Calculate the size of the smallest rice grain in the image.

Hi,I want to calculate the size of the smallest rice grain in the image

so that I can use it in my function to get a decision that, if the size is less than I want, to treat it as noise and don't count it. Please guide me.

[Bharti Patel]

Respected Authors,

How to get dataset for rice grain counting. Please provide me this type of images.

[Image Analyst]

We do not have photos for you but you can easily create your own.

1. Get a bag or box of rice.
2. Spread some grains out on a uniformly colored surface. Preferably something not the same color as the rice. Black velvet will work very nicely.
3. Take your camera (webcam, DSLR, or smartphone) and snap some photos.

[Walter Roberson]

Black velvet might not be suitable for black rice or wild rice ;-) https://en.wikipedia.org/wiki/Black_rice

Answer 1

[Image Analyst]

Try this:

% function testRGBImage()
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 = 20;

%===============================================================================
% Get the name of the image the user wants to use.
baseFileName = 'ricesam2.jpg';
folder = fileparts(which(baseFileName)); % Determine where demo folder is (works with all versions).
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 the original image.
subplot(2, 2, 1);
imshow(rgbImage, []);
axis on;
caption = sprintf('Original Color Image, %s', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

% 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;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.

% Get a mask of the blue channel
binaryImage = rgbImage(:,:,3) < 173;
% Get rid of junk near edge of image.
binaryImage = imclearborder(binaryImage);
% Display the mask image.
subplot(2, 2, 2);
imshow(binaryImage, []);
axis on;
caption = sprintf('Binary Image');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

% Filter out blobs smaller than 100 or bigger than 1000
binaryImage = bwareafilt(binaryImage, [100, 1000]);
% Display the mask image.
subplot(2, 2, 3);
imshow(binaryImage, []);
axis on;
caption = sprintf('Size Filtered Image');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

% Find the areas of what's left.
props = regionprops(binaryImage, 'Area');
allAreas = [props.Area]
% Display the distribution of areas.
subplot(2, 2, 4);
histogram(allAreas);
axis on;
grid on;
title('Histogram of Areas', 'FontSize', fontSize, 'Interpreter', 'None');

message = sprintf('The smallest area = %.1f pixels', min(allAreas));
uiwait(helpdlg(message));

You could do a better job by improving the contrast with better lighting or a contrasting color (e.g. black) background material, and reducing the background illumination non-uniformity by using a better lens or by dividing your image by the image of a blank white sheet.

Answer 2

[Akira Agata]

Here is another try:

% Read the image
I = imread('ricesam2.jpg');
Igray = rgb2gray(I);

% Extract target regions
BW = edge(Igray);
se90 = strel('line', 2, 90);
se0 = strel('line', 2, 0);
BW2 = imdilate(BW,[se90 se0]);
BWfill = imfill(BW2,'holes');
seD = strel('diamond',3);
BWfinal = imerode(BWfill,seD);

% Measure the statistics
stats = regionprops(BWfinal,{'Area','Centroid'});
stats = struct2table(stats);

% Show the result
figure
imshow(I)
hold on
for kk = 1:height(stats)
  text(stats.Centroid(kk,1)+10, stats.Centroid(kk,2),...
      num2str(stats.Area(kk)))
end

Answer 3

[Walter Roberson]

regionprops() of MajorAxisLength to get the "size" of the items.

bwareafilt() to do the filtering.