AI-Guided Feature Segmentation Techniques to Model Features from Single Crystal Diamond Growth

Abstract:

Improving diamond growth to achieve high-quality materials for applications like optics and quantum detectors is a key objective. Leveraging machine learning, especially with its challenges such as complex, time-dependent data features and the sheer data volume per growth cycle, presents a promising solution. The extraction of accurate spatial features from images for real-time diamond growth monitoring is challenging due to data's complex and sparse nature. This paper evaluates various feature extraction methods in diamond growth, introducing a novel deep learning approach for precise geometric feature segmentation. It utilizes a human-in-the-loop system for efficient data annotation, significantly cutting down labeling time and costs. Our approach, using the DeeplabV3plus model, showcases high efficiency in feature classification, with accuracies up to 96.31% for pocket holders, 98.60% for diamond tops, and 91.64% for sides, demonstrating deep learning's potential in handling complex dataset features effectively.

• Periodical: Key Engineering Materials (Volume 993)
• Pages: 67-74
• DOI: https://doi.org/10.4028/p-6bfVRH
• Online since: November 2024
• Authors: Rohan Reddy Mekala*, Elias Garratt, Matthias Muehle, Arjun Srinivasan, Adam Porter, Mikael Lindvall
• Keywords: Active Learning, AI in Material Science, Data Labeling, Deep Learning, Diamond Growth

References

[1] Y. LeCun, Y. Bengio, and G. Hinton, "Deep learning," nature 521, 436–444 (2015).

DOI: 10.1038/nature14539

[2] A. Garcia-Garcia, S. Orts-Escolano, S. Oprea, V. Villena-Martinez, and J. Garcia-Rodriguez, "A review on deep learning techniques applied to semantic segmentation," arXiv preprint arXiv:1704.06857 (2017).

DOI: 10.1016/j.asoc.2018.05.018

[3] G. Di Leo, C. Liguori, A. Pietrosanto, and P. Sommella, "A vision system for the online quality monitoring of industrial manufacturing," Optics and Lasers in Engineering 89, 162–168 (2017).

DOI: 10.1016/j.optlaseng.2016.05.007

[4] Pastor-López, I. Santos, A. Santamaría-Ibirika, M. Salazar, J. De-la Peña-Sordo, and P. G. Bringas, "Machine-learning-based surface defect detection and categorisation in high-precision foundry," in 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA) (IEEE, 2012) p.1359–1364.

DOI: 10.1109/iciea.2012.6360934

[5] A. M. Hafiz and G. M. Bhat, "A survey on instance segmentation: state of the art," International journal of multimedia information retrieval 9, 171–189 (2020).

DOI: 10.1007/s13735-020-00195-x

[6] S. M. Azimi, D. Britz, M. Engstler, M. Fritz, and F. Mücklich, "Advanced steel microstructural classification by deep learning methods," Scientific reports 8, 1–14 (2018).

DOI: 10.1038/s41598-018-20037-5

[7] D. Tabernik, S. Šela, J. Skvarˇc, and D. Skoˇcaj, "Segmentation-based deep learning approach for surface-defect detection," Journal of Intelligent Manufacturing 31, 759–776 (2020).

DOI: 10.1007/s10845-019-01476-x

[8] F. Silva, X. Bonnin, J. Achard, O. Brinza, A. Michau, and A. Gicquel, "Geometric modeling of homoepitaxial cvd diamond growth: I. the 100111110113 system," Journal of Crystal Growth 310, 187–203 (2008).

DOI: 10.1016/j.jcrysgro.2007.09.044

[9] I. Sunagawa, "Growth and morphology of diamond crystals under stable and metastable contitions," Journal of Crystal Growth 99, 1156–1161 (1990).

DOI: 10.1016/s0022-0248(08)80100-5

[10] Minaee, S., Boykov, Y., Porikli, F., Plaza, A., Kehtarnavaz, N., & Terzopoulos, D. (2021). Image segmentation using deep learning: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(7), 3523-3542.

DOI: 10.1109/tpami.2021.3059968

[11] M. Muehle, J. Asmussen, M. Becker, and T. Schuelke, "Extending microwave plasma assisted cvd scd growth to pressures of 400 torr," Diamond and Related Materials 79, 150–163 (2017).

DOI: 10.1016/j.diamond.2017.09.013

[12] K. Konyushkova, R. Sznitman, and P. Fua, "Learning active learning from data," Advances in neural information processing systems 30 (2017).

[13] "The leading training data platform for data labeling," Labelbox.

[14] M. Desmond, M. Muller, Z. Ashktorab, C. Dugan, E. Duesterwald, K. Brimijoin, C. Finegan-Dollak, M. Brachman, A. Sharma, N. N. Joshi,et al., "Increasing the speed and accuracy of data labeling through an ai assisted interface," in 26th International Conference on Intelligent User Interfaces (2021) p.392–401.

DOI: 10.1145/3397481.3450698

[15] S. Jadon, "A survey of loss functions for semantic segmentation," in 2020 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB) (IEEE, 2020) p.1–7.

DOI: 10.1109/cibcb48159.2020.9277638