HAL will be down for maintenance from Friday, June 10 at 4pm through Monday, June 13 at 9am. More information
Skip to Main content Skip to Navigation
Journal articles

Leveraging EBSD data by deep learning for bainite, ferrite and martensite segmentation

Abstract : A U-Net model was trained to perform the segmentation of bainite, ferrite and martensite on EBSD maps using the kernel average misorientation and the pattern quality index as input. The manual labeling work was eased by introducing an "unknown" phase that is ignored by the model during training. The influence of providing maps with different acquisition steps, indexation quality and phase content to the model during training was investigated to demonstrate the importance of training the model with a wide range of configurations. The model can differentiate the three phases with an 92% mean accuracy. An additional channel containing the map acquisition step was provided to the model and helped it generalize to various EBSD acquisition steps.
Complete list of metadata

Contributor : Nathalie Gey Connect in order to contact the contributor
Submitted on : Sunday, March 6, 2022 - 9:23:13 PM
Last modification on : Wednesday, March 9, 2022 - 3:34:27 AM


 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2022-08-22

Please log in to resquest access to the document


Distributed under a Creative Commons Attribution - NonCommercial - NoDerivatives 4.0 International License



S. Breumier, T. Martinez Ostormujof, B. Frincu, Nathalie Gey, A. Couturier, et al.. Leveraging EBSD data by deep learning for bainite, ferrite and martensite segmentation. Materials Characterization, Elsevier, 2022, 186, pp.111805. ⟨10.1016/j.matchar.2022.111805⟩. ⟨hal-03480629v2⟩



Record views