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.
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.
References
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.
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.
Fort S, Ren J, Lakshminarayanan B. Exploring the limits of out-of-distribution detection. In: Advances in Neural Information Processing Systems 2021
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.
Hendrycks D, Gimpel K. A baseline for detecting misclassified and out-of-distribution examples in neural networks. In: International Conference on Learning Representations 2017.
Hendrycks D, Mazeika M, Dietterich T. Deep anomaly detection with outlier exposure. In: International Conference on Learning Representations 2019.
Kemmler M, Rodner E, Wacker ES, Denzler J. One-class classification with gaussian processes. Pattern Recogn. 2013;46(12):3507–18.
Khan SS, Madden MG. One-class classification: taxonomy of study and review of techniques. Knowl Eng Rev. 2014;29(3):345–74.
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.
Koner R, Sinhamahapatra P, Roscher K, Günnemann S, Tresp V. Oodformer: Out-of-distribution detection transformer. arXiv preprint arXiv:2107.08976 2021.
Krizhevsky A, Hinton G, et al. Learning multiple layers of features from tiny images 2009.
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.
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.
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.
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.
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.
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.
Perera P, Patel VM. Learning deep features for one-class classification. IEEE Trans Image Process. 2019;28(11):5450–63.
Roerdink JB, Meijster A. The watershed transform: Definitions, algorithms and parallelization strategies. Fund Inform. 2000;41(1, 2):187–228.
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.
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.
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.
Xiao Y, Wang H, Xu W, Zhou J. Robust one-class svm for fault detection. Chemom Intell Lab Syst. 2016;151:15–25.
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
Zenati H, Foo CS, Lecouat B, Manek G, Chandrasekhar VR. Efficient gan-based anomaly detection. arXiv 2018.
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.
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.
Author information
Authors and Affiliations
Corresponding author
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.
About this article
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
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s42979-023-01765-6