Deep Learning Method for Wafer Flaw Detection in Lab-level Photolithography

Authors

Subin Lee
Daegu Catholic University image/svg+xml
Kyunghan Chun
Daegu Catholic University image/svg+xml
DOI: https://doi.org/10.52549/ijeei.v14i2.7975
Download PDF
Published: 30-06-2026 • Issue: Vol. 14 No. 2: June 2026 • Section: Regular paper

Abstract

In this paper, we propose a deep learning-based method for wafer flaw detection and classification in lab-label photolithography, known as a core step of the semiconductor manufacturing process. In photolithography, defects due to particles or process errors are critical to product yield and reliability. To detect these flaws, images were collected and efficientnet deep learning method was applied. Data augmentation and model lightweighting techniques were also applied to improve the limitations of the dataset. experimental results showed the relation between model complexity and the amount of training data. For EfficientNetB5, the massive architecture, caused the overfitting problem because of learning even noise in small datasets. But EfficientNetB0, the lightweight model, with batch normalization and early stopping techniques shows improvement of the reliability. In conclusion, this study provides practical guidelines for building and efficient flaw detection method in a data-limited research environment.
Keywords: Photolithography; Wafer Defect Detection; EfficientNet; Transfer Learning; Data Imbalance; Small Dataset Learning

References

S. He, G. A. Wang, M. Zhang, and D. F. Cook, “Multivariate process monitoring and fault identification using multiple decision tree classifiers,†International Journal of Production Research, vol. 51, no. 11, pp. 3355–3371, 2013.

Q. P. He and J. Wang, “Fault detection using the k-nearest neighbor rule for semiconductor manufacturing processes,†IEEE Transactions on Semiconductor Manufacturing, vol. 20, no. 4, pp. 345–354, Nov. 2007.

G. Verdier and A. Ferreira, “Adaptive mahalanobis distance and k-nearest neighbor rule for fault detection in semiconductor manufacturing,†IEEE Transactions on Semiconductor Manufacturing, vol. 24, no. 1, pp. 59–68, Feb. 2011.

R. Baly and H. Hajj, “Wafer classification using support vector machines,†IEEE Transactions on Semiconductor Manufacturing, vol. 25, no. 3, pp. 373–383, Aug. 2012.

J. Kwak, T. Lee, and C. O. Kim, “An incremental clustering-based fault detection algorithm for class-imbalanced process data,†IEEE Transactions on Semiconductor Manufacturing, vol. 28, no. 3, pp. 318–328, Aug. 2015.

H. Yang, Y. Lin, B. Yu, and E. F. Y. Young, “Lithography hotspot detection: From shallow to deep learning,†30th IEEE International System-on-Chip Conference, pp. 233–238, 2017.

K. Kyeong and H. Kim, “Classification of mixed-type defect patterns in wafer bin maps using convolutional neural networks,†IEEE Transactions on Semiconductor Manufacturing, vol. 31, no. 3, pp. 395–402, 2018.

S. Cheon, H. Lee, C. O. Kim, and S. H. Lee, “Convolutional neural network for wafer surface defect classifcation and the detection of unknown defect class,†IEEE Transactions on Semiconductor Manufacturing, vol. 32, pp. 163–170, 5 2019.

Y. Nam, M.-C. Kang, K. Kim, J. Hong, S. Lee, and D.-N. Kim, “Adversarial defect detection in semiconductor manufacturing process,†IEEE Transactions on Semiconductor Manufacturing, vol. 34, no. 3, pp. 365–371, 2021.

B. Dey, E. Dehaerne, K. Khalil, S. Halder, P. Leray, and M. A. Bayoumi, “Deep learning based defect classification and detection in SEM images: A Mask R-CNN approach,†arXiv preprint arXiv:2211.02185, 2022.

S. Choi, Q. Xie, N. Greeneltch, H. J. Lee, M. Govindaraj, S. Jayaram, M. Pereira, S. Biswas, S. Bhamidipati, and I. Torunoglu, “Fast and accurate automatic wafer defect detection and classification using machine learning-based SEM image analysis,†Proceedings of the SPIE, vol. 12955, Metrology, Inspection, and Process Control XXXVIII, 129553M, Apr. 2024.

How to Cite

[1]
S. Lee and K. Chun, “Deep Learning Method for Wafer Flaw Detection in Lab-level Photolithography”, IJEEI, vol. 14, no. 2, pp. 582–594, Jun. 2026, doi: 10.52549/ijeei.v14i2.7975.