[2P08] EBSD Kikuchi pattern analysis using autoencoder
Electron backscatter diffraction (EBSD) is a surface analysis method that provides detailed information on the crystal orientation and strain of a solid sample and is applied to the evaluation of the crystal structure of various solid samples. We have developed a new analysis system for EBSD raw data (Kikuchi pattern maps) using multivariate analysis. In this study, we aim to extract more detailed crystal structures by applying autoencoder which is an unsupervised learning method based on artificial neural networks. Stainless steel was analyzed using EBSD with a scanning electron microscope. The pixels of each Kikuchi pattern map were the variables and the pixels of the measured area were the samples. The data set was analyzed using sparse autoencoder. As a result, the measurement area of the sample was divided into several regions in the features and a Kikuchi pattern map corresponding to each divided region were extracted in the decoder weights.
Abstract password authentication.
Password is required to view the abstract. Please enter a password to authenticate.