IPSDK  4_1_0_2
IPSDK : Image Processing Software Development Kit
Image 2d registration using grey signed features
Image processing algorithms » Image Registration

algorithm allowing registration of 2d images using features associated to grey signature More...

IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration (const image::ImageConstPtr &pInOriginImg2d, const image::ImageConstPtr &pInTargetImg2d, const ipsdk::imaproc::attr::eRegistrationMotionModel2d &inRegMotionModel2d)
 wrapper function for algorithm allowing registration of 2d images using features associated to grey signature More...
 
IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration (const image::ImageConstPtr &pInOriginImg2d, const image::ImageConstPtr &pInTargetImg2d, const ipsdk::imaproc::attr::ScaleCandidatesConstPtr &pInScaleCandidates, const ipReal32 inGradStdDev, const attr::GaussianCoverageConstPtr &pInOptGradientGaussianCoverage, const ipsdk::imaproc::attr::CornerDetectionParamsConstPtr &pInCornerDetectionParams2d, const ipUInt32 inNbFeatures, const ipUInt32 inFeaturesDistX, const ipUInt32 inFeaturesDistY, const ipsdk::imaproc::attr::eInterpolationPolicy &inInterpolationPolicy, const ipsdk::imaproc::attr::SamplingBallInfoConstPtr &pInSamplingBallInfo2d, const ipsdk::imaproc::attr::eRegistrationMotionModel2d &inRegMotionModel2d, const ipReal64 inCorrelationThreshold2d, const ipsdk::imaproc::attr::RobustEstimationConfigConstPtr &pInOptRegistrationEstimationConfig, const ipsdk::imaproc::attr::Features2dRegistrationResultsPtr &pOutFeatures2dRegistrationResults)
 wrapper function for algorithm allowing registration of 2d images using features associated to grey signature More...
 
IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration (const image::ImageConstPtr &pInOriginImg2d, const image::ImageConstPtr &pInTargetImg2d)
 wrapper function for algorithm allowing registration of 2d images using features associated to grey signature More...
 
IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration (const image::ImageConstPtr &pInOriginImg2d, const image::ImageConstPtr &pInTargetImg2d, const ipReal32 inGradStdDev, const ipUInt32 inNbFeatures, const ipUInt32 inFeaturesDist, const attr::Features2dRegistrationResultsPtr &pOutFeatures2dRegistrationResults)
 wrapper function for algorithm allowing registration of 2d images using features associated to grey signature More...
 
IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration (const image::ImageConstPtr &pInOriginImg2d, const image::ImageConstPtr &pInTargetImg2d, const attr::ScaleCandidatesConstPtr &pInScaleCandidates)
 wrapper function for algorithm allowing registration of 2d images using features associated to grey signature More...
 
IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration (const image::ImageConstPtr &pInOriginImg2d, const image::ImageConstPtr &pInTargetImg2d, const attr::ScaleCandidatesConstPtr &pInScaleCandidates, const ipReal32 inGradStdDev, const ipUInt32 inNbFeatures, const ipUInt32 inFeaturesDist, const attr::Features2dRegistrationResultsPtr &pOutFeatures2dRegistrationResults)
 wrapper function for algorithm allowing registration of 2d images using features associated to grey signature More...
 

Detailed Description

algorithm allowing registration of 2d images using features associated to grey signature

This algorithm allows to automatically compute motion transform linking two images. Given an origin image $InOriginImg2d$ and a target image $InTargetImg2d$, this algorithm basically allows to automatically compute motion transform linking. We compute transformation allowing to link points of images with following formula :

\[ P_{target}=sR(\theta)P_{origin} + T(T_x, T_y) \]

with :

The computed transformation can also be of form :

\[ \bar{P}_{target}=H \bar{P}_{origin} \]

in case of homography motion model (ipsdk::imaproc::attr::eRegistrationMotionModel2d::eRMM2d_Homography) with :

This algorithm is composed of three main phasis :

Extraction phasis can be controlled via following parameters : $InOptGradStdDev$, $InOptGradientGaussianCoverage$, $InOptCornerDetectionParams2d$, $InOptNbFeatures$, $InOptFeaturesDistX$, $InOptFeaturesDistY$, $InOptInterpolationPolicy$ and $InOptSamplingBallInfo2d$ (see Extract grey signed features 2d).

Motion transform computation phasis can be controlled via following parameters : $InOptRegMotionModel2d$, $InOptCorrelationThreshold2d$ and $InOptRegistrationEstimationConfig$. Note that in case where $InOptRegMotionModel2d$ parameter is set to ipsdk::imaproc::attr::eRegistrationMotionModel2d::eRMM2d_Similarity or ipsdk::imaproc::attr::eRegistrationMotionModel2d::eRMM2d_Homography, algorithm will iterate on its three main phasis searching for best results adusting used scale for feature extraction (this phasis is not scale invariant see Extract grey signed features 2d). In this case an additional parameter $InOptScaleCandidates$ allows to defined candidates for tested scale factor.

Here is an example of usage of this algorithm in case of similarity transform computation :

greySignedFeaturesImg2dRegistration1.png

In this case, we ask for 100 detected features. Given used distance between features, algorithm provided 100 detected features in first image and only 95 in second one. Given used correlation threshold (set to 0.95 in this case), only 27 made pairs are keeped (blue points stands for rejected data during pairing phasis).

This allows a robust computation of similarity transformation which detects 8 outliers in input collections (red points) leaving 19 inliers (green points linked between images).

On output algorithm estimates a root mean square of residuals equal to 1.38 pixels which grants a good estimation of transformation.

Here is a second example of usage of this algorithm in case of similarity transform computation :

greySignedFeaturesImg2dRegistration2.png

In this case, we ask for 100 detected features. Given used distance between features, algorithm provided 100 detected features in first image and second images. Given used correlation threshold (set to 0.95 in this case), only 27 made pairs are keeped (blue points stands for rejected data during pairing phasis).

This allows a robust computation of similarity transformation which detects 2 outliers in input collections (red points) leaving 25 inliers (green points linked between images).

On output algorithm estimates a root mean square of residuals equal to 1.77 pixels which grants a good estimation of transformation.

Attributes description

Attribute description for algorithm :

Name ToolTip Default Initializer
ipsdk::imaproc::attr::InOriginImg2d [Input] Origin 2d image provided to registration algorithm X
ipsdk::imaproc::attr::InTargetImg2d [Input] Target 2d image provided to registration algorithm X
ipsdk::imaproc::attr::InOptScaleCandidates [Input Optional] scale candidates for processing X
ipsdk::imaproc::attr::InOptGradStdDev [Input Optional] standard deviation used for gradient computation X
ipsdk::imaproc::attr::InOptGradientGaussianCoverage [Input Optional] Parameter allowing to specify a gaussian distribution coverage for processing X
ipsdk::imaproc::attr::InOptCornerDetectionParams2d [Input Optional] parameters used during corner detection process X
ipsdk::imaproc::attr::InOptNbFeatures [Input Optional] target number of features to be detected by algorithm X
ipsdk::imaproc::attr::InOptFeaturesDistX [Input Optional] distance between detected features along x axis (tchebychev distance) X
ipsdk::imaproc::attr::InOptFeaturesDistY [Input Optional] distance between detected features along y axis (tchebychev distance) X
ipsdk::imaproc::attr::InOptInterpolationPolicy [Input Optional] interpolation policy used to extract local data from image X
ipsdk::imaproc::attr::InOptSamplingBallInfo2d [Input Optional] Parameters for used sampling ball around image points X
ipsdk::imaproc::attr::InOptRegMotionModel2d [Input Optional] 2d motion model which should be used for computation X
ipsdk::imaproc::attr::InOptCorrelationThreshold2d [Input Optional] threshold on 2d correlation scores used during pairs matching X
ipsdk::imaproc::attr::InOptRegistrationEstimationConfig [Input Optional] configuration for robust estimation part of features registration X
ipsdk::imaproc::attr::OutWk1Img [Output] Temporary working image for algorithm promoteReInterpretable (_pOutWk1Img, _pInOriginImg2d, _pInTargetImg2d, ipsdk::imaproc::ePromoteBinaryType::ePBT_UpperSigned)
ipsdk::imaproc::attr::OutWk2Img [Output] Temporary working image for algorithm promoteReInterpretable (_pOutWk2Img, _pInOriginImg2d, _pInTargetImg2d, ipsdk::imaproc::ePromoteBinaryType::ePBT_UpperSigned)
ipsdk::imaproc::attr::OutWk3Img [Output] Temporary working image for algorithm promoteReInterpretable (_pOutWk3Img, _pInOriginImg2d, _pInTargetImg2d, ipsdk::imaproc::ePromoteBinaryType::ePBT_UpperSigned)
ipsdk::imaproc::attr::OutWk4Img [Output] Temporary working image for algorithm promoteReInterpretable (_pOutWk4Img, _pInOriginImg2d, _pInTargetImg2d, ipsdk::imaproc::ePromoteBinaryType::ePBT_UpperSigned)
ipsdk::imaproc::attr::OutFeatures2dRegistrationResults [Output] collection of results for features 2d registration algorithm allocate (_pOutFeatures2dRegistrationResults)

Global Rule description

Global rule description for algorithm :
((ipsdk::imaproc::matchBufferType (_pInOriginImg2d,_pInTargetImg2d)) && 
 (ipsdk::imaproc::isReInterpretable (_pOutWk1Img,_pInOriginImg2d)) && 
 (ipsdk::imaproc::isReInterpretable (_pOutWk1Img,_pInTargetImg2d)) && 
 (ipsdk::imaproc::matchSizeAndType (_pOutWk1Img,_pOutWk2Img,_pOutWk3Img,_pOutWk4Img)))

Example of Python code :

Example imports

import PyIPSDK
import PyIPSDK.IPSDKIPLRegistration as registration

Code Example

# opening of input images
inImg1 = PyIPSDK.loadTiffImageFile(inputImgPath1)
inImg2 = PyIPSDK.loadTiffImageFile(inputImgPath2)
# computation of motion transform between images
outRegistrationResult = registration.greySignedFeaturesImg2dRegistration(inImg1, inImg2)
transformParams = outRegistrationResult.transform.params
# print of results
print("Registration results :")
print("----------------------")
print("Nb original features : " + str(outRegistrationResult.indicators.nbFeatures1))
print("Nb target features : " + str(outRegistrationResult.indicators.nbFeatures2))
print("Nb made pairs : " + str(outRegistrationResult.indicators.nbPairs))
print("Robust estimation status :")
print("--------------------------")
print(outRegistrationResult.indicators.estimationResults.toString())
print("Estimated motion transform :")
print("----------------------------")
print("Rotation (theta in radians) : " + str(transformParams[PyIPSDK.Rigid2d.eTP_Theta]))
print("Translation : {" + str(transformParams[PyIPSDK.Rigid2d.eTP_Tx]) + ", " + str(transformParams[PyIPSDK.Rigid2d.eTP_Ty]) + "}")

Example of C++ code :

Example informations

Associated library

IPSDKIPLRegistration

Header file

#include <IPSDKIPL/IPSDKIPLRegistration/Processor/GreySignedFeaturesImg2dRegistration/GreySignedFeaturesImg2dRegistration.h>

Code Example

// Load the input images
ImagePtr pInImg1 = loadTiffImageFile(inImgFilePath1);
ImagePtr pInImg2 = loadTiffImageFile(inImgFilePath2);
// computation of motion transform between images
Features2dRegistrationResultPtr pOutRegistrationResult = greySignedFeaturesImg2dRegistration(pInImg1, pInImg2);
const RegistrationMotionTransform2d& outTransform = pOutRegistrationResult->getNode<Features2dRegistrationResult::Transform>();
See also
GreySignedFeaturesImg2dRegistrationLvl1

Function Documentation

◆ greySignedFeaturesImg2dRegistration() [1/6]

IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration ( const image::ImageConstPtr &  pInOriginImg2d,
const image::ImageConstPtr &  pInTargetImg2d,
const ipsdk::imaproc::attr::eRegistrationMotionModel2d &  inRegMotionModel2d 
)

wrapper function for algorithm allowing registration of 2d images using features associated to grey signature

In this case computed transformation type is defined by user

Exceptions
ipsdk::processor::IPSDKBaseProcessingExceptionon failure
Returns
best registration result

◆ greySignedFeaturesImg2dRegistration() [2/6]

IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration ( const image::ImageConstPtr &  pInOriginImg2d,
const image::ImageConstPtr &  pInTargetImg2d 
)

wrapper function for algorithm allowing registration of 2d images using features associated to grey signature

In this case we compute a rigid transformation

Exceptions
ipsdk::processor::IPSDKBaseProcessingExceptionon failure
Returns
best registration result

◆ greySignedFeaturesImg2dRegistration() [3/6]

IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration ( const image::ImageConstPtr &  pInOriginImg2d,
const image::ImageConstPtr &  pInTargetImg2d,
const attr::ScaleCandidatesConstPtr &  pInScaleCandidates 
)

wrapper function for algorithm allowing registration of 2d images using features associated to grey signature

In this case we compute a similarity transformation

Exceptions
ipsdk::processor::IPSDKBaseProcessingExceptionon failure
Returns
best registration result

◆ greySignedFeaturesImg2dRegistration() [4/6]

IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration ( const image::ImageConstPtr &  pInOriginImg2d,
const image::ImageConstPtr &  pInTargetImg2d,
const ipsdk::imaproc::attr::ScaleCandidatesConstPtr &  pInScaleCandidates,
const ipReal32  inGradStdDev,
const attr::GaussianCoverageConstPtr &  pInOptGradientGaussianCoverage,
const ipsdk::imaproc::attr::CornerDetectionParamsConstPtr &  pInCornerDetectionParams2d,
const ipUInt32  inNbFeatures,
const ipUInt32  inFeaturesDistX,
const ipUInt32  inFeaturesDistY,
const ipsdk::imaproc::attr::eInterpolationPolicy &  inInterpolationPolicy,
const ipsdk::imaproc::attr::SamplingBallInfoConstPtr &  pInSamplingBallInfo2d,
const ipsdk::imaproc::attr::eRegistrationMotionModel2d &  inRegMotionModel2d,
const ipReal64  inCorrelationThreshold2d,
const ipsdk::imaproc::attr::RobustEstimationConfigConstPtr &  pInOptRegistrationEstimationConfig,
const ipsdk::imaproc::attr::Features2dRegistrationResultsPtr &  pOutFeatures2dRegistrationResults 
)

wrapper function for algorithm allowing registration of 2d images using features associated to grey signature

In this case computed transformation type is defined by user

Exceptions
ipsdk::processor::IPSDKBaseProcessingExceptionon failure
Returns
best registration result

◆ greySignedFeaturesImg2dRegistration() [5/6]

IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration ( const image::ImageConstPtr &  pInOriginImg2d,
const image::ImageConstPtr &  pInTargetImg2d,
const ipReal32  inGradStdDev,
const ipUInt32  inNbFeatures,
const ipUInt32  inFeaturesDist,
const attr::Features2dRegistrationResultsPtr &  pOutFeatures2dRegistrationResults 
)

wrapper function for algorithm allowing registration of 2d images using features associated to grey signature

In this case we compute a rigid transformation

Exceptions
ipsdk::processor::IPSDKBaseProcessingExceptionon failure
Returns
best registration result

◆ greySignedFeaturesImg2dRegistration() [6/6]

IPSDKIPLREGISTRATION_API attr::Features2dRegistrationResultPtr ipsdk::imaproc::registration::greySignedFeaturesImg2dRegistration ( const image::ImageConstPtr &  pInOriginImg2d,
const image::ImageConstPtr &  pInTargetImg2d,
const attr::ScaleCandidatesConstPtr &  pInScaleCandidates,
const ipReal32  inGradStdDev,
const ipUInt32  inNbFeatures,
const ipUInt32  inFeaturesDist,
const attr::Features2dRegistrationResultsPtr &  pOutFeatures2dRegistrationResults 
)

wrapper function for algorithm allowing registration of 2d images using features associated to grey signature

In this case we compute a similarity transformation

Exceptions
ipsdk::processor::IPSDKBaseProcessingExceptionon failure
Returns
best registration result
Generated on Tue Apr 15 2025 16:24:06 for IPSDK by   doxygen 1.8.14