Deep Learning for Electron Microscopy

About

I am YESP member Dr.-Ing. Bashir Kazimi and currently working as a research group leader at the Institute for Materials Data Science and Informatics (IAS-9) led Prof. Dr. Stefan Sandfeld.

Our group specializes in the development and application of techniques in deep learning and computer vision for electron microscopy tasks. We tackle challenges such as denoising, resolution enhancement, representation learning, super-resolution, semantic and instance segmentation, as well as tracking. These techniques find application in various electron microscopy tasks, including nanomaterial characterization, crystallographic defect identification, dislocation detection and tracking, and orientation mapping. Leveraging the power of deep learning and computer vision, we aim to advance the analysis and interpretation of electron microscopy data in materials science and related fields.

We conduct our work in close collaboration with our partners at the Ernst-Ruska-Center (ER-C) who are experts in electron microscopy.

Research Topics

Deep Learning
Computer Vision
Electron Microscopy Image Analysis

Contact

Dr.-Ing. Bashir Kazimi

IAS-9

Building TZA-Aachen / Room D1.21

+49 241/927803-38

E-Mail

Research Topics

Self Supervised Learning of Electron Microscopy Images

This research focuses on leveraging image-to-image translation Generative Adversarial Networks (GANs) for self-supervised learning of electron microscopy (EM) images.

More

Semantic Segmentation of Nanoparticles in HRTEM Images

This research project is dedicated to the precise semantic segmentation of nanoparticles in high-resolution transmission electron microscopy (TEM) images.

More

Denoising, Background Removal and Super-Resolution in TEM Images

In this project, we leverage deep learning and computer vision methods to address key challenges in transmission electron microscopy (TEM) image processing.

More

This research focuses on leveraging image-to-image translation Generative Adversarial Networks (GANs) for self-supervised learning of electron microscopy (EM) images.

More

News

Events

Publications

Mirza, A., Yang, L., Chandran, A.K., Östreicher, J., Bompas, S., Kazimi, B., Kesselheim, S., Friederich, P., Sandfeld, S. and Jablonka, K.M., 2025. MatBind: Probing the multimodality of materials science with contrastive learning. In: AI for Accelerated Materials Design - ICLR 2025. [online] Available at: https://openreview.net/forum?id=ZG0MBXi55v

Kazimi, B. and Sandfeld, S., 2024. Enhancing semantic segmentation in high-resolution TEM images: A comparative study of batch normalization and instance normalization. Microscopy and Microanalysis. (Accepted for publication).

Kazimi, B., Ruzaeva, K. and Sandfeld, S., 2024. Self-supervised learning with generative adversarial networks for electron microscopy. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp.71–81.

Lopes Marinho, A., Kazimi, B., Ćwieka, H., Marek, R., Beckmann, F., Willumeit-Römer, R., Moosmann, J. and Zeller-Plumhoff, B., 2024. A comparison of deep learning segmentation models for synchrotron radiation based tomograms of biodegradable bone implants. Frontiers in Physics, 12, p.1257512.

More pulications (JuSER)

Last Modified: 15.05.2025

YESP-Member