Combining polarized light microscopy with machine learning to map crystallographic textures on cubic metals

Wang, Xiaogang; Sibo, Yang; Seita, Matteo

doi:10.1016/j.matchar.2022.112082

Cited by 5 publications

(1 citation statement)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[ 25 ] However, it holds greatest promise wherever conventional characterization techniques, such as EBSD, struggle to assess large-scale microstructure variability, e.g., in additively manufactured materials. [ 26 , 27 ] Other techniques that integrate multiple images to expand the microstructure information obtainable through optical microscopy include ones that vary light polarization to infer crystallographic textures [ 28 – 30 ] or, in some cases, full crystal orientations. [ 31 ] Crystallographic textures may also be inferred from topographic analysis.…”

Section: Multi-image Characterization Of a Single Sample Locationmentioning

confidence: 99%

Quantitative multi-image analysis in metals research

et al. 2022

View full text Add to dashboard Cite

Quantitative multi-image analysis (QMA) is the systematic extraction of new information and insight through the simultaneous analysis of multiple, related images. We present examples illustrating the potential for QMA to advance materials research in multi-image characterization, automatic feature identification, and discovery of novel processing-structure–property relationships. We conclude by discussing opportunities and challenges for continued advancement of QMA, including instrumentation development, uncertainty quantification, and automatic parsing of literature data. Graphical abstract

show abstract