Disparity angularity 2dSee full documentation

measure allowing to build an histogram of disparity between angle measured on shape and angle measured on reference ellipse

This measure allows to quantified the angularity of a shape using the difference between angle of consecutive segments of polygonal approximation of shape with angle on its equivalent ellipse.

Note that equivalent ellipse associated to a shape is define such as :

• ellipse center is set at shape barycenter (see Barycenter2d)
• ellipse orientation is equal to orientation extracted from second order moment of shape (see Inertia Orientation 2d)
• ellipse dimensions are defined such that ellipse perimeter and area match with shape perimeter (see Perimeter2d) and shape area (see Area2d).

For each tops of the polygonal approximation of shape, we compute an angularity value given by :

where :

• is angle between segments ending at considered top .
• is the associated angle on equivalent ellipse.
  

We then compute the histogram of these values using a number of orientation defined by parameter NbOrientations.

The global shape angularity value is then given by mean value associated to bin containing quantile value defined by parameter Quantile.

Here is an example of degree of angularity 2d computation on few caracteristic shapes :

measure allowing to build an histogram of disparity between angle measured on shape and angle measured on reference ellipse

Measure synthesis :

Measure Type	Measure Unit Type	Parameter Type	Result Type	Shape Requirements
Geometry 2d	Angle	DisparityAngularity2dMsrParams	Value (ipsdk::ipReal64)	Both

See Shape measurement for additional information on these pictograms

Example of Python code :

Generic example in 2d case :

import PyIPSDK
import PyIPSDK.IPSDKIPLShapeAnalysis as shapeanalysis

    # Create the infoset
    inMeasureInfoSet2d = PyIPSDK.createMeasureInfoSet2d()
    PyIPSDK.createMeasureInfo(inMeasureInfoSet2d, "GradientAngularityIndex2dMsr")
    
    #Perform the analysis
    outMeasureSet = shapeanalysis.labelAnalysis2d(inGreyImg, inLabelImg2d, inMeasureInfoSet2d)
    
    # save results to csv format
    PyIPSDK.saveCsvMeasureFile(os.path.join(tmpPath,  "shape_analysis_results.csv"), outMeasureSet)
    
    # retrieve measure results
    outMsr = outMeasureSet.getMeasure("GradientAngularityIndex2dMsr")
    
    # retrieve measure values
    outMsrValues = outMsr.getMeasureResult().getColl(0)
    print("First label measurement equal " + str(outMsrValues[1]))

Example of C++ code :

Example informations

Associated library

IPSDKIPLShapeAnalysis

Code Example

    // opening grey level input image
    ImagePtr pInGreyImg2d = loadTiffImageFile(inputGreyImgPath);

    // read entity shape 2d collection used for processing
    Shape2dCollPtr pShape2dColl = boost::make_shared<Shape2dColl>();
    IPSDK_REQUIRE(readFromXmlFile(inputShape2dCollPath, *pShape2dColl) == true);

    // define a measure info set
    MeasureInfoSetPtr pMeasureInfoSet = MeasureInfoSet::create2dInstance();
    createMeasureInfo(pMeasureInfoSet, "DisparityAngularity2dMsr");
    
    // compute measure on shape 2d collection
    MeasureSetPtr pOutMeasureSet = shapeAnalysis2d(pInGreyImg2d, pShape2dColl, pMeasureInfoSet);

    // retrieve associated results
    const MeasureConstPtr& pDisparityAngularity2dOutMsr = pOutMeasureSet->getMeasure("DisparityAngularity2dMsr");
    const ipsdk::shape::analysis::ValueMeasureResult<ipsdk::ipReal64>& outResults = static_cast<const ipsdk::shape::analysis::ValueMeasureResult<ipsdk::ipReal64>&>(pDisparityAngularity2dOutMsr->getMeasureResult());