Inspection of Solder Mask Defects Using Vision Transformers to Improve Manufacturing
Abstract
O controle de qualidade é vital na fabricação moderna. Este artigo aborda a inspeção de chips GSM durante a soldagem em substratos de PCB. Propomos um método baseado em Vision Transformers, que utiliza a autoatenção para aprender características visuais espaciais e hierárquicas. Nossa abordagem alcançou 95,83% de precisão em experimentos reais e simulados. Mesmo sob ruído e desfoque, a precisão permaneceu alta: 94,94% (Sal & Pimenta) e 94,17% (Gaussiano). Os resultados confirmam a robustez e o potencial industrial do método.References
Al Radi, M., Li, P., Karki, H., Werghi, N., Javed, S., and Dias, J. (2023). Multi-view inspection of flare stacks operation using a vision-controlled autonomous uav. In IECON 2023-49th Annual Conference of the IEEE Industrial Electronics Society, pages 1–6.
Beuth, F., Schlosser, T., Friedrich, M., and Kowerko, D. (2020). Improving automated visual fault detection by combining a biologically plausible model of visual attention with deep learning. In IECON 2020 The 46th Annual Conf. of the IEEE Industrial Elect. Soc., pages 5323–5330.
Dong, X., Taylor, C. J., and Cootes, T. F. (2018). Small defect detection using convolutional neural network features and random forests. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pages 0–0.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale.
Heng, P. Y. (2022). Detection of defect regions in solder mask peel off images using you-only-look-once convolutional neural network.
Hida, Y., Makariou, S., and Kobayashi, S. (2021). Smart image inspection using defect-removing autoencoder. Proc. CIRP, 104:559–564.
Iglesias, B. P., Otani, M., and Oliveira, F. G. (2021). Glue level estimation through automatic visual inspection in pcb manufacturing. In ICINCO, pages 731–738.
Kumaresan, S., Aultrin, K. J., Kumar, S., and Anand, M. D. (2021). Transfer learning with cnn for classification of weld defect. Ieee Access, 9:95097–95108.
Rocha, C. S., Menezes, M. A., and Oliveira, F. G. (2016). Detecção automática de micro-componentes smt ausentes em placas de circuito impresso. In Workshop on Industry Applications (WIA) in the 29th Conference on Graphics, Patterns and Images (SIBGRAPI 2016), São José dos Campos, Sp, Brazil, volume 1.
Silva, C. N., Ferreira, N. P., Meireles, S. S., Otani, M., da Silva, V. J., de Freitas, C. A. O., and Oliveira, F. G. (2022a). The visual inspection of solder balls in semiconductor encapsulation. In ICINCO, pages 750–757.
Silva, D., Lopes, A. P., Costa, D., Cabral, J., Silva, C. A., and Lopes, S. (2022b). A dataflow execution engine for automatic visual inspection of production lines. In IECON 2022 – 48th Annual Conf. of the IEEE Industrial Elect. Society, pages 1–6.
Swathi, G., Reddy B, R., Reddy M, A., and Kumar, R. P. (2023). Automated printed circuit board inspection: Incorporating yolov8 for efficient defect detection. In 2023 6th Int. Conf. on Recent Trends in Advance Computing (ICRTAC), pages 742–747.
Wang, Y.-C. Z., Huang, P.-W., and Wang, F.-C. (2023). Bubble object witness inspection equipment - a machine vision based bubble inspection device for petroleum industry. In IECON 2023-49th Annual Conf. of the IEEE Industrial Elect. Society, pages 1–4.
Wu, H., Lei, R., and Peng, Y. (2022). Pcbnet: A lightweight convolutional neural network for defect inspection in surface mount technology. IEEE Trans. on Instrumentation and Measurement, 71:1–14.
Zhang, Q., Zhang, M., Gamanayake, C., Yuen, C., Geng, Z., Jayasekara, H., Woo, C.-w., Low, J., Liu, X., and Guan, Y. L. (2022). Deep learning based solder joint defect detection on industrial printed circuit board x-ray images. Complex amp; Int. Systems, 8(2):1525–1537.
Beuth, F., Schlosser, T., Friedrich, M., and Kowerko, D. (2020). Improving automated visual fault detection by combining a biologically plausible model of visual attention with deep learning. In IECON 2020 The 46th Annual Conf. of the IEEE Industrial Elect. Soc., pages 5323–5330.
Dong, X., Taylor, C. J., and Cootes, T. F. (2018). Small defect detection using convolutional neural network features and random forests. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, pages 0–0.
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., and Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale.
Heng, P. Y. (2022). Detection of defect regions in solder mask peel off images using you-only-look-once convolutional neural network.
Hida, Y., Makariou, S., and Kobayashi, S. (2021). Smart image inspection using defect-removing autoencoder. Proc. CIRP, 104:559–564.
Iglesias, B. P., Otani, M., and Oliveira, F. G. (2021). Glue level estimation through automatic visual inspection in pcb manufacturing. In ICINCO, pages 731–738.
Kumaresan, S., Aultrin, K. J., Kumar, S., and Anand, M. D. (2021). Transfer learning with cnn for classification of weld defect. Ieee Access, 9:95097–95108.
Rocha, C. S., Menezes, M. A., and Oliveira, F. G. (2016). Detecção automática de micro-componentes smt ausentes em placas de circuito impresso. In Workshop on Industry Applications (WIA) in the 29th Conference on Graphics, Patterns and Images (SIBGRAPI 2016), São José dos Campos, Sp, Brazil, volume 1.
Silva, C. N., Ferreira, N. P., Meireles, S. S., Otani, M., da Silva, V. J., de Freitas, C. A. O., and Oliveira, F. G. (2022a). The visual inspection of solder balls in semiconductor encapsulation. In ICINCO, pages 750–757.
Silva, D., Lopes, A. P., Costa, D., Cabral, J., Silva, C. A., and Lopes, S. (2022b). A dataflow execution engine for automatic visual inspection of production lines. In IECON 2022 – 48th Annual Conf. of the IEEE Industrial Elect. Society, pages 1–6.
Swathi, G., Reddy B, R., Reddy M, A., and Kumar, R. P. (2023). Automated printed circuit board inspection: Incorporating yolov8 for efficient defect detection. In 2023 6th Int. Conf. on Recent Trends in Advance Computing (ICRTAC), pages 742–747.
Wang, Y.-C. Z., Huang, P.-W., and Wang, F.-C. (2023). Bubble object witness inspection equipment - a machine vision based bubble inspection device for petroleum industry. In IECON 2023-49th Annual Conf. of the IEEE Industrial Elect. Society, pages 1–4.
Wu, H., Lei, R., and Peng, Y. (2022). Pcbnet: A lightweight convolutional neural network for defect inspection in surface mount technology. IEEE Trans. on Instrumentation and Measurement, 71:1–14.
Zhang, Q., Zhang, M., Gamanayake, C., Yuen, C., Geng, Z., Jayasekara, H., Woo, C.-w., Low, J., Liu, X., and Guan, Y. L. (2022). Deep learning based solder joint defect detection on industrial printed circuit board x-ray images. Complex amp; Int. Systems, 8(2):1525–1537.
Published
2025-07-01
How to Cite
VIANA, Walter Jonas de S.; OLIVEIRA, Felipe Gomes de.
Inspection of Solder Mask Defects Using Vision Transformers to Improve Manufacturing. In: ICET TECHNOLOGY CONFERENCE (CONNECTECH), 2. , 2025, Itacoatiara/AM.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2025
.
p. 249-256.
DOI: https://doi.org/10.5753/connect.2025.12341.
