ImageDev

AutoSegmentation3Phases

Performs an automatic 2-level segmentation of a grayscale image.

Access to parameter description

As an introduction: This algorithm computes an automatic segmentation on a grayscale image, separating the image in 3 classes of pixels.
Three methods of classification are available: Entropy, Factorisation, or Moments. These methods are detailed in the AutoThresholdingBright documentation.

The computed threshold is returned in the AutoSegmentation3PhasesMsr object.

The output image is a label image with 2 non-zero levels.

See also

Function Syntax

This function returns a AutoSegmentation3PhasesOutput structure containing outputLabelImage and outputMeasurement.
// Output structure of the autoSegmentation3Phases function.
struct AutoSegmentation3PhasesOutput
{
    /// The output binary image. Its dimensions are forced to the same values as the input.
    std::shared_ptr< iolink::ImageView > outputLabelImage;
    /// The computed threshold values.
    AutoSegmentation3PhasesMsr::Ptr outputMeasurement;
};

// Function prototype
AutoSegmentation3PhasesOutput autoSegmentation3Phases( std::shared_ptr< iolink::ImageView > inputGrayImage, AutoSegmentation3Phases::RangeMode rangeMode, iolink::Vector2d intensityInputRange, AutoSegmentation3Phases::ThresholdCriterion thresholdCriterion, std::shared_ptr< iolink::ImageView > outputLabelImage = NULL, AutoSegmentation3PhasesMsr::Ptr outputMeasurement = NULL );
This function returns a tuple containing output_label_image and output_measurement.
// Function prototype.
auto_segmentation3_phases( input_gray_image,
                           range_mode = AutoSegmentation3Phases.RangeMode.MIN_MAX,
                           intensity_input_range = [0, 255],
                           threshold_criterion = AutoSegmentation3Phases.ThresholdCriterion.ENTROPY,
                           output_label_image = None,
                           output_measurement = None )
This function returns a AutoSegmentation3PhasesOutput structure containing outputLabelImage and outputMeasurement.
/// Output structure of the AutoSegmentation3Phases function.
public struct AutoSegmentation3PhasesOutput
{
    /// 
    /// The output binary image. Its dimensions are forced to the same values as the input.
    /// 
    public IOLink.ImageView outputLabelImage;
    /// The computed threshold values.
    public AutoSegmentation3PhasesMsr outputMeasurement;
};

// Function prototype.
public static AutoSegmentation3PhasesOutput
AutoSegmentation3Phases( IOLink.ImageView inputGrayImage,
                         AutoSegmentation3Phases.RangeMode rangeMode = ImageDev.AutoSegmentation3Phases.RangeMode.MIN_MAX,
                         double[] intensityInputRange = null,
                         AutoSegmentation3Phases.ThresholdCriterion thresholdCriterion = ImageDev.AutoSegmentation3Phases.ThresholdCriterion.ENTROPY,
                         IOLink.ImageView outputLabelImage = null,
                         AutoSegmentation3PhasesMsr outputMeasurement = null );

Class Syntax

Parameters

Parameter Name Description Type Supported Values Default Value
input
inputGrayImage
The input grayscale image. Image Grayscale nullptr
input
rangeMode
The way to determine the input intensity range.
MIN_MAX The histogram is computed between the minimum and the maximum of the image.
OTHER The histogram is computed between user-defined bounds [a,b].
Enumeration MIN_MAX
input
intensityInputRange
The input intensity range [a,b] inside which the threshold is searched. This parameter is ignored if the range mode is set to MIN_MAX. Vector2d Any value {0.f, 255.f}
input
thresholdCriterion
The criterion to compute the threshold from the histogram.
ENTROPY The measure of dispersion used in the algorithm is the entropy of the intensity distribution.
FACTORISATION The measure of dispersion used in the algorithm is the variance of the intensity distribution (also known as Otsu method).
MOMENTS The measure of dispersion used in the algorithm is the moments of the intensity distribution.
Enumeration ENTROPY
output
outputLabelImage
The output binary image. Its dimensions are forced to the same values as the input. Image nullptr
output
outputMeasurement
The computed threshold values. AutoSegmentation3PhasesMsr nullptr
Parameter Name Description Type Supported Values Default Value
input
input_gray_image
The input grayscale image. image Grayscale None
input
range_mode
The way to determine the input intensity range.
MIN_MAX The histogram is computed between the minimum and the maximum of the image.
OTHER The histogram is computed between user-defined bounds [a,b].
enumeration MIN_MAX
input
intensity_input_range
The input intensity range [a,b] inside which the threshold is searched. This parameter is ignored if the range mode is set to MIN_MAX. vector2d Any value [0, 255]
input
threshold_criterion
The criterion to compute the threshold from the histogram.
ENTROPY The measure of dispersion used in the algorithm is the entropy of the intensity distribution.
FACTORISATION The measure of dispersion used in the algorithm is the variance of the intensity distribution (also known as Otsu method).
MOMENTS The measure of dispersion used in the algorithm is the moments of the intensity distribution.
enumeration ENTROPY
output
output_label_image
The output binary image. Its dimensions are forced to the same values as the input. image None
output
output_measurement
The computed threshold values. AutoSegmentation3PhasesMsr None
Parameter Name Description Type Supported Values Default Value
input
inputGrayImage
The input grayscale image. Image Grayscale null
input
rangeMode
The way to determine the input intensity range.
MIN_MAX The histogram is computed between the minimum and the maximum of the image.
OTHER The histogram is computed between user-defined bounds [a,b].
Enumeration MIN_MAX
input
intensityInputRange
The input intensity range [a,b] inside which the threshold is searched. This parameter is ignored if the range mode is set to MIN_MAX. Vector2d Any value {0f, 255f}
input
thresholdCriterion
The criterion to compute the threshold from the histogram.
ENTROPY The measure of dispersion used in the algorithm is the entropy of the intensity distribution.
FACTORISATION The measure of dispersion used in the algorithm is the variance of the intensity distribution (also known as Otsu method).
MOMENTS The measure of dispersion used in the algorithm is the moments of the intensity distribution.
Enumeration ENTROPY
output
outputLabelImage
The output binary image. Its dimensions are forced to the same values as the input. Image null
output
outputMeasurement
The computed threshold values. AutoSegmentation3PhasesMsr null

Object Examples

std::shared_ptr< iolink::ImageView > polystyrene = ioformat::readImage( std::string( IMAGEDEVDATA_IMAGES_FOLDER ) + "polystyrene.tif" );

AutoSegmentation3Phases autoSegmentation3PhasesAlgo;
autoSegmentation3PhasesAlgo.setInputGrayImage( polystyrene );
autoSegmentation3PhasesAlgo.setRangeMode( AutoSegmentation3Phases::RangeMode::MIN_MAX );
autoSegmentation3PhasesAlgo.setIntensityInputRange( {0, 255} );
autoSegmentation3PhasesAlgo.setThresholdCriterion( AutoSegmentation3Phases::ThresholdCriterion::ENTROPY );
autoSegmentation3PhasesAlgo.execute();

std::cout << "outputLabelImage:" << autoSegmentation3PhasesAlgo.outputLabelImage()->toString();
std::cout << "thresholdLow: " << autoSegmentation3PhasesAlgo.outputMeasurement()->thresholdLow( 0 ) ;
polystyrene = ioformat.read_image(imagedev_data.get_image_path("polystyrene.tif"))

auto_segmentation3_phases_algo = imagedev.AutoSegmentation3Phases()
auto_segmentation3_phases_algo.input_gray_image = polystyrene
auto_segmentation3_phases_algo.range_mode = imagedev.AutoSegmentation3Phases.MIN_MAX
auto_segmentation3_phases_algo.intensity_input_range = [0, 255]
auto_segmentation3_phases_algo.threshold_criterion = imagedev.AutoSegmentation3Phases.ENTROPY
auto_segmentation3_phases_algo.execute()

print( "output_label_image:", str( auto_segmentation3_phases_algo.output_label_image ) )
print( "thresholdLow: ", str( auto_segmentation3_phases_algo.output_measurement.threshold_low( 0 ) ) )
ImageView polystyrene = ViewIO.ReadImage( @"Data/images/polystyrene.tif" );

AutoSegmentation3Phases autoSegmentation3PhasesAlgo = new AutoSegmentation3Phases
{
    inputGrayImage = polystyrene,
    rangeMode = AutoSegmentation3Phases.RangeMode.MIN_MAX,
    intensityInputRange = new double[]{0, 255},
    thresholdCriterion = AutoSegmentation3Phases.ThresholdCriterion.ENTROPY
};
autoSegmentation3PhasesAlgo.Execute();

Console.WriteLine( "outputLabelImage:" + autoSegmentation3PhasesAlgo.outputLabelImage.ToString() );
Console.WriteLine( "thresholdLow: " + autoSegmentation3PhasesAlgo.outputMeasurement.thresholdLow( 0 ) );

Function Examples

std::shared_ptr< iolink::ImageView > polystyrene = ioformat::readImage( std::string( IMAGEDEVDATA_IMAGES_FOLDER ) + "polystyrene.tif" );

auto result = autoSegmentation3Phases( polystyrene, AutoSegmentation3Phases::RangeMode::MIN_MAX, {0, 255}, AutoSegmentation3Phases::ThresholdCriterion::ENTROPY );

std::cout << "outputLabelImage:" << result.outputLabelImage->toString();
std::cout << "thresholdLow: " << result.outputMeasurement->thresholdLow( 0 ) ;
polystyrene = ioformat.read_image(imagedev_data.get_image_path("polystyrene.tif"))

result_output_label_image, result_output_measurement = imagedev.auto_segmentation3_phases( polystyrene, imagedev.AutoSegmentation3Phases.MIN_MAX, [0, 255], imagedev.AutoSegmentation3Phases.ENTROPY )

print( "output_label_image:", str( result_output_label_image ) )
print( "thresholdLow: ", str( result_output_measurement.threshold_low( 0 ) )  )
ImageView polystyrene = ViewIO.ReadImage( @"Data/images/polystyrene.tif" );

Processing.AutoSegmentation3PhasesOutput result = Processing.AutoSegmentation3Phases( polystyrene, AutoSegmentation3Phases.RangeMode.MIN_MAX, new double[]{0, 255}, AutoSegmentation3Phases.ThresholdCriterion.ENTROPY );

Console.WriteLine( "outputLabelImage:" + result.outputLabelImage.ToString() );
Console.WriteLine(  "thresholdLow: " + result.outputMeasurement.thresholdLow( 0 )  );