A facile methodology to identify microstructural grains on etched surfaces using panoptic segmentation

Girerd, Thomas; Martínez-Arellano, Giovanna; Clare, Adam Thomas; Speidel, Alistair

Abstract

The advancement of manufacturing processes demands the deployment of new innovative solutions to control polycrystalline material microstructures in cheap, safe and rapid manner. Analysing polycrystalline microstructures requires grain segmentation, which is typically performed on image data or spatially resolved diffraction data collected from carefully prepared specimens. Recently, machine learning (ML) models have been developed to identify grain boundaries and defects from acquired image data. Despite existing ML-based methods showing an improvement over classical computational methods, there is still a significant structure error due to the necessity to have a high accuracy in detected boundaries to avoid grain misidentification. This investigation deploys a simple and open panoptic model, YOLO (You only look once), to directly identify grains from etched surfaces. The model performance was evaluated after appropriate data preparation and training. Even with a limited number of samples, the model outperformed computational methods like the Canny edge algorithm with an intersection-over-union (IoU) score 45 % higher and an aggregated Jaccard index score three times higher. Additionally, an index to measure segmentation quality was introduced, particularly suited for objects with a wide range of sizes, such as microstructural grains. By detecting grains directly instead of relying on boundary detection, common issues—such as failed grains reconstruction due to missing grain boundaries—are avoided, resulting in more accurate grain structures with reduced sensitivity to surface defects. The proposed approach offers significant potential for application to various materials and grain sizes, facilitating the detection of grains, defects, and microstructural artefacts.

Citation

Girerd, T., Martínez-Arellano, G., Clare, A. T., & Speidel, A. (2025). A facile methodology to identify microstructural grains on etched surfaces using panoptic segmentation. Materials Characterization, 227, Article 115224. https://doi.org/10.1016/j.matchar.2025.115224

• Journal Article Type: Article
• Acceptance Date: May 27, 2025
• Online Publication Date: May 28, 2025
• Publication Date: 2025-09
• Deposit Date: Jun 25, 2025
• Publicly Available Date: Jun 25, 2025
• Journal: Materials Characterization
• Print ISSN: 1044-5803
• Electronic ISSN: 1873-4189
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 227
• Article Number: 115224
• DOI: https://doi.org/10.1016/j.matchar.2025.115224
• Keywords: Optical microscopy, Machine learning, Panoptic segmentation, Microstructural analysis, Polarized light microscopy, Materials characterization
• Public URL: https://nottingham-repository.worktribe.com/output/50711884
• Publisher URL: https://www.sciencedirect.com/science/article/pii/S1044580325005133?via%3Dihub