Journal of Applied Mathematics

Research Article

Multilevel Thresholding Segmentation Based on Harmony Search Optimization

Algorithm 1

  1. Set the parameters HMS, HMCR, PAR, BW and NI.
  2. Initialize the HM and calculate the objective function value of each harmony vector.
  3. Improvise a new harmony as follows:
   for ( to ) do
      if ( < HMCR) then
       = where
      if ( < PAR) then
         where
      end if
        if
        
        end if
        if
        
        end if
      else
          , where
      end if
   end for
  4. Update the HM as
  5. If NI is completed, the best harmony vector in the HM is returned; otherwise go back to .