Learning-based defect recognition for quasi-periodic HRSTEM images. (July 2021)

• Record Type: Journal Article
• Authors: Dennler, Nik; Foncubierta-Rodriguez, Antonio; Neupert, Titus; Sousa, Marilyne
• Is Part Of: Micron. Volume 146(2021)
• Publication Date: 2021-07
• Subjects: High-resolution scanning transmission electron microscopy -- III–V/Si materials -- Machine learning -- Computer vision -- Crystalline defects recognition; Microscopy -- Periodicals; Electron Probe Microanalysis -- Periodicals; Microscopy -- Periodicals; Microscopie -- Périodiques; Microscopy; Periodicals; 502.82
• DOI: 10.1016/j.micron.2021.103069
• Languages: English
• ISSNs: 0968-4328

Abstract

Highlights: Automatic lattice defect detection system for atomic resolution microscopy. Combines convolutional neural networks, graph-based heuristics and image filters. Effective, robust and able to cope with very small training image data sets. Identifies defect-containing image in 3–5 s, segments defects in 2–3 min. Code is freely available at https://github.com/nkdnnlr/TEMDefectClassification . Abstract: Controlling crystalline material defects is crucial, as they affect properties of the material that may be detrimental or beneficial for the final performance of a device. Defect analysis on the sub-nanometer scale is enabled by high-resolution scanning transmission electron microscopy (HRSTEM), where the identification of defects is currently carried out based on human expertise. However, the process is tedious, highly time consuming and, in some cases, yields ambiguous results. Here we propose a semi-supervised machine learning method that assists in the detection of lattice defects from atomic resolution HRSTEM images. It involves a convolutional neural network that classifies image patches as defective or non-defective, a graph-based heuristic that chooses one non-defective patch as a model, and finally an automatically generated convolutional filter bank, which highlights symmetry breaking such as stacking faults, twin defects and grain boundaries. Additionally, we suggest a variance filter to segment amorphous regions and beam defects. The algorithm is tested on III–V/Si crystalline materials and successfully evaluated against different metrics and a baseline approach, showing promising results even for extremely small training data sets and for noise compromised images. By combining the data-driven classification generality, robustness and speed of deep learning with the effectiveness of image filters in segmenting faulty symmetry arrangements, we provide a valuable open-source tool to the microscopist community that can streamline future HRSTEM analyses of crystalline materials.