Dresden 2026 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

TUT: Tutorien

TUT 3: Tutorial: Machine Learning Use Cases in Materials Science (joint session AKPIK/TUT)

TUT 3.4: Tutorium

Sonntag, 8. März 2026, 17:35–18:15, HSZ/0003

Machine Learning-based Analysis of Electron Microscopy Images: Segmentation — •Amir Omidvarnia — Forschungszentrum Jülich, Jülich, Germany

The second session focuses on segmentation of EM images using modern deep-learning architectures. Through a step-by-step Jupyter Notebook demonstration, the tutorial walks through the training and evaluation of a U-Net style segmentation model. Participants will see real examples of common challenges in EM segmentation, such as low contrast, overlapping nanoscale structures, and label ambiguity. By the end of the session, attendees will have an implementation-oriented understanding of how segmentation pipelines are built and validated in practice.

Keywords: Image processing; Machine learning; Segmenttaion; Edge detection; Electron microscopy