From Ohm

Noise Reduction with ITK

Noise reduction with anisotropic diffusion (itk::GradientAnisotropicDiffusionImageFilter):

IsoDiffusion AnisoDiffusion sci utah/itk.org
// create diffusion filter
typedef itk::Image< double, 3> Image3DDoubleType;
typedef itk::GradientAnisotropicDiffusionImageFilter< Image3DType, Image3DDoubleType > DiffusionImageFilterType;
DiffusionImageFilterType::Pointer diffusionFilter = DiffusionImageFilterType::New();
diffusionFilter->SetInput(reader->GetOutput());

// filter settings
diffusionFilter->SetNumberOfIterations(5);
diffusionFilter->SetTimeStep(0.05);
diffusionFilter->SetConductanceParameter(3.0);

Applying the anisotropic diffusion filter:

without noise reduction with noise reduction

Applying a thresholding filter:

thresholding with prior noise reduction thresholding without prior noise reduction

Note: Although diffusion filtering is performed automatically in parallel, diffusion is a computational expensive task that may take several minutes.

Retrieved from http://schorsch.efi.fh-nuernberg.de/roettger/index.php/MedicalVisualization/NoiseReductionWithITK

Page last modified on December 19, 2014, at 07:08 PM