Modelling intensity and gradient distribution of 3D tomography data for direct extraction of physical parameters and robust evaluation of segmentation — ICTMS Committee Dep of Applied Maths Australian National University
  1. Schedule
  2. Theme 2: Automated methods for volume segmentation/analysis, e.g., machine learning
  3. Modelling intensity and gradient distribution of 3D tomography data for direct extraction of physical parameters and robust evaluation of segmentation

Modelling intensity and gradient distribution of 3D tomography data for direct extraction of physical parameters and robust evaluation of segmentation (88)

Elise O Brenne 1 , Vedrana A Dahl 1 , Peter S Jørgensen 1
  1. DTU, København K, REGION HOVEDSTADEN, Denmark

We propose a novel intensity distribution model for material interfaces. Intensity gradient informa-tion is exploited for robust model fitting. Our model allows for direct extraction of physical sample parameters,assists segmentation, and provides a methodology for evaluating segmentation results.

Full Paper