How do I remove the white background of any image?

I want to remove white backgrounds of the image and crop only the currency image portion.

[Walter Roberson]

Removing the white background of any image is a quite difficult task; I suspect it is impossible to do.

Removing the white background of specific images has more hope of success.

[Rosy]

background means only the white borders that are appearing in the image. I want to crop only the currency image without white border.

[Image Analyst]

Easy, but why? How is your algorithm harmed by the white frame?

[Rosy]

Thanks. When I am trying to calculate height width ratio of the currency it gives a inaccurate calculation.

Answer 1

[Image Analyst]

See attached.

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 16;

%===============================================================================
% Get the name of the image the user wants to use.
baseFileName = '200_bcg.jpg';
folder = pwd
fullFileName = fullfile(folder, baseFileName);

% Check if file exists.
if ~exist(fullFileName, 'file')
  % The file doesn't exist -- didn't find it there in that folder.
  % Check the entire search path (other folders) for the file by stripping off the folder.
  fullFileNameOnSearchPath = baseFileName; % No path this time.
  if ~exist(fullFileNameOnSearchPath, 'file')
    % Still didn't find it.  Alert user.
    errorMessage = sprintf('Error: %s does not exist in the search path folders.', fullFileName);
    uiwait(warndlg(errorMessage));
    return;
  end
end

%=======================================================================================
% Read in demo image.
rgbImage = imread(fullFileName);
% Get the dimensions of the image.
[rows, columns, numberOfColorChannels] = size(rgbImage)

% Display image.
subplot(2, 2, 1);
imshow(rgbImage, []);
axis on;
caption = sprintf('Original Color Image\n%s', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.

% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0.05 1 0.95]);
% Get rid of tool bar and pulldown menus that are along top of figure.
% set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off')
drawnow;

[mask, maskedRGBImage] = createMask(rgbImage);
% Take the largest blob only, to get rid of noise.
% mask = bwareafilt(mask, 1);
% Fill any holes in it.
mask = imfill(mask, 'holes');
% Let's assume it's supposed to be convex.  Make sure.
mask = bwconvhull(mask);

% Display the image.
subplot(2, 2, 2);
imshow(mask, []);
axis on;
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;

% Mask the image with the new, cleaned mask.
% Mask the image using bsxfun() function to multiply the mask by each channel individually.
maskedRgbImage = bsxfun(@times, rgbImage, cast(mask, 'like', rgbImage));

% Display the image.
subplot(2, 2, 3);
imshow(maskedRgbImage, []);
axis on;
title('Masked RGB Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;

% Get the equivalent bounding box.
props = regionprops(mask, 'BoundingBox');
% Crop the image
croppedImage = imcrop(rgbImage, props.BoundingBox);
% Display the image.
subplot(2, 2, 4);
imshow(croppedImage, []);
axis on;
title('Cropped RGB Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;

function [BW,maskedRGBImage] = createMask(RGB)
%createMask  Threshold RGB image using auto-generated code from colorThresholder app.
%  [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
%  auto-generated code from the colorThresholder app. The colorspace and
%  range for each channel of the colorspace were set within the app. The
%  segmentation mask is returned in BW, and a composite of the mask and
%  original RGB images is returned in maskedRGBImage.

% Auto-generated by colorThresholder app on 17-Feb-2018
%------------------------------------------------------

% Convert RGB image to chosen color space
I = rgb2hsv(RGB);

% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.000;
channel1Max = 1.000;

% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.077;
channel2Max = 1.000;

% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.000;
channel3Max = 1.000;

% Create mask based on chosen histogram thresholds
sliderBW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
  (I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
  (I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;

% Initialize output masked image based on input image.
maskedRGBImage = RGB;

% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;

end

[Image Analyst]

Tuhina's comment moved here:

Thanks. When I am trying to calculate height width ratio of the currency it gives a inaccurate calculation.

[Image Analyst]

Why do you say that? What are the physical dimensions of the bill, and why does the height and width ratio of the bounding box give a different ratio? What are the two ratios (real, and from image analysis)?

[Rosy]

No it was before with the white bcg. Now its fine. Thanks for the solution. Its help me to crop only the actual currency image for further processing.

[Rosy]

Previous answer helps me a lot . I need your help on this for further progress. Please check this one.

https://in.mathworks.com/matlabcentral/answers/389635-which-matching-algorithm-will-be-suitable-for-segment-matching

Answer 2

[mohd abdul wahed faisal faisal]

bro i want to remove outer white part(border) from image.while reading and showing it is happening like this.

[Image Analyst]

Use imclearborder to get the mask

binaryImage = grayImage == 255
borderMask = binaryImage - imclearborder(binaryImage);
grayImage(borderMask) = 0; % or whatever value you want the border to be.

[Malini Bakthavatchalam]

Sir I have a question. I have a color image , so I have to use the alpha layer remove background and find the median of the image histogram and then break them into two halfs like below and above the median and get the three images including the original color image, upper and lower rectified image and their corresponding histograms? I am able to make the code in bits and pieces but not whole thing as a script .

[Walter Roberson]

What error do you encounter when you attempt to put the three parts together?

If you are able to get all three parts working separately, you could consider putting the parts into functions, so that the functions would not interfere with each other.