| About this Abstract |
| Meeting |
2020 TMS Annual Meeting & Exhibition
|
| Symposium
|
Characterization: Structural Descriptors, Data-Intensive Techniques, and Uncertainty Quantification
|
| Presentation Title |
Machine Learning Approaches to Image Segmentation of Large Materials Science Datasets |
| Author(s) |
Tiberiu Stan, Zachary Thompson, Bo Lei, Elizabeth Holm, Peter Voorhees |
| On-Site Speaker (Planned) |
Tiberiu Stan |
| Abstract Scope |
Modern imaging techniques generate an increasing amount of data that must be accurately analyzed to extract materials parameters. We have trained a variety of machine learning convolutional neural network (NN) architectures to perform semantic segmentation of large materials science datasets such as x-ray computed tomography, serial sectioning optical microscopy, and scanning electron microscopy. The images contain diverse microstructural features, length scales, and artifacts which make segmentation challenging. Many NN architectures have fundamentally different encoder and decoder networks, thus some architectures perform better on certain datasets than others. Ways to increase NN performance using limited training data, general best practice NN training methods, and NN transferability are discussed. Fully trained NNs can accurately segment images nearly 1000 times faster than humans and sematic segmentation is becoming a powerful tool for analysis of large datasets. |
| Proceedings Inclusion? |
Planned: Supplemental Proceedings volume |