Sciweavers

Share
ISBI
2002
IEEE

Detecting branching structures using local Gaussian models

9 years 8 months ago
Detecting branching structures using local Gaussian models
Wepresentamethodformodellingandestimatingbranchingstructures,such asbloodvesselbifurcations,frommedicalimages.Wemodelbranchesasa superpositionofNGaussianfunctionsinalocalregionwhichdescribethe amplitude,positionandorientationsoflinearfeaturesandalsobranches.The centroidsofcomponentfeaturesareseparatedbyapplyingk-meanstothelocalFourierphaseandthecovariancesandamplitudessubsequentlyestimated byalikelihoodmaximisation.Weapplyapenalisedlikelihoodtest(AIC)to selectthebestfitmodelinaregion.Resultsarepresentedonsyntheticand representative2Dretinalimageswhichshowtheestimationtoberobustand accurateinthepresenceofnoise.Wecompareourresultsascale-spaceoperatormethod.
Li Wang, Abhir Bhalerao
Added 20 Nov 2009
Updated 20 Nov 2009
Type Conference
Year 2002
Where ISBI
Authors Li Wang, Abhir Bhalerao
Comments (0)
books