MATLAB Answers

Kim
0

How to crop out the barcode??

Asked by Kim
on 11 Feb 2012
Latest activity Edited by Cedric Wannaz
on 8 Oct 2013
I have found out the way to determine the barcode and currently working on cropping out the barcode. How can I write the code so that it can crop out the barcode?? I have paste my original image and my coding below.
Original Image
Processed Image
% Read Image
rgb = imread('barcode.jpg');
% Resize Image
rgb = imresize(rgb,0.33);
%figure(),imshow(rgb);
% Convert from RGB to Gray
Igray = rgb2gray(rgb);
BW2 = edge(Igray,'canny');
%figure(),imshow(BW2);
% Perform the Hough transform
[H, theta, rho] = hough(BW2);
% Find the peak pt in the Hough transform
peak = houghpeaks(H);
% Find the angle of the bars
barAngle = theta(peak(2));
J = imrotate(rgb,barAngle,'bilinear','crop');
%figure(),imshow(J);
Jgray = double(rgb2gray(J));
% Calculate the Gradients
[dIx, dIy] = gradient(Jgray);
%if min(dIx(:))<= -100 && max(dIx(:))>=100 || min(dIy(:))<=-100 && max(dIy(:))>=100
if barAngle <= 65 && barAngle >=-65 && min(dIx(:))<= -100
B = abs(dIx) - abs(dIy);
else
B = abs(dIy) - abs(dIx);
end
% Low-Pass Filtering
H = fspecial('gaussian', 20, 10);
C = imfilter(B, H);
C = imclearborder(C);
%figure(),imshow(C);
figure(),imagesc(C);colorbar;

  0 Comments

Sign in to comment.

3 Answers

Answer by Chandra Kurniawan on 12 Feb 2012
 Accepted Answer

D = C > 20;
Ilabel = bwlabel(D);
stat = regionprops(Ilabel,'boundingbox');
for x = 1 : length(stat)
Icrop{x} = imcrop(J,stat(x).BoundingBox);
end

  0 Comments

Sign in to comment.


Image Analyst
Answer by Image Analyst
on 11 Feb 2012

Looks like thresholding at about 20 should do it. Then label and use regionprops to do size filtering and get the bounding box. Then use imcrop to do the cropping.

  2 Comments

Kim
on 11 Feb 2012
How can I implement this to my coding??
Image Analyst
on 12 Feb 2012
Looks like Chandra provided that to you. If you want just the biggest blob though, you'd have to do it slightly differently.

Sign in to comment.


Answer by Andrea Carron on 16 Feb 2012

I tried to use the code posted by Kim with the image above, but I obtained this figure:
How is it possible?

  0 Comments

Sign in to comment.