How to do the image matching?

I have cropped out individual image of the objects as shown below and require to do a template matching. I have read out on this

http://www.mathworks.com/matlabcentral/fileexchange/20061-template-matching/content/tmp.m

but could not understand. How can I apply the template matching method to my current coding? thanks

Original Image:

Processed Image:

Template:

im=imread('bus70.jpg');
im=rgb2gray(im); % convert to gray scale
im=im>graythresh(im)*255; % covert to binary
siz=size(im); % image dimensions
L=bwlabel(im,8); % Label the disconnected foreground regions (using 8 conned neighbourhood)
% Get the bounding box around each object
bb=regionprops(L,'BoundingBox');
% Crop the individual objects and store them in a cell
n=max(L(:)); % number of objects
ObjCell=cell(n,1);
for i=1:n
      % Get the bb of the i-th object and offest by 2 pixels in all
      % directions
      bb_i=ceil(bb(i).BoundingBox);
      idx_x=[bb_i(1)-2 bb_i(1)+bb_i(3)+2]; %  bb_i(1) read from 1st location
      idx_y=[bb_i(2)-2 bb_i(2)+bb_i(4)+2];
      if idx_x(1)<1, idx_x(1)=1; end
      if idx_y(1)<1, idx_y(1)=1; end
      if idx_x(2)>siz(2), idx_x(2)=siz(2); end
      if idx_y(2)>siz(1), idx_y(2)=siz(1); end
      % Crop the object and write to ObjCell
      im=L==i;
      ObjCell{i}=im(idx_y(1):idx_y(2),idx_x(1):idx_x(2));
end
% Visualize the individual objects
figure
for i=1:n
    subplot(1,n,i)

      imshow(ObjCell{i})
  end
  clear im L bb n i bb_i idx_x idx_y siz

Answer 1

[David Young]

If you have the Image Processing Toolbox, use normxcorr2. In the documentation, "template" means your small image, and "A" is the large original image. You find the maximum of the result to get the accuracy of the match and the coordinates at which the best match occurs.

[lingru celine]

@David Young

thanks ,,,can i have the coding ?

[lingru celine]

@David Young

I have tried [normxcorr2], but seemed not work for matching? below is my code, any part need to modify?

cover = rgb2gray(imread('bus70.jpg'));

template = rgb2gray(imread('70blackA.jpg'));

[m n] = size(template);

Icorr = normxcorr2(template,cover);

[max_c, imax] = max(abs(Icorr(:)));

[yp, xp] = ind2sub(size(Icorr),imax(1));

xy = [(xp-n) (yp-m)];

figure, imshow(cover); hold on;

rectangle('position',[xy(1) xy(2) n m],...

'edgecolor','g','linewidth',2);