fan M, Liu F, Liao G, Shi T. Detection of micro solder balls using active thermography technology and k-means algorithm. IEEE Trans Industr Inf. 2018;14(12):5620–8.

    Article  Google Scholar 

  17. Pang G, Shen C, Cao L, Hengel AVD. Deep learning for anomaly detection: a review. ACM Comput Surv. 2021;54:2. https://doi.org/10.1145/3439950.

    Article  Google Scholar 

  18. Perera P, Patel VM. Learning deep features for one-class classification. IEEE Trans Image Process. 2019;28(11):5450–63.

    Article  MathSciNet  MATH  Google Scholar 

  19. Roerdink JB, Meijster A. The watershed transform: Definitions, algorithms and parallelization strategies. Fund Inform. 2000;41(1, 2):187–228.

    MathSciNet  MATH  Google Scholar 

  20. Ruff L, Vandermeulen R, Goernitz N, Deecke L, Siddiqui SA, Binder A, Müller E, Kloft M. Deep one-class classification. In: International conference on machine learning 2018; 4393–4402.

  21. Sabokrou M, Khalooei M, Fathy M, Adeli E. Adversarially learned one-class classifier for novelty detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition 2018; 3379–3388.

  22. Schlegl T, Seeböck P, Waldstein SM, Langs G, Schmidt-Erfurth U. f-anogan: Fast unsupervised anomaly detection with generative adversarial networks. Med Image Anal. 2019;54:30–44.

    Article  Google Scholar 

  23. Xiao Y, Wang H, Xu W, Zhou J. Robust one-class svm for fault detection. Chemom Intell Lab Syst. 2016;151:15–25.

    Article  Google Scholar 

  24. Yung LC. Investigation of the solder void defect in ic semiconductor packaging by 3d computed tomography analysis. In: 2018 IEEE 20th Electronics Packaging Technology Conference (EPTC), IEEE 2018; 886–889

  25. Zenati H, Foo CS, Lecouat B, Manek G, Chandrasekhar VR. Efficient gan-based anomaly detection. arXiv 2018.

  26. Zhang Q, Zhang M, Gamanayake C, Yuen C, Geng Z, Jayasekara H, Cw Woo, Low J, Liu X, Guan YL. Deep learning based solder joint defect detection on industrial printed circuit board x-ray images. Complex Intell Syst. 2022;8(2):1525–37.

    Article  Google Scholar 

  27. Wang Zhou, Bovik AC, Sheikh HR, Simoncelli EP. Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process. 2004;13(4):600–12.

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Singapore University of Technology and Design, Singapore, Singapore

    Hirunima Jayasekara & Chau Yuen

  2. University of Maryland, College Park, USA

    Hirunima Jayasekara

  3. National ASIC Research Center, Southeast University, Nanjing, China

    Qianru Zhang & Meng Zhang

  4. Keysight Company, Singapore, Singapore

    Chia-Wei Woo & Jenny Low

Authors
  1. Hirunima Jayasekara
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Qianru Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chau Yuen
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Meng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chia-Wei Woo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Jenny Low
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Hirunima Jayasekara.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Consent for publication

Not applicable.

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

Jayasekara, H., Zhang, Q., Yuen, C. et al. Detecting Anomalous Solder Joints in Multi-sliced PCB X-ray Images: A Deep Learning Based Approach. SN COMPUT. SCI. 4, 307 (2023). https://doi.org/10.1007/s42979-023-01765-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s42979-023-01765-6

Keywords

Search

Navigation