An Efficient Morphological Active Surface Model for Volumetric Image Segmentation

  • Authors:
  • Andrei C. Jalba;Jos B. Roerdink

  • Affiliations:
  • Institute for Mathematics and Computing Science, Eindhoven University of Technology, Eindhoven, The Netherlands 5600;Institute for Mathematics and Computing Science, University of Groningen, Groningen, The Netherlands 9700

  • Venue:
  • ISMM '09 Proceedings of the 9th International Symposium on Mathematical Morphology and Its Application to Signal and Image Processing
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Using tools from multi-scale morphology, we reformulate a region-based active-contour model using a minimum-variance criterion. Experimental results of 3D data show that our discrete model achieves similar segmentation quality as the continuous model based on the level-set framework, while being two orders of magnitude faster than optimized implementations of the original continuous model.