DIC-ROI-Mask-Generator

Machine learning-based automated ROI masking and mesh refinement for DIC analysis of complex sample geometries.

A machine learning approach that automates region selection, mesh refinement, and subset splitting near complex sample edges for improved DIC analysis efficiency.

Key Features:

  • SAM2-based automatic ROI detection from speckle images
  • Adaptive mesh generation near complex boundaries
  • Eliminates manual ROI definition in DIC workflows

Publication: Machine Learning-Aided Spatial Adaptation for Improved DIC Analysis of Complex Geometries, Strain, 2026