Automatic detection of grains in partially recrystallized microstructures using deep learning

Fengxiang Lin*, Haixing Fang, Hong Liu, Yubin Zhang, Dorte Juul Jensen*, Emil Hovad

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

18 Downloads (Pure)

Abstract

Precise identification of recrystallizing grains in partially recrystallized microstructures is essential to obtain quantitative information regarding the recrystallization process. Automatic, robust, user-friendly, and unbiased identification methods that do not rely on hard-coded, preselected values would be highly advantageous. In this study, we test convolutional neural network instance segmentation models to achieve automatic segmentation of individual recrystallizing grains in partially recrystallized microstructures. Our training dataset includes micrographs obtained using electron backscattered diffraction from five alloys with different thermal-mechanical histories and more than 100,000 recrystallizing grains. We adapt and train two state of the art deep learning models, namely Mask R-CNN and PointRend. Both models provide instance segmentation results of good quality, enabling quantitative determination of the microstructural parameters. The PointRend model demonstrates better performance for grains with irregular shapes than Mask R-CNN. Compared to conventional methods, the trained deep learning approach is easier to use, more flexible, and applicable to a wide range of materials.

Original languageEnglish
Article number114576
JournalMaterials Characterization
Volume219
Number of pages15
ISSN1044-5803
DOIs
Publication statusPublished - 2025

Keywords

  • Computer vision
  • Convolutional neural network
  • Deep learning
  • EBSD
  • Instance segmentation
  • Microstructure
  • Recrystallization

Fingerprint

Dive into the research topics of 'Automatic detection of grains in partially recrystallized microstructures using deep learning'. Together they form a unique fingerprint.

Cite this