Abstract
The printed circuit board (PCB) is one of the important components in the electronic industry. Among them, Establishing Pre-reflow PCB defect detection before reflow soldering is critical to PCB production quality guarantee. More than a dozen different algorithms should be adopted to successively inspect various defects in different types of elements in existing Pre-reflow printed circuit board (PCB) defect detection systems. This may complicate the corresponding detection process as well as reduce the robustness of detection systems. To address the shortcomings of currently utilised detection systems, a deep learning-based object detection algorithm is combined with the traditional template matching approach to put forward an efficient Pre-reflow PCB defect detection method. The proposed method possesses a rather strong feature learning capability. By establishing the corresponding mathematical model, it can precisely identify a specific defect type, thus realising synchronous detection of elements and defects of diverse types. The improved CentreNet model has a detection speed of 102 FPS when targeting relevant datasets, and its detection precision index AP75 reaches 97.1, which is 0.6 higher than the original model. Subsequently, dichotomous and eight-category tests were performed to validate the proposed Pre-reflow PCB defect detection method. It turns out that the accuracy of this method is up to 98.6% in dichotomous tests but 95.3% in eight-category tests. Therefore, it is sufficiently proved by relevant experimental results that the proposed method has the capability of detecting different types of defects in a variety of elements synchronously.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dan, L., Chengfang, Y.: Application of Genetic Algorithm in PCB Component Detection. Fudan J. 45(4), Natural Science edn, 452–456 (2006)
Liao, C.-T., Lee, W.-H., Lai, S.-H.: A flexible PCB inspection system based on statistical learning. J. Sign. Process. Syst. 67(3), 279–290 (2012)
Ajaib, A., Hussain, A.: Weighted CBMO estimates for commutators of matrix Hausdorff operator on the Heisenberg group. Open Math. 18(1), 496–511 (2020)
Hsieh, C-J., Chang, K-W., Lin, C-J., et al.: A dual coordinate descent method for large-scale linear SVM. In: Proceedings of the 25th International Conference on Machine Learning (ICML’08), pp. 408–415 (2008). https://doi.org/10.1145/1390156.1390208
Dongming, Y.: Research on PCB patch defect detection before furnace based on vision and neural network [D]. Huazhong University of Science and Technology (2020)
Zhou, X., Wang, D., Krähenbühl, P.: Objects as points. ar**v:1904.07850 (ar**v:1904.07850v2) (2019). https://doi.org/10.48550/ar**v.1904.07850
Hinton, G., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. ar**v:1503.02531 (ar**v:1503.02531v1) (2015). https://doi.org/10.48550/ar**v.1503.02531
Chen, G., Choi, W., Yu, X., et al.: Learning efficient object detection models with knowledge distillation. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS 2017), pp. 742–751 (2017)
Ranjan, R., Castillo, C.D., Chellappa, R.: L2-constrained softmax loss for discriminative face verification. ar**v:1703.09507 (ar**v:1703.09507v3). (2017). https://doi.org/10.48550/ar**v.1703.09507
Kumar, A., Shaikh, A.M., Li, Y., Bilal, H., Yin, B.: Pruning filters with L1-norm and capped L1-norm for CNN compression. Appl. Intell. 51(2), 1152–1160 (2020). https://doi.org/10.1007/s10489-020-01894-y
Ling, Y.: Electronic Assembly Defect Detection Based on Digital Image Processing Technology. **dian University, **’an (2010)
**g, F.: Analysis of SMT surface mount technology. Electron. World, pp. 174–175 (2018)
Völp, A.R., Fessler, F., Reiner, J., et al.: High throughput object recognition and sizing in disperse systems using an image processing tool based on template matching. Chem. Eng. Technol. 43(9), 1897–1902 (2020)
He, K., Zhang, X., Ren, S., et al.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016)
Yu, F., Wang, D., Shelhamer, E., et al.: Deep layer aggregation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR),pp. 2403–2412 (2018)
Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Computer Vision – ECCV 2016. Lecture Notes in Computer Science, vol. 9912. Springer, Cham. https://doi.org/10.1007/978-3-319-46484-8_29
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. ar**v:1804.02767 (ar**v:1804.02767v1) (2018). https://doi.org/10.48550/ar**v.1804.02767
Lin, T-Y., Goyal, P., Girshick, R., et al.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2980–2988 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Yang, Y., Guo, H., Fu, X. (2023). On Pre-reflow PCB Defect Detection Based on Object Detection and Template Matching. In: Dong, J., Zhang, L. (eds) Proceedings of the International Conference on Internet of Things, Communication and Intelligent Technology . IoTCIT 2022. Lecture Notes in Electrical Engineering, vol 1015. Springer, Singapore. https://doi.org/10.1007/978-981-99-0416-7_63
Download citation
DOI: https://doi.org/10.1007/978-981-99-0416-7_63
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0415-0
Online ISBN: 978-981-99-0416-7
eBook Packages: EngineeringEngineering (R0)