get the width of bounding box

i'm trying to make a size sorter but ran into a problem; does anyone know how to make matlab draw a box around this potato and then determine the width of this box?

Answer 1

[Akira Agata]

It seems that regionprops function will be helpful, like:

% Read the image and binarize
I = imread('aardappels.jpg');

% Create the region of interest (ROI)
Igray = rgb2gray(I);
ROI = ~imbinarize(Igray, 0.9);
ROI = bwconvhull(ROI);

% Measure properties of the ROI
stats = regionprops(ROI, 'BoundingBox','MajorAxisLength','MinorAxisLength');

% Show the result
imshow(I);
hold on;
rectangle('Position', stats.BoundingBox,'EdgeColor','b');

The major and minor axis of the bounding box is stored in stats.

>> stats
stats = 
  BoundingBox: [53.5000 68.5000 698 883]
  MajorAxisLength: 899.6647
  MinorAxisLength: 708.4894

[wille spri]

best Akira Agata, Frist I want to say thanks for the time and your answer, but do you perhaps know a simple way to make sure that the potato is always in the smallest possible box? if, for example the potato on the picture is rotated (like in this picture(test.jpg)) can the box be rotated with it, so I can still get the width of the potato?(like in potatobox.png) thanks for the help.

[Akira Agata]

Hi wille-san,

In my script, unfortunately, the potato is NOT always in the smallest box if rotated. But I have an idea to obtain such a bounding box. Please give me a few more days :-)

[Akira Agata]

I've just modified. As far as shape of a potato is similar to ellipse, I believe it works!

% Read the image and binarize
I = imread('test.jpg');

% Create the region of interest (ROI)
Igray = rgb2gray(I);
ROI = ~imbinarize(Igray, 0.9);
ROI = bwconvhull(ROI);

% Measure properties of the ROI
stats = regionprops(ROI,...
  'Centroid','MajorAxisLength','MinorAxisLength','Orientation');

% Make position array of rectangle w/o rotation and translate
pos = [-stats.MajorAxisLength/2, -stats.MinorAxisLength/2,...
  stats.MajorAxisLength, stats.MinorAxisLength];

% Show the result
imshow(I)
hold on
g = hgtransform;
g.Matrix = makehgtform('translate',[stats.Centroid, 0])*...
  makehgtform('zrotate', -deg2rad(stats.Orientation));
rectangle('Position', pos,'EdgeColor','b','Parent',g)

The result is stored in stats:

>> stats
stats = 

           Centroid: [727.8221 735.9809]
    MajorAxisLength: 1.4733e+03
    MinorAxisLength: 935.3463
        Orientation: 17.0534

Answer 2

[jue xi]

can i know the major/minor axis length unit? cos i need to get the measurement in cm. so i need to know its unit to convert it to cm. tq

[Akira Agata]

The major/minor axis length is in pixels. So, to measure in cm, you need to know the ratio of pixel-length in your image against cm in real world.

[jue xi]

thank you.. but here one more question.. how to get the ratio of pixel-length in my image ? i have the manual measurement in cm but in pixel..?

if true
  % code 
folder=('C:\Users\user\MATLAB');
  baseFileName=('img11.jpg');
  fullFileName=fullfile(folder,baseFileName);
  format long g;
  format compact;
  fontSize = 20;
  %IMAGE SEGMENTATION
  img=imread(fullFileName);
  img=rgb2ycbcr(img);
  for i=1:size(img,1)
      for j= 1:size(img,2)
          cb = img(i,j,2);
          cr = img(i,j,3);
          if(~(cr > 132 && cr < 173 && cb > 76 && cb < 126))
              img(i,j,1)=235;
              img(i,j,2)=128;
              img(i,j,3)=128;
          end
      end
  end
  img=ycbcr2rgb(img);
  subplot(2,2,1);
  image1=imshow(img);
  axis on;
  title('Skin Segmentation', 'FontSize', fontSize);
  set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);
  %SEGMENTED IMAGE TO GRAYIMAGE
  grayImage=rgb2gray(img);
  subplot(2,2,2);
  image2=imshow(grayImage);
  axis on;
  title('Original Grayscale Image', 'FontSize', fontSize);
  set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);
 %GRAY TO BINARY IMAGE
  binaryImage = grayImage < 245;
  subplot(2, 2, 3);
  axis on;
  image3=imshow(binaryImage, []);
  title('Binary Image', 'FontSize', fontSize);
  % Label the image 
  labeledImage = bwlabel(binaryImage);  % label the connected components in an image and assigning each one a unique label
  measurements = regionprops(labeledImage, 'BoundingBox', 'Area');
  for k = 1 : length(measurements)
    thisBB = measurements(k).BoundingBox;
    rectangle('Position', [thisBB(1),thisBB(2),thisBB(3),thisBB(4)],...
    'EdgeColor','r','LineWidth',2 )
  end
  % Let's extract the second biggest blob - that will be the hand.
  allAreas = [measurements.Area];
  [sortedAreas, sortingIndexes] = sort(allAreas, 'descend');
  handIndex = sortingIndexes(2); % The hand is the second biggest, face is biggest.
  % Use ismember() to extact the hand from the labeled image.
  handImage = ismember(labeledImage, handIndex);
  % Now binarize
  handImage = handImage > 0;
  % Display the image.
  subplot(2, 2, 4);
  image4=imshow(handImage, []);
  axis on;
  axis image;
  title('Hand Image', 'FontSize', fontSize);
   % Label the image 
  labeledImage = bwlabel(handImage);  % label the connected components in an image and assigning each one a unique label
  measurements = regionprops(labeledImage, 'BoundingBox', 'Area');
  for k = 1 : length(measurements)
    thisBB = measurements(k).BoundingBox;
    rectangle('Position', [thisBB(1),thisBB(2),thisBB(3),thisBB(4)],...
    'EdgeColor','r','LineWidth',2 )
  end
  % Make measurements of bounding box
props = regionprops(labeledImage, 'BoundingBox');
width = props.BoundingBox(3);
height = props.BoundingBox(4);
hold on;
rectangle('Position', props.BoundingBox, 'EdgeColor', 'r', 'LineWidth', 2);
message = sprintf('The width = %f.\nThe height = %f', width, height);
uiwait(helpdlg(message));
end

[Akira Agata]

OK, let's take a look at these two images. They show the same contents --- red rectangle with 3cm width --- in different resolution.

Then, by using imtool or something, you can measure the length of the width in pixel for each file. The result will be as follows (around 114 pixels and 183 pixels, respectively).

Since the resolution of each picture is different, pixel length becomes different even when the same object in real world. That's why you have to know the ratio between pixel length and cm in real world (in this case, 3/114 [cm/pixel] for the first picture, and 3/183 [cm/pixel] for the second).

scale1.jpg:

scale2.jpg:

[jue xi]

i see, i'll try it,thanks you btw for your time.

Answer 3

[jue xi]

is this what u mean? if im not mistaken. my ratio is 4:3

Answer 4

[jue xi]

hi, i combining this coding to convert it to cm.. is this the right coding to use?

if true
  % codeprops = regionprops(labeledImage, 'BoundingBox','MajorAxisLength');
X= props.BoundingBox(3);
Y = props.BoundingBox(4);
res=info.ResolutionUnit;
resX=info.XResolution;
resY=info.YResolution;
if strcmp( res,'Inch');
  width=2.54*X/resX;
  height=2.54*Y/resY;
else
  width=X/ resX;
  height=Y/resY;
end
fprintf('X Resolution = %.2f %s\n', resX, res);
fprintf('Y Resolution = %.2f %s\n', resY, res);
disp('Size of Object:');
fprintf('Width = %.2f cm\n', width);
fprintf('Height = %.2f cm\n', height);
end

then after i get the width and height, i apply the Pythagoras theorem to get the hand measurement from elbow line to finger.. below are the whole coding to get as pic above..

[jue xi]

if true
  % code
folder=('C:\Users\user\MATLAB');
  baseFileName=('img2.jpg');
  info=imfinfo(baseFileName);
  fullFileName=fullfile(folder,baseFileName);
  format long g;
  format compact;
  fontSize = 20;
%IMAGE SEGMENTATION
  img=imread(fullFileName);
  img=rgb2ycbcr(img);
  for i=1:size(img,1)
      for j= 1:size(img,2)
          cb = img(i,j,2);
          cr = img(i,j,3);
          if(~(cr > 132 && cr < 173 && cb > 76 && cb < 126))
              img(i,j,1)=235;
              img(i,j,2)=128;
              img(i,j,3)=128;
          end
      end
  end
  img=ycbcr2rgb(img);
  subplot(2,2,1);
  image1=imshow(img);
  axis on;
  title('Skin Segmentation', 'FontSize', fontSize);
  set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);
  %SEGMENTED IMAGE TO GRAYIMAGE
  grayImage=rgb2gray(img);
  subplot(2,2,2);
  image2=imshow(grayImage);
  axis on;
  title('Original Grayscale Image', 'FontSize', fontSize);
  set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);
 %GRAY TO BINARY IMAGE
  binaryImage = grayImage < 245;
  subplot(2, 2, 3);
  axis on;
  image3=imshow(binaryImage, []);
  title('Binary Image', 'FontSize', fontSize);
  % Label the image 
  labeledImage = bwlabel(binaryImage);  % label the connected components in an image and assigning each one a unique label
  measurements = regionprops(labeledImage, 'BoundingBox', 'Area');
  for k = 1 : length(measurements)
    thisBB = measurements(k).BoundingBox;
    rectangle('Position', [thisBB(1),thisBB(2),thisBB(3),thisBB(4)],...
    'EdgeColor','r','LineWidth',2 )
  end
  % Let's extract the second biggest blob - that will be the hand.
  allAreas = [measurements.Area];
  [sortedAreas, sortingIndexes] = sort(allAreas, 'descend');
  handIndex = sortingIndexes(2); % The hand is the second biggest, face is biggest.
  % Use ismember() to extact the hand from the labeled image.
  handImage = ismember(labeledImage, handIndex);
  % Now binarize
  handImage = handImage > 0;
  % Display the image.
  subplot(2, 2, 4);
  image4=imshow(handImage, []);
  axis on;
  axis image;
  title('Hand Image', 'FontSize', fontSize);
   % Label the image 
  labeledImage = bwlabel(handImage);  % label the connected components in an image and assigning each one a unique label
  measurements = regionprops(labeledImage, 'BoundingBox', 'MajorAxisLength');
  for k = 1 : length(measurements)
    thisBB = measurements(k).BoundingBox;
    rectangle('Position', [thisBB(1),thisBB(2),thisBB(3),thisBB(4)],...
    'EdgeColor','r','LineWidth',2 )
  end
% Make measurements of bounding box
props = regionprops(labeledImage, 'BoundingBox','MajorAxisLength');
X= props.BoundingBox(3);
Y = props.BoundingBox(4);
res=info.ResolutionUnit;
resX=info.XResolution;
resY=info.YResolution;
if strcmp( res,'Inch');
  width=2.54*X/resX;
  height=2.54*Y/resY;
else
  width=X/ resX;
  height=Y/resY;
end
fprintf('X Resolution = %.2f %s\n', resX, res);
fprintf('Y Resolution = %.2f %s\n', resY, res);
disp('Size of Object:');
fprintf('Width = %.2f cm\n', width);
fprintf('Height = %.2f cm\n', height);
hold on;
rectangle('Position', props.BoundingBox, 'EdgeColor', 'r', 'LineWidth', 2);
message = sprintf('The width = %f.\nThe height = %f', width, height);
uiwait(helpdlg(message));
end