removal of shadow area

I have used adaptive thresholding technique to distinguish foreground and background pixel as per the attachment in the link. https://www.mathworks.com/matlabcentral/fileexchange/8647-local-adaptive-thresholding?focused=6119920&tab=function

I have incorporated connected component analysis to the threshold coding.

I am attaching input and thresholded image here. Can anyone suggest me how to remove the shadow part alone.

   function bw=adaptivethreshold(IM,ws,C,tm)

    if (nargin<3)
        error('You must provide the image IM, the window size ws, and C.');
    elseif (nargin==3)
        tm=0;
    elseif (tm~=0 && tm~=1)
        error('tm must be 0 or 1.');
    end

    IM=mat2gray(IM);

    if tm==0
        mIM=imfilter(IM,fspecial('average',ws),'replicate');
    else
        mIM=medfilt2(IM,[ws ws]);
    end
    sIM=mIM-IM-C;
    bw=im2bw(sIM,0);
    bw=imcomplement(bw);

Test Code:

clear;
close all;
  % im1=imread('inputimage.jpg');
  im2=imread('foregroundimage.jpg');
  % bwim1=adaptivethreshold(im1,11,0.03,0);
  bwim2=adaptivethreshold(im2,15,0.02,0);
  % ModeFilterFunction = @(x) mode(x(:));
  % modeImage = nlfilter(bwim2, [3 3], ModeFilterFunction);
  CC = bwconncomp(bwim2,8);
  S = regionprops(CC, 'Area');
  L = labelmatrix(CC);
  BW2 = ismember(L, find([S.Area] >= 100));
   subplot(2, 2, 3);
  imshow(BW2, []);
  subplot(2,2,1);
  imshow(im2);
  subplot(2,2,2);
  imshow(bwim2);

[Image Analyst]

You forgot to attach 'inputimage.jpg' and 'foregroundimage.jpg'. A .fig file does us no good.

[SHOBA MOHAN]

Sorry for inconvenience now I am attaching foreground image. Thanks for the response.

[Monisha Gowda]

Hi, Have you done it. I am also looking for the same. Can you help me on this?

Answer 1

[Malhar Ashtaputre]

Kindly go through following link for help in shadow removing:

http://lxu.me/mypapers/XuL_ShadowRemoval.pdf

[Maisha Maimuna]

Hello Malhar Ashtaputre,

have you got the solution? I am stuck with the same problem.