3d Canny surface detector

Detects surfaces in a 3d image using Canny's algorithm. More...

IPSDKIPLFEATUREDETECTION_API image::ImagePtr	ipsdk::imaproc::fd::cannySurfaces3dImg (const image::ImageConstPtr &pInGxImg3d, const image::ImageConstPtr &pInGyImg3d, const image::ImageConstPtr &pInGzImg3d, const ipsdk::imaproc::attr::CannyThresholdsConstPtr &pThresholds)
	wrapper function for detection of edges in images using Canny's algorithm More...
IPSDKIPLFEATUREDETECTION_API void	ipsdk::imaproc::fd::cannySurfaces3dImg (const image::ImageConstPtr &pInGxImg3d, const image::ImageConstPtr &pInGyImg3d, const image::ImageConstPtr &pInGzImg3d, const ipsdk::imaproc::attr::CannyThresholdsConstPtr &pThresholds, const ipsdk::imaproc::attr::eProcessingOptimizationPolicy &inOptOptimizationPolicy, const image::ImagePtr &pOutImg)
	wrapper function for detection of edges in images using Canny's algorithm More...

Detailed Description

Detects surfaces in a 3d image using Canny's algorithm.

Detects boundary surfaces in a 3d image using Canny's algorithm, and generates an output binary image, with voxels associated to the found surfaces in white, and the rest in black.

Given 3 gradient images (computed, for instance, thanks to Sobel Gradient 3d or Gaussian Gradient 3d), respectively along x (Gx image), y (Gy image) and z-axis (Gz image), Canny surface detector can be decomposed into the following steps:

1. from Gx, Gy and Gz images, magnitude and orientation of gradient is computed
2. non-maxima suppression: for each voxel in the image of gradient magnitude, if the pixel value is greater than the values of its 2 neighbours along the gradient direction, then the pixel is marked as "to be processed"; otherwise, it is marked as "not a boundary surface". This step prevents from having too thick boundary surfaces.
3. for all voxels tagged "to be processed", mark as:
   • "not a boundary surface" voxels whose gradient magnitude value is lower than low threshold value specified by the user
   • "strong boundary surface" voxels whose gradient magnitude value is higher than high threshold value specified by the user
   • "perhaps a boundary surface" voxels whose gradient magnitude value is between low and high threshold values
4. process voxels tagged "perhaps a boundary surface": a voxel tagged "perhaps a boundary surface" is a strong boundary surface if it is directly or indirectly (ie. there exists a path of connected voxels tagged "perhaps a boundary surface" that link the current voxel to a "strong boundary surface" voxel) connected to a "strong boundary surface" voxel. Otherwise it is affected the "not a boundary surface" value.

See 2d Canny edge detector for an illustration of Canny edge detection applied to a 2d image.

Attributes description

Attribute description for algorithm :

Name	ToolTip	Default Initializer
ipsdk::imaproc::attr::InGxGreyImg3d	[Input] 3d grey levels image of gradient computed along x-axis	X
ipsdk::imaproc::attr::InGyGreyImg3d	[Input] 3d grey levels image of gradient computed along y-axis	X
ipsdk::imaproc::attr::InGzGreyImg3d	[Input] 3d grey levels image of gradient computed along z-axis	X
ipsdk::imaproc::attr::InCannyThresholds	[Input] low and high thresholds used for the Canny edges detection during the hysteresis phasis	X
ipsdk::imaproc::attr::InOptOptimizationPolicy	[Input Optional] processing optimization policy for algorithm	X
ipsdk::imaproc::attr::OutOptWk1BinImg	[Output Optional] Temporary working image for algorithm	X
ipsdk::imaproc::attr::OutOptWk2BinImg	[Output Optional] Temporary working image for algorithm	X
ipsdk::imaproc::attr::OutOptWk1LabelImg	[Output Optional] Temporary working image for algorithm	X
ipsdk::imaproc::attr::OutBinImg	[Output] binary image for processing operation	ipsdk::imaproc::duplicateInOut (_pOutBinImg, _pInGxGreyImg3d, ipsdk::image::eImageBufferType::eIBT_Binary)

Global Rule description

Global rule description for algorithm :
ipsdk::imaproc::matchSize (_pInGxGreyImg3d,_pInGyGreyImg3d) && 
ipsdk::imaproc::matchSize (_pInGxGreyImg3d,_pInGzGreyImg3d) && 
ipsdk::imaproc::matchSize (_pInGxGreyImg3d,_pOutBinImg) && 
(ipsdk::processor::ifIsSet (
  _pOutOptWk1BinImg, (
   ipsdk::imaproc::matchSize (_pInGxGreyImg3d,_pOutOptWk1BinImg)))) && 
(ipsdk::processor::ifIsSet (
  _pOutOptWk2BinImg, (
   ipsdk::imaproc::matchSize (_pInGxGreyImg3d,_pOutOptWk2BinImg)))) && 
(ipsdk::processor::ifIsSet (
  _pOutOptWk1LabelImg, (
   ipsdk::imaproc::matchSize (_pInGxGreyImg3d,_pOutOptWk1LabelImg))))

Example of Python code :

Example imports

import PyIPSDK
import PyIPSDK.IPSDKIPLFeatureDetection as fd
import PyIPSDK.IPSDKIPLFiltering as filter

Code Example

    # opening of input image
    inImg = PyIPSDK.loadTiffImageFile(inputImgPath)
    inImg = filter.gaussianSmoothing3dImg(inImg, 1.0);
    
    # associated gradient images computation
    gxImg,  gyImg, gzImg = filter.sobelGradient3dImg(inImg, PyIPSDK.eSobelKernelType.eSKT_SobelHalfKnlSz1, True)
    
    outImg = fd.cannySurfaces3dImg(gxImg, gyImg, gzImg, PyIPSDK.createCannyThresholds(50, 100))
    

Example of C++ code :

Example informations

Associated library

IPSDKIPLFeatureDetection

Header file

#include <IPSDKIPL/IPSDKIPLFeatureDetection/Processor/CannySurfaces3dImg/CannySurfaces3dImg.h>

Code Example

    ImageConstPtr pInImg = loadTiffImageFile(inImgPath);

    ImageGeometryPtr pGradGeometry = geometry3d(eImageBufferType::eIBT_Real32, pInImg->getSizeX(), pInImg->getSizeY(), pInImg->getSizeZ());

    boost::shared_ptr<MemoryImage> pGxImg = boost::make_shared<MemoryImage>();
    pGxImg->init(*pGradGeometry);
    boost::shared_ptr<MemoryImage> pGyImg = boost::make_shared<MemoryImage>();
    pGyImg->init(*pGradGeometry);
    boost::shared_ptr<MemoryImage> pGzImg = boost::make_shared<MemoryImage>();
    pGzImg->init(*pGradGeometry);

    ImageGeometryPtr pOutGeometry = geometry3d(eImageBufferType::eIBT_Binary, pInImg->getSizeX(), pInImg->getSizeY(), pInImg->getSizeZ());
    boost::shared_ptr<MemoryImage> pOutImg = boost::make_shared<MemoryImage>();
    pOutImg->init(*pOutGeometry);

    filter::sobelGradient3dImg(pInImg, eSobelKernelType::eSKT_SobelHalfKnlSz1, false, pGxImg, pGyImg, pGzImg);
    cannySurfaces3dImg(pGxImg, pGyImg, pGzImg, pThresholds, eProcessingOptimizationPolicy::ePOP_MaximizeSpeed, pOutImg);

See also

CannySurfaces3dImgLvl1

CannySurfaces3dImgLvl2

CannySurfaces3dImgLvl3

Function Documentation

cannySurfaces3dImg() [1/2]

IPSDKIPLFEATUREDETECTION_API image::ImagePtr ipsdk::imaproc::fd::cannySurfaces3dImg	(	const image::ImageConstPtr &	pInGxImg3d,
		const image::ImageConstPtr &	pInGyImg3d,
		const image::ImageConstPtr &	pInGzImg3d,
		const ipsdk::imaproc::attr::CannyThresholdsConstPtr &	pThresholds
	)

wrapper function for detection of edges in images using Canny's algorithm

Exceptions

ipsdk::processor::IPSDKBaseProcessingException

on failure

cannySurfaces3dImg() [2/2]

IPSDKIPLFEATUREDETECTION_API void ipsdk::imaproc::fd::cannySurfaces3dImg	(	const image::ImageConstPtr &	pInGxImg3d,
		const image::ImageConstPtr &	pInGyImg3d,
		const image::ImageConstPtr &	pInGzImg3d,
		const ipsdk::imaproc::attr::CannyThresholdsConstPtr &	pThresholds,
		const ipsdk::imaproc::attr::eProcessingOptimizationPolicy &	inOptOptimizationPolicy,
		const image::ImagePtr &	pOutImg
	)

wrapper function for detection of edges in images using Canny's algorithm

Exceptions

ipsdk::processor::IPSDKBaseProcessingException

on failure