Number of the records: 1
Deep learning of crystalline defects from TEM images: a solution for the problem of 'never enough training data'
- 1.
SYSNO ASEP 0581983 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Deep learning of crystalline defects from TEM images: a solution for the problem of 'never enough training data' Author(s) Govind, K. (DE)
Oliveros, D. (FR)
Dlouhý, Antonín (UFM-A) RID, ORCID
Legros, M. (FR)
Sandfeld, S. (DE)Number of authors 5 Article number 015006 Source Title MACHINE LEARNING-SCIENCE AND TECHNOLOGY
Roč. 5, č. 1 (2024)Number of pages 22 s. Language eng - English Country GB - United Kingdom Keywords situ ; insights ; deep learning ; synthetic training data ; segmentation ; data mining ; transmission electron microscopy ; dislocation ; crystal defect Subject RIV IN - Informatics, Computer Science OECD category Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8) Method of publishing Open access Institutional support UFM-A - RVO:68081723 UT WOS 001142818000001 EID SCOPUS 85182737745 DOI 10.1088/2632-2153/ad1a4e Annotation Crystalline defects, such as line-like dislocations, play an important role for the performance and reliability of many metallic devices. Their interaction and evolution still poses a multitude of open questions to materials science and materials physics. In-situ transmission electron microscopy (TEM) experiments can provide important insights into how dislocations behave and move. The analysis of individual video frames from such experiments can provide useful insights but is limited by the capabilities of automated identification, digitization, and quantitative extraction of the dislocations as curved objects. The vast amount of data also makes manual annotation very time consuming, thereby limiting the use of deep learning (DL)-based, automated image analysis and segmentation of the dislocation microstructure. In this work, a parametric model for generating synthetic training data for segmentation of dislocations is developed. Even though domain scientists might dismiss synthetic images as artificial, our findings show that they can result in superior performance. Additionally, we propose an enhanced DL method optimized for segmenting overlapping or intersecting dislocation lines. Upon testing this framework on four distinct real datasets, we find that a model trained only on synthetic training data can also yield high-quality results on real images-even more so if the model is further fine-tuned on a few real images. Our approach demonstrates the potential of synthetic data in overcoming the limitations of manual annotation of TEM image data of dislocation microstructure, paving the way for more efficient and accurate analysis of dislocation microstructures. Last but not least, segmenting such thin, curvilinear structures is a task that is ubiquitous in many fields, which makes our method a potential candidate for other applications as well. Workplace Institute of Physics of Materials Contact Yvonna Šrámková, sramkova@ipm.cz, Tel.: 532 290 485 Year of Publishing 2025 Electronic address https://iopscience.iop.org/article/10.1088/2632-2153/ad1a4e
Number of the records: 1