image = adaptiveThresholdMean3dImg (inImg3d,halfKnlSize)

Detailed Description

binarize a 3d input image according an adaptive threshold based on the mean intensity of the voxel's neighbourhood

For each voxel, the algorithm computes a threshold according to a neighbourhood described by $InKnlSize$ . The computed threshold $T$ is the mean intensity along the voxel's neighbourhood $\aleph$ :

$T(x, y, z) = \frac{1}{N} \sum_{(i, j, k) \in \aleph}{InImg(x+i, y+j, z+k)}$

Where $N$ is the number of voxels in $\aleph$ .

This algorithm is equivalent to the Adaptive Threshold 3d binarization algorithm, with each kernel coefficient set to $1/N$ . However, it is optimized to compute a mean adaptive threshold based binarization and yields better performances.

Note: To avoid a noisy binarization, it is advised to filter the input image with a median filter before computing the binarization.

See Adaptive Threshold Mean 2d for a 2d example of the adaptative mean threshold result.

Example of Python code :

Example imports

import PyIPSDK

import PyIPSDK.IPSDKIPLBinarization as bin

Code Example

    # opening of input images
    inImg = PyIPSDK.loadTiffImageFile(inputImgPath)
    
    # threshold computation with a given kernel
    outImg = bin.adaptiveThresholdMean3dImg(inImg, halfKnlSize)

Example of C++ code :

Example informations

Header file

#include <IPSDKIPL/IPSDKIPLBinarization/Processor/AdaptiveThresholdMean3dImg/AdaptiveThresholdMean3dImg.h>

Code Example

            // Sample with a generated output image
            // ------------------------------------
            // compute absolute value of input image
            ImagePtr pAutoOutImg = adaptiveThresholdMean3dImg(pInImg, halfKnlSize);
            // Sample with a provided output image
            // -----------------------------------
            // Retrieve the input image size
            const ipUInt64 sizeX = pInImg->getSizeX();
            const ipUInt64 sizeY = pInImg->getSizeY();
            const ipUInt64 sizeZ = pInImg->getSizeZ();
            // create output image
            ImageGeometryPtr pOutputImageGeometry = geometry3d(eImageBufferType::eIBT_Binary, sizeX, sizeY, sizeZ);
            boost::shared_ptr<MemoryImage> pOutImg(boost::make_shared<MemoryImage>());
            pOutImg->init(*pOutputImageGeometry);
            // compute absolute value of input image
            adaptiveThresholdMean3dImg(pInImg, halfKnlSize, pOutImg);