Abstract
We propose instance segmentation as a useful tool for image analysis in materials science. Instance segmentation is an advanced technique in computer vision which generates individual segmentation masks for every object of interest that is recognized in an image. Using an out-of-the-box implementation of Mask R-CNN, instance segmentation is applied to images of metal powder particles produced through gas atomization. Leveraging transfer learning allows for the analysis to be conducted with a very small training set of labeled images. As well as providing another method for measuring the particle size distribution, we demonstrate the first direct measurements of the satellite content in powder samples. After analyzing the results for the labeled data dataset, the trained model was used to generate measurements for a much larger set of unlabeled images. The resulting particle size measurements showed reasonable agreement with laser scattering measurements. The satellite measurements were self-consistent and showed good agreement with the expected trends for different samples. Finally, we present a small case study showing how instance segmentation can be used to measure spheroidite content in the UltraHigh Carbon Steel DataBase, demonstrating the flexibility of the technique.
Similar content being viewed by others
References
K. Song and Y. Yan, Appl. Surf. Sci. 285, 858 (2013). https://doi.org/10.1016/J.APSUSC.2013.09.002.
A.R. Kitahara and E.A. Holm, Integr. Mater. Manuf. Innov. 7(3), 148 (2018). https://doi.org/10.1007/s40192-018-0116-9.
W. Li, K.G. Field, and D. Morgan, NPJ Comput. Mater. 4(1), 1 (2018). https://doi.org/10.1038/s41524-018-0093-8.
L. Scime and J. Beuth, Addit. Manuf. 19, 114 (2018). https://doi.org/10.1016/j.addma.2017.11.009.
L. Tan Phuc and M. Seita, Mater. Des. 164, 107562 (2019). https://doi.org/10.1016/J.MATDES.2018.107562.
B.L. DeCost and E.A. Holm, Comput. Mater. Sci. 126, 438 (2017). https://doi.org/10.1016/J.COMMATSCI.2016.08.038.
B.L. DeCost, B. Lei, T. Francis, and E.A. Holm, Microsc. Microanal. 25, 1 (2019). https://doi.org/10.1017/S1431927618015635.
Z. Chen and S. Daly, Mater. Sci. Eng. A 736, 61 (2018). https://doi.org/10.1016/j.msea.2018.08.083.
T. Stan, Z.T. Thompson, and P.W. Voorhees, Mater. Charact. 160, 110119 (2020). https://doi.org/10.1016/j.matchar.2020.110119.
C. Kusche, T. Reclik, M. Freund, T. Al-Samman, U. Kerzel, and S. Korte-Kerzel, PLoS ONE 14(5), e0216493 (2019). https://doi.org/10.1371/journal.pone.0216493.
F. Ram, S. Wright, S. Singh, and M. De Graef, Ultramicroscopy 181, 17 (2017). https://doi.org/10.1016/j.ultramic.2017.04.016.
A. Ziletti, D. Kumar, M. Scheffler, and L.M. Ghiringhelli, Nat. Commun. 9, 1 (2018). https://doi.org/10.1038/s41467-018-05169-6.
A. Campbell, P. Murray, E. Yakushina, S. Marshall, and W. Ion, Mater. Des. 141, 395 (2018). https://doi.org/10.1016/J.MATDES.2017.12.049.
W. Rawat and Z. Wang, in Proceedings of the 18th International Conference on Artificial Intelligence and Statistics (2017). https://doi.org/10.1162/NECO_a_00990.
S.A. Taghanaki, K. Abhishek, J.P. Cohen, J. Cohen-Adad, and G. Hamarneh (2019). arXiv:1910.07655.
Z.Q. Zhao, P. Zheng, S.T. Xu, and X. Wu, IEEE Trans. Neural Netw. Learn. Syst. 30(11), 3212 (2019). https://doi.org/10.1109/TNNLS.2018.2876865.
T.Y. Lin, M. Maire, S. Belongie, L. Bourdev, R. Girshick, J. Hays, P. Perona, D. Ramanan, C.L. Zitnick, and P. Dollár, Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recogn. (2015). https://doi.org/10.1109/CVPR.2014.471.
K. He, G. Gkioxari, P. Dollár, and R. Girshick (2017). arXiv:1703.06870.
S. Ren, K. He, R. Girshick, and J. Sun (2015). arXiv:1506.01497.
I.E. Anderson, E.M. White, and R. Dehoff, Curr. Opin. Solid State Mater. Sci. 22(1), 8 (2018). https://doi.org/10.1016/J.COSSMS.2018.01.002.
J. Clayton, D. Millington-Smith, and B. Armstrong, JOM 67(3), 544 (2015). https://doi.org/10.1007/s11837-015-1293-z.
P. Sun, Z.Z. Fang, Y. Zhang, and Y. Xia, JOM 69(10), 1853 (2017). https://doi.org/10.1007/s11837-017-2513-5.
A. Dutta and A. Zisserman, in Proceedings of the 27th ACM International Conference on Multimedia (ACM, New York, NY, USA, 2019), MM ’19. https://doi.org/10.1145/3343031.3350535.
A. Dutta, A. Gupta, and A. Zissermann. VGG Image Annotator (VIA) (2016). http://www.robots.ox.ac.uk/~vgg/software/via/. Accessed 24 May 2021.
R. Girshick, arXiv (2015). arXiv:1504.08083.
R. Girshick, J. Donahue, T. Darrell, and J. Malik (2013). arXiv:1311.2524.
Y. Wu, A. Kirillov, F. Massa, W.Y. Lo, and R. Girshick. Detectron2 (2019). https://github.com/facebookresearch/detectron2. Accessed 24 May 2021.
L. Taylor and G. Nitschke, arXiv (2017). arXiv:1708.06020.
S.P. Narra, Z. Wu, R. Patel, J. Capone, M. Paliwal, J. Beuth, and A. Rollett, Addit. Manuf. 34, 101188 (2020). https://doi.org/10.1016/j.addma.2020.101188.
B.L. DeCost and E.A. Holm, Data Brief 9, 727 (2016). https://doi.org/10.1016/J.DIB.2016.10.011.
M.D. Hecht, B.A. Webler, and Y.N. Picard, Mater. Charact. 117, 134 (2016). https://doi.org/10.1016/j.matchar.2016.04.012.
B.L. DeCost, M.D. Hecht, T. Francis, B.A. Webler, Y.N. Picard, and E.A. Holm, Integr. Mater. Manuf. Innov. 6(2), 197 (2017). https://doi.org/10.1007/s40192-017-0097-0.
B. DeCost, M. Hecht, T. Sibley, T. Francis, B. Webler, Y. Picard, and E. Holm, Ultrahigh Carbon Steel Microconstituent Annotations (2018). https://materialsdata.nist.gov/handle/11256/964?show=full. Accessed 24 May 2021.
Acknowledgements
This work was supported by the National Science Foundation under Grant CMMI-1826218 and by the Air Force Research Laboratory under Cooperative Agreement No. FA8650-19-2-5209.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Disclaimer
The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the Air Force Research Laboratory or the U.S. Government.
Conflict of interests
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Cohn, R., Anderson, I., Prost, T. et al. Instance Segmentation for Direct Measurements of Satellites in Metal Powders and Automated Microstructural Characterization from Image Data. JOM 73, 2159–2172 (2021). https://doi.org/10.1007/s11837-021-04713-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11837-021-04713-y