3:45 PM - 4:00 PM
[16p-D221-7] Handling Microstructure Images for Data Driven Research
Keywords:STEM image, PCA, feature extraction
We tried to apply transmission electron microscope image data to data-driven research. First, principal component analysis (PCA) was performed on a data set of 787 cross-sectional STEM images of 111 thin film samples acquired at the Central Research Institute of Electric Power Industry for the aim of extracting features from image data. In performing PCA, we will present the results of examining parameter settings, data set creation, and feature extraction methods.