HuMatch2d

Computes the distance between Hu moments of shapes in an image and and several templates' Hu moments. More...

Classes
class	ipsdk::imaproc::shape::analysis::HuMatch2dMsr
	Measurement object for measure HuMatch2d. More...
class	ipsdk::imaproc::shape::analysis::HuMatch2dMsrInfo
	Information object for measure HuMatch2d. More...
class	ipsdk::imaproc::shape::analysis::HuMatch2dMsrParams
	Parameter object for measure HuMatch2d. More...

Detailed Description

Computes the distance between Hu moments of shapes in an image and and several templates' Hu moments.

This measure computes the distance between the Hu moment invariants of reference shapes and the Hu invariants of each shape. The available distances are detailed in the HuDistance2d measure.

If a distance is higher than the input threshold, the measure considers it as a bad match and sets the distance to the maximum possible value of ipReal64 type.

Here is an example of Hu moment matching measurement in 2d case with the distance type , a threshold set to 1.2 and without processing holes (the 'X' represent bad matches):

See also HuMoments2d.

Author

R. Abbal

Date

2017/06/06

Copyright

2017 Reactiv'IP, all right reserved.

Computes the distance between Hu moments of shapes in an image and and several templates' Hu moments

Measure synthesis :

Measure Type	Measure Unit Type	Parameter Type	Result Type	Shape Requirements
Geometry 2d	None	HuMatch2dMsrParams	Collection (ipsdk::ipReal64)	Boundary Approximation

See Shape measurement for additional information on these pictograms

Measure Type :

This is a geometry 2d measure

• it use shape 2d data to compute a result
• it optionally can use dependencies to other measures to compute a result (see Measure Dependencies section)

This measure can only be used in 2d case

Measure Unit Type:

Measure HuMatch2d is not associated to any unit [ipsdk::shape::analysis::eMsrUnitFormat::eMUF_NoUnit]

Measure Parameter Type :

Measure HuMatch2d is associated to HuMatch2dMsrParams parameters

Measure Result Type :

Measure HuMatch2d is associated to ipsdk::shape::analysis::CollMeasureResult<ipsdk::ipReal64> results

Measure Shape Requirements :

Measure HuMatch2d requires boundary approximation from shape data

Measure Dependencies :

Measure HuMatch2d depends on following measures :

Measure Mode	Measure Name	Measure Type	Measure Parameters
eMVP_2d	HuMoments2d	HuMoments2d	createHolesBasicPolicyMsrParams(_pMsrParams->getValue<HuMatch2dMsrParams::ProcessHoles>())

Note

See Shape Analysis 2d for more information on general shape 2d analysis and measurement usage.

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, "HuMatch2dMsr")
    
    #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("HuMatch2dMsr")
    
    # 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);

    // For the example, the reference shape is the first same shapes than the shapes in the input image
    // In this case, the distance must be 0 when matching the shape with itself
    std::vector<Shape2dPtr> vRefShapes2d = std::vector<Shape2dPtr>(pShape2dColl->getColl().begin() + 1, pShape2dColl->getColl().end());

    // define a measure info set
    MeasureInfoSetPtr pMeasureInfoSet = MeasureInfoSet::create2dInstance();
    createMeasureInfo(pMeasureInfoSet, "HuMatch2dMsr", createHuMatch2dMsrParams(vRefShapes2d, bProcessHoles, distType, threshold));
    
    // compute measure on shape 2d collection
    MeasureSetPtr pOutMeasureSet = shapeAnalysis2d(pInGreyImg2d, pShape2dColl, pMeasureInfoSet);

    // retrieve associated results
    const MeasureConstPtr& pHuMatch2dOutMsr = pOutMeasureSet->getMeasure("HuMatch2dMsr");
    const CollMeasureResult<ipReal64>& outResults = static_cast<const CollMeasureResult<ipReal64>&>(pHuMatch2dOutMsr->getMeasureResult());