IntensityLUT = equalize (inHistogram,inOutputRange)

Detailed Description

computes look up table used to equalize an histogram

Given an input histogram $InHistoBins$ (associated to $N$ classes) and an output range for values $InOutputRange = [InOutputMin, InOutputMax]$ , output look up table $OutIntensityLUT$ is computed as follow :
We first compute cumulative distribution function :

$Cdf[i] = \sum_{j=0}^{i}{InHistoBins_{Frequency}[j]}$

Output look up table $OutIntensityLUT$ is then given by :

$OutIntensityLUT[i] = \dfrac{InOutputMax - InOutputMin}{NormFactor}Cdf[i] + InOutputMin$

where

$NormFactor = \sum_{j=0}^{N}{InHistoBins_{Frequency}[j]}$

See also: http://en.wikipedia.org/wiki/Equalization; http://en.wikipedia.org/wiki/Histogram_equalization

Example of Python code :

Example imports

import PyIPSDK
import PyIPSDK.IPSDKIPLIntensityTransform as itrans
import PyIPSDK.IPSDKIPLGlobalMeasure as glbmsr

Code Example

    # opening of input images
    inImg = PyIPSDK.loadTiffImageFile(inputImgPath)
    
    # computation of image histogram
    histo = glbmsr.histogramMsr2d(inImg)
    
    # definition of equalization range
    equalizeRange = PyIPSDK.createRange(0,  255)
    
    # equalization lut computation
    outLut = itrans.equalize(histo,  equalizeRange)

Example of C++ code :

Example informations

Header file

#include <IPSDKIPL/IPSDKIPLIntensityTransform/Processor/Equalize/Equalize.h>

Code Example

    // open input image
    ImagePtr pInImg = loadTiffImageFile(inputImgPath);
    // compute histogram of input image
    HistogramDataConstPtr pOutHistogram = histogramMsr(pInImg);
    // define an output range for operation
    RangePtr pInOutputRange(boost::make_shared<Range>());
    pInOutputRange->setValue<Range::Min>(0);
    pInOutputRange->setValue<Range::Max>(255);
    // compute histogram equalization
    IntensityLUTPtr pOutIntensityLUT = equalize(pOutHistogram, pInOutputRange);