How to find the green area?

I am trying to find the area within the green boundaries. How should I go about with the codes?

[Image Analyst]

Why are you starting a new thread instead of continuing your prior duplicate thread? Even if you didn't like my answer, you don't need to start a new discussion for others to answer.

[Epah]

Image Analyst, I apologise for the new thread. The answer that you have provided me on the previous thread does not help me with my matlab code. Thank you.

Answer 1

[Image Analyst]

All right, well let's start all over again here.

Do you have the coordinates of the green dots on the perimeter? I think you must because you put the green dots into the overlay, or someone did. If you don't want to use concave hull, then alpha shapes will certainly scare you off, so another approach we can take is morphology. Take the green coordinates and make it a binary image, or if someone else gave you this image and won't tell you the green coordinates, then you can extract it from the image. But with morphology because some of the green dots are spaces quite far apart compared to the others, to get those to close the gap we need to use a large structuring element which will distort the boundary. It won't be exact like the convave hull solution I gave you in your duplicate question. Nonetheless, here is a morphological solution.

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 color demo image.
folder = 'C:\Users\Sharifah\Documents\Temporary';
baseFileName = 'Screen Shot 2013-10-23 at 8.18.51 PM.png';
% Get the full filename, with path prepended.
fullFileName = fullfile(folder, baseFileName);
if ~exist(fullFileName, 'file')
  % Didn't find it there.  Check the search path for it.
  fullFileName = baseFileName; % No path this time.
  if ~exist(fullFileName, 'file')
    % Still didn't find it.  Alert user.
    errorMessage = sprintf('Error: %s does not exist.', fullFileName);
    uiwait(warndlg(errorMessage));
    return;
  end
end
rgbImage = imread(fullFileName);
% Get the dimensions of the image.  numberOfColorBands should be = 3.
[rows, columns, numberOfColorBands] = size(rgbImage);
% Display the original color image.
subplot(2, 2, 1);
imshow(rgbImage);
axis on;
title('Original Color Image', 'FontSize', fontSize);
% Enlarge figure to full screen.
set(gcf, 'units','normalized','outerposition',[0 0 1 1]);

% Extract the individual red, green, and blue color channels.
redChannel = rgbImage(:, :, 1);
greenChannel = rgbImage(:, :, 2);
blueChannel = rgbImage(:, :, 3);

binaryImage = greenChannel >= 250 & redChannel == 0;
% Display the binary image.
subplot(2, 2, 2);
imshow(binaryImage);
title('Binary Image', 'FontSize', fontSize);

% Do a morphological closing on it.
se = strel('disk',15);
closedImage = imclose(binaryImage, se);
% Fill the image.
filledImage = imfill(closedImage, 'holes');
% Display the binary image.
subplot(2, 2, 3);
imshow(filledImage);
title('Closed, filled Image', 'FontSize', fontSize);

area = bwarea(filledImage)
message = sprintf('The Area = %.3f pixels', area);
msgbox(message);

[Epah]

Hi Image Analyst,

I tried to use regionprops to find the Area and MajorAxisLength, but the computed result is not in pixels but instead in struct array(what does this means?) :

results = regionprops(filledImage, 'Area', 'MajorAxisLength');
results = 

    8x1 struct array with fields:
        Area
        MajorAxisLength

May I know what is the error? Is there any other way to find the major length axis? Thank you.

[Image Analyst]

That is not an error. You have an array of structures. Each element is a structure that describes one single object with whatever measurements you asked for. You can extract them all into individual arrays if you want:

allAreas = [results.Area];
allMajorAxesLengths = [results.MajorAxesLength];

Answer 2

[aredhel_vlsi]

Hello people, I would like to locate the green pixels of the image and extract their position in the image. For example at this image : folder = fullfile(matlabroot, '\toolbox\images\imdemos'); baseFileName = 'peppers.png';

I would like to remove the green peppers, and know their position at my image. Could you please help me in that ? Is there any tool I could use? I don't have skills at Image processing, I just want to use it for extracting information. I have managed so far to read the image, imageshow the R,G,B channels but I am stuck now. Please help !Thank you in advance !

[Image Analyst]

Look at my color segmentation demos. It's simple matter to adapt the thresholds in the demo to pick out green. http://www.mathworks.com/matlabcentral/fileexchange/?term=authorid%3A31862

Answer 3

[riya reetu]

Could you please give me code for Detection of roadside vegetation

[Image Analyst]

See my answer https://www.mathworks.com/matlabcentral/answers/91200-how-to-find-the-green-area#comment_197113