Locally adaptive conductance in geometry-driven-diffusion filtering of magnetic resonance tomograms

Ivan Bajla, Igor Holländer

Research output: Contribution to journalArticlepeer-review

Abstract

A method of local adapting of the conductance using a pixel dissimilarity measure. It involves a specific cost function suitable for the calculation of the optimum relaxation parameter and for the selection of the optimal exponential conductance in geometry-driven-diffusion (GDD) equation
Original languageEnglish
Pages (from-to)271-282
Number of pages12
JournalIee Proceedings - Vision Image and Signal Processing
Publication statusPublished - 2000

Research Field

  • Not defined

Keywords

  • nonlinear image filtering
  • geometry-driven diffusion
  • image segmentation
  • magnetic resonance imaging

Fingerprint

Dive into the research topics of 'Locally adaptive conductance in geometry-driven-diffusion filtering of magnetic resonance tomograms'. Together they form a unique fingerprint.

Cite this