YOLO models trained on synthetic datasets for four particle shapes identify 2D colloidal assemblies with near-perfect accuracy on synthetic images but 43.1% average error on experimental images, varying by particle geometry.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.soft 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Application of Machine Learning for the Identification of 2D Colloidal Assemblies: A Case Study on Particles of Distinct Shapes
YOLO models trained on synthetic datasets for four particle shapes identify 2D colloidal assemblies with near-perfect accuracy on synthetic images but 43.1% average error on experimental images, varying by particle geometry.