motif-learn 0.1.2

Zernike feature representation and manifold learning of scanning transmission electron microscopy images

motif-learn: machine learning in scanning transmission electron microscopy

Welcome to motif-learn, a Python package designed to apply machine learning techniques to scanning transmission electron microscopy (STEM) data. This tool enables researchers to identify and analyze structural motifs in atomic resolution images efficiently, offering a powerful way to explore materials with defects.

Installation🛠️

pip install motif-learn

To install the latest development version directly from GitHub:

pip install git+https://github.com/jiadongdan/motif-learn.git

How to use motif-learn👨‍🏫

• 📘Introduction to Zernike polynimials.
• 🔧How to use ZPs?
• 🔷How to extract symmetry information using zmoments?
• 🧩How to automatically estimate patch size from image?

License⚖️

motif-learn is licensed under the MIT License. For more details, see the LICENSE file.

Citation📜

If you find this project useful, please cite:

Dan, Jiadong, Xiaoxu Zhao, Shoucong Ning, Jiong Lu, Kian Ping Loh, Qian He, N. Duane Loh, and Stephen J. Pennycook. "Learning motifs and their hierarchies in atomic resolution microscopy." Science Advances 8, no. 15 (2022): eabk1005. 📄[paper]

Dan, Jiadong, Cheng Zhang, Xiaoxu Zhao and N. Duane Loh. " Symmetry quantification and segmentation in STEM imaging through Zernike moments." Chinese Physics B, (2024). 📄[paper]