pcorrelationbinarization

Performs binarization on image using maximum correlation criterion.

Synopsis

pcorrelationbinarization [-m mask] [im_in|-] [im_out|-]

Description

pcorrelationbinarization classifies pixels of the input image im_in into 2 clusters: the background and the foreground. The threshold value is determined as the gray level value s that maximizes the total amount of correlation provided by the background and the foreground separately. The total amount of correlation for threshold s is:

   TC(s) = Cb(s) + Cf(s) { correlation for background + correlation for foreground }
         = -ln[G(s)*G'(s)] +2*ln[P(s)*(1-P(s))]
     where P(s) = SUM{i=0->s} [p(i)]
     and G(s) = SUM{i=0->s} [p(i)^2)]
     and G'(s) = SUM{i=s->m-1} [(p(i)^2]
     and pi = fi/W*H

The maximum correlation criterion is to determine the threshold smax such that:

TC(smax) = max TC(s)

Inputs

im_in: a grayscale image of bytes (Img2duc, Img3duc).

Outputs

im_out: a grayscale image of bytes (Img2duc, Img3duc).

Result

Returns the threshold value.

Examples

Segments the tangram pieces:

   pcorrelationbinarization tangram.pan a.pan

C++ prototype

Errc PCorrelationBinarization( const Img2duc &im_in, Img2duc &im_out );

Version française

Binarisation de l'image par maximisation de la corrélation interclasse.

Reference

J-C Yen, F-J Chang, S. Chang, "A New Criterion for Automatic Multilevel Thresholding", IEEE Trans. on Image Processing, vol. 4, no. 3, pp 370-378, 1995.

Author: Régis Clouard