Counting Australian coins in matlab

Question

Jamil 2013-6-2

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/77721-counting-australian-coins-in-matlab

Hi, I need to write a function that calculates how many coins are in a picture and determines there combined value, I have the following code that works for a stock image, but I cant seem to apply it to work with an image containing Australian coins, such as this:

Here is the current code I have:

_______________________________________________________
coin1 = im2bw(imread('coins.png'));
coin2 = imfill(coin1,'holes');
[L Ne]=bwlabel(double(coin2));
prop=regionprops(L,'Area','Centroid');
total=0;
imshow(imread('coins.png'));hold on
for n=1:size(prop,1)
  doll=prop(n).Centroid;
  X=doll(1);Y=doll(2);
  if prop(n).Area>2000
      text(X-10,Y,'$1') 
      total=total+1;
  else
      total=total+2;
      text(X-10,Y,'$2') 
  end
end
number = n
dollar = total
hold on
title(['Dollars: $',num2str(dollar),'  ', 'Number of coins:',num2str(n)])
_________________________________________________________________

Any help would be appreciated, thanks

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Image Analyst 2013-6-2

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/77721-counting-australian-coins-in-matlab#answer_87432

See my demo where I do the same thing with the US coins supplied in the standard MATLAB demo image: http://www.mathworks.com/matlabcentral/fileexchange/25157-image-segmentation-tutorial-blobsdemo I find 5 cent and ten cent coins. Of course from that point it's a simple matter to add up the value of the coins.

Just a quick glance looks like your code should work as long as there are only two type of coins and those with area more than 2000 all have the same value and those with area less than that all have the same value. What is not working?

11 个评论
显示 9更早的评论隐藏 9更早的评论

Image Analyst 2013-6-3

在 MATLAB Online 中打开

Try this, it was the best I could do in 5 minutes but it gets the job done:

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
imtool close all;  % Close all imtool figures if you have the Image Processing Toolbox.
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;
% Read in a standard MATLAB gray scale demo image.
folder = 'C:\Users\Mark\Documents\Temporary';
baseFileName = 'coins.jpg';
% Get the full filename, with path prepended.
fullFileName = fullfile(folder, baseFileName);
grayImage = imread(fullFileName);
[rows, columns, numberOfColorBands] = size(grayImage);
if numberOfColorBands > 1
  % It's not really gray scale like we expected - it's color.
  % Convert it to gray scale by taking only the green channel.
  grayImage = grayImage(:, :, 2); % Take green channel.
end
% Display the original gray scale image.
subplot(2, 2, 1);
imshow(grayImage, []);
title('Original Grayscale Image', 'FontSize', fontSize);
% Enlarge figure to full screen.
set(gcf, 'units','normalized','outerposition',[0 0 1 1]);
% Give a name to the title bar.
set(gcf,'name','Demo by ImageAnalyst','numbertitle','off') 
% Let's compute and display the histogram.
[pixelCount, grayLevels] = imhist(grayImage);
subplot(2, 2, 2); 
bar(pixelCount);
grid on;
title('Histogram of original image', 'FontSize', fontSize);
xlim([0 grayLevels(end)]); % Scale x axis manually.
binaryImage = grayImage < 240
subplot(2, 2, 3); 
imshow(binaryImage, []);
title('Binary Image', 'FontSize', fontSize);
% Fill holes
binaryImage = bwconvhull(binaryImage, 'objects', 4);
subplot(2, 2, 4); 
imshow(binaryImage, []);
title('Binary Image', 'FontSize', fontSize);
% Get rid of particles smaller than 2000 pixels.
binaryImage = bwareaopen(binaryImage, 2000);
% Label image.
[LabeledImage, numberOfCoins]=bwlabel(binaryImage);
% Make measurements of centroid and area.
measurements = regionprops(LabeledImage,'Area','Centroid');
% Print out areas.
allAreas = [measurements.Area]
total=0;
hold on
% Loop through, counting and labeling coins.
for n=1:size(measurements,1)
  centroid = measurements(n).Centroid;
  X=centroid(1);
  Y=centroid(2);
  if measurements(n).Area > 3000
    text(X-10,Y,'$1')
    total=total+1;
  else
    total=total+2;
    text(X-10,Y,'$2')
  end
end
number = n
dollar = total
hold on
title(['Dollars: $',num2str(dollar),'  ', 'Number of coins:',num2str(n)],...
  'FontSize', fontSize)

Jamil 2013-6-3

Im not sure, I assume the coins are less than 2000 pixels, but then i cant imagine why it worked fine for my stock image, sorry like i said im new to matlab and im multitasking this task with a bunch of others, ive found this to be very confusing im not sure what i need to change in the code

Jamil 2013-6-3