A pipeline combining edge detection, an encoder-decoder, and iterative refinement, trained on concept-oriented synthetic TEM images, extracts grain boundaries from real metal images with about 97% accuracy relative to EBSD maps.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Novel Concept-Oriented Synthetic Data approach for Training Generative AI-Driven Crystal Grain Analysis Using Diffusion Model
A pipeline combining edge detection, an encoder-decoder, and iterative refinement, trained on concept-oriented synthetic TEM images, extracts grain boundaries from real metal images with about 97% accuracy relative to EBSD maps.