estimate_noiseestimate_noiseEstimateNoiseEstimateNoiseestimate_noise (Operator)

Name

estimate_noiseestimate_noiseEstimateNoiseEstimateNoiseestimate_noise — Estimate the image noise from a single image.

Signature

estimate_noise(Image : : Method, Percent : Sigma)

Herror estimate_noise(const Hobject Image, const char* Method, double Percent, double* Sigma)

Herror T_estimate_noise(const Hobject Image, const Htuple Method, const Htuple Percent, Htuple* Sigma)

void EstimateNoise(const HObject& Image, const HTuple& Method, const HTuple& Percent, HTuple* Sigma)

HTuple HImage::EstimateNoise(const HString& Method, const HTuple& Percent) const

double HImage::EstimateNoise(const HString& Method, double Percent) const

double HImage::EstimateNoise(const char* Method, double Percent) const

double HImage::EstimateNoise(const wchar_t* Method, double Percent) const   ( Windows only)

static void HOperatorSet.EstimateNoise(HObject image, HTuple method, HTuple percent, out HTuple sigma)

HTuple HImage.EstimateNoise(string method, HTuple percent)

double HImage.EstimateNoise(string method, double percent)

def estimate_noise(image: HObject, method: str, percent: Union[int, float]) -> Sequence[float]

def estimate_noise_s(image: HObject, method: str, percent: Union[int, float]) -> float

Description

The operator estimate_noiseestimate_noiseEstimateNoiseEstimateNoiseEstimateNoiseestimate_noise estimates the standard deviation of additive noise within the domain of the image that is passed in ImageImageImageImageimageimage. The standard deviation is returned in SigmaSigmaSigmaSigmasigmasigma.

To estimate the noise, one of the following four methods can be selected in MethodMethodMethodMethodmethodmethod:

Note that the methods 'foerstner'"foerstner""foerstner""foerstner""foerstner""foerstner" and 'immerkaer'"immerkaer""immerkaer""immerkaer""immerkaer""immerkaer" assume a Gaussian distribution of the image noise, whereas the methods 'least_squares'"least_squares""least_squares""least_squares""least_squares""least_squares" and'mean'"mean""mean""mean""mean""mean" can be applied to images with arbitrarily distributed noise. In general, the method 'foerstner'"foerstner""foerstner""foerstner""foerstner""foerstner" returns the most accurate results while the method 'immerkaer'"immerkaer""immerkaer""immerkaer""immerkaer""immerkaer" shows the fastest computation.

If the image noise could not be estimated reliably, the error 3175 is raised. This may happen if the image does not contain enough homogeneous regions, if the image was artificially created, or if the noise is not of Gaussian type. In order to avoid this error, it might be useful in some cases to try one of the following modifications in dependence of the estimation method that is passed in MethodMethodMethodMethodmethodmethod:

Attention

Note that filter operators may return unexpected results if an image with a reduced domain is used as input. Please refer to the chapter Filters.

Execution Information

Parameters

ImageImageImageImageimageimage (input_object)  singlechannelimage(-array) objectHImageHObjectHImageHobject (byte / uint2)

Input image.

MethodMethodMethodMethodmethodmethod (input_control)  string HTuplestrHTupleHtuple (string) (string) (HString) (char*)

Method to estimate the image noise.

Default: 'foerstner' "foerstner" "foerstner" "foerstner" "foerstner" "foerstner"

List of values: 'foerstner'"foerstner""foerstner""foerstner""foerstner""foerstner", 'immerkaer'"immerkaer""immerkaer""immerkaer""immerkaer""immerkaer", 'least_squares'"least_squares""least_squares""least_squares""least_squares""least_squares", 'mean'"mean""mean""mean""mean""mean"

PercentPercentPercentPercentpercentpercent (input_control)  number HTupleUnion[int, float]HTupleHtuple (real / integer) (double / int / long) (double / Hlong) (double / Hlong)

Percentage of used image points.

Default: 20

Suggested values: 1, 2, 5, 7, 10, 15, 20, 30, 40, 50

Restriction: 0 < Percent && Percent <= 50.

SigmaSigmaSigmaSigmasigmasigma (output_control)  real(-array) HTupleSequence[float]HTupleHtuple (real) (double) (double) (double)

Standard deviation of the image noise.

Assertion: Sigma >= 0

Example (HDevelop)

read_image (Image, 'combine')
estimate_noise (ImageNoise, 'foerstner', 20, SigmaFoerstner)
estimate_noise (ImageNoise, 'immerkaer', 20, SigmaImmerkaer)
estimate_noise (ImageNoise, 'least_squares', 20, SigmaLeastSquares)
estimate_noise (ImageNoise, 'mean', 20, SigmaMean)

Result

If the parameters are valid, the operator estimate_noiseestimate_noiseEstimateNoiseEstimateNoiseEstimateNoiseestimate_noise returns the value 2 ( H_MSG_TRUE) . If necessary an exception is raised. If the image noise could not be estimated reliably, the error 3175 is raised.

Possible Predecessors

grab_imagegrab_imageGrabImageGrabImageGrabImagegrab_image, grab_image_asyncgrab_image_asyncGrabImageAsyncGrabImageAsyncGrabImageAsyncgrab_image_async, read_imageread_imageReadImageReadImageReadImageread_image, reduce_domainreduce_domainReduceDomainReduceDomainReduceDomainreduce_domain

Possible Successors

binomial_filterbinomial_filterBinomialFilterBinomialFilterBinomialFilterbinomial_filter, gauss_filtergauss_filterGaussFilterGaussFilterGaussFiltergauss_filter, mean_imagemean_imageMeanImageMeanImageMeanImagemean_image, smooth_imagesmooth_imageSmoothImageSmoothImageSmoothImagesmooth_image

Alternatives

noise_distribution_meannoise_distribution_meanNoiseDistributionMeanNoiseDistributionMeanNoiseDistributionMeannoise_distribution_mean, intensityintensityIntensityIntensityIntensityintensity, min_max_graymin_max_grayMinMaxGrayMinMaxGrayMinMaxGraymin_max_gray

See also

gauss_distributiongauss_distributionGaussDistributionGaussDistributionGaussDistributiongauss_distribution, add_noise_distributionadd_noise_distributionAddNoiseDistributionAddNoiseDistributionAddNoiseDistributionadd_noise_distribution

References

W. Förstner: “Image Preprocessing for Feature Extraction in Digital Intensity, Color and Range Images“, Springer Lecture Notes on Earth Sciences, Summer School on Data Analysis and the Statistical Foundations of Geomatics, 1999
J. Immerkaer: “Fast Noise Variance Estimation“, Computer Vision and Image Understanding, Vol. 64, No. 2, pp. 300-302, 1996

Module

Foundation