[ VIGRA Homepage | Function Index | Class Index | Namespaces | File List | Main Page ]
NoiseNormalizationOptions Class Reference |
Pass options to one of the noise normalization functions. More...
#include <vigra/noise_normalization.hxx>
Public Member Functions | |
NoiseNormalizationOptions & | averagingQuantile (double quantile) |
NoiseNormalizationOptions & | clusterCount (unsigned int c) |
NoiseNormalizationOptions & | noiseEstimationQuantile (double quantile) |
NoiseNormalizationOptions () | |
NoiseNormalizationOptions & | noiseVarianceInitialGuess (double guess) |
NoiseNormalizationOptions & | useGradient (bool r) |
NoiseNormalizationOptions & | windowRadius (unsigned int r) |
Pass options to one of the noise normalization functions.
NoiseNormalizationOptions
is an argument object that holds various optional parameters used by the noise normalization functions. If a parameter is not explicitly set, a suitable default will be used.
Usage:
#include <vigra/noise_normalization.hxx>
Namespace: vigra
Initialize all options with default values.
NoiseNormalizationOptions& useGradient | ( | bool | r | ) |
Select the noise estimation algorithm.
If r is true
, use the gradient-based noise estimator according to Förstner (default). Otherwise, use an algorithm that uses the intensity values directly.
NoiseNormalizationOptions& windowRadius | ( | unsigned int | r | ) |
Set the window radius for a single noise estimate. Every window of the given size gives raise to one intensity/variance pair.
Default: 6 pixels
NoiseNormalizationOptions& clusterCount | ( | unsigned int | c | ) |
Set the number of clusters for non-parametric noise normalization. The intensity/variance pairs found are grouped into clusters before the noise normalization transform is computed.
Default: 10 clusters
NoiseNormalizationOptions& averagingQuantile | ( | double | quantile | ) |
Set the quantile for cluster averaging. After clustering, the cluster center (i.e. average noise variance as a function of the average intensity in the cluster) is computed using only the cluster members whose estimated variance is below quantile times the maximum variance in the cluster.
Default: 0.8
Precondition: 0 < quantile <= 1.0
NoiseNormalizationOptions& noiseEstimationQuantile | ( | double | quantile | ) |
Set the operating range of the robust noise estimator. Intensity changes that are larger than quantile times the current estimate of the noise variance are ignored by the robust noise estimator.
Default: 1.5
Precondition: 0 < quantile
NoiseNormalizationOptions& noiseVarianceInitialGuess | ( | double | guess | ) |
Set the initial estimate of the noise variance. Robust noise variance estimation is an iterative procedure starting at the given value.
Default: 10.0
Precondition: 0 < guess
© Ullrich Köthe (ullrich.koethe@iwr.uni-heidelberg.de) |
html generated using doxygen and Python
|