How can I sepearte extruded part from its boundary in a grey scale image using matlab ?

Split the red and green portion in modified_image. Matlab code and images are attached.

Answer 1

[Image Analyst]

The simplest way is to just have the user encircle either the protrusions of the main trunk using drawpoly().

[Surendra Ratnu]

But I have 100 images and the protrusion portion placed in different position in every images. So i could not seperate the main trunk and protrusions portion for all images.

[Image Analyst]

Why not? If you hand trace, what's preventing you? Do you not know how to loop over files? If not, see

https://matlab.fandom.com/wiki/FAQ#How_can_I_process_a_sequence_of_files?

If it's a super complicated structure - so complicated that you don't know for sure what's a protrusion and what's not -- then developing an automated algorithm for those complicated images would be very difficult.

[Surendra Ratnu]

Agreed with your point. But The protrusion part have a different location in every image and it is random. we could not predict what is location of the protrusion in every images.

[Image Analyst]

I don't know why that would prevent people from being able to see where to chop off the protrusions. However if you insist on an automatic way, here is a start. There are other ways though to smooth out the left edge, like fit it with a Savitzky-Golay filter.

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 18;
% Have user browse for a file, from a specified "starting folder."
% For convenience in browsing, set a starting folder from which to browse.
startingFolder = pwd;  % or 'C:\wherever';
if ~exist(startingFolder, 'dir')
    % If that folder doesn't exist, just start in the current folder.
    startingFolder = pwd;
end
% Get the name of the file that the user wants to use.
defaultFileName = fullfile(startingFolder, 'protrusions.png');
[baseFileName, folder] = uigetfile(defaultFileName, 'Select a file');
if baseFileName == 0
    % User clicked the Cancel button.
    return;
end
fullFileName = fullfile(folder, baseFileName)
%===============================================================================
% Check if file exists.
if ~isfile(fullFileName)
    % 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
rgbImage = imread(fullFileName);
% Get the dimensions of the image.
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(rgbImage)
if numberOfColorChannels > 1
    % It's not really gray scale like we expected - it's color.
    % Use weighted sum of ALL channels to create a gray scale image.
    % 	grayImage = rgb2gray(rgbImage);
    % ALTERNATE METHOD: Convert it to gray scale by taking only the green channel,
    % which in a typical snapshot will be the least noisy channel.
    grayImage = rgbImage(:, :, 1); % Take red channel.
else
    grayImage = rgbImage; % It's already gray scale.
end
% Now it's gray scale with range of 0 to 255.
% Display the image.
subplot(3, 2, 1);
imshow(grayImage, []);
title('Original Image', 'FontSize', fontSize, 'Interpreter', 'None');
axis('on', 'image');
hp = impixelinfo();
%------------------------------------------------------------------------------
% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0, 0.04, 1, 0.96]);
% 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;
% Display the image.
subplot(3, 2, 2);
histogram(grayImage);
grid on;
title('Histogram of Gray Scale Image', 'FontSize', fontSize, 'Interpreter', 'None');
% Use fixed thresholds.
lowThreshold = 0;
highThreshold = 180;
% % Use triangle threshold method on the image
% pixelCounts = imhist(grayImage, 256);
% % pixelCounts(1:2) = 0; % Suppress gray level of background since those bins would be so high.
% showPlot = true;
% highThreshold = triangle_threshold(pixelCounts, 'L', showPlot)
% Interactively and visually set a threshold on a gray scale image.
% https://www.mathworks.com/matlabcentral/fileexchange/29372-thresholding-an-image?s_tid=srchtitle
% [lowThreshold, highThreshold, lastThresholdedBand] = threshold(lowThreshold, highThreshold, grayImage);
% Show line on histogram.
hold on;
xline(highThreshold, 'Color', 'r', 'LineWidth', 2);
% Binarize the image.
mask = grayImage > lowThreshold & grayImage < highThreshold;
% Take largest blob.
mask = bwareafilt(mask, 1);
% Display the mask.
subplot(3, 2, 3);
imshow(mask, []);
title('Mask', 'FontSize', fontSize, 'Interpreter', 'None');
axis('on', 'image');
% For each line, take only the longest stretch of white.
for row = 1 : rows
    thisRow = mask(row, :);
    % Find the rightmost blob.
    props = regionprops(thisRow, 'Centroid');
    xy = vertcat(props.Centroid);
    % Find the max x value
    [maxx, indexOfRightBlob] = max(xy(:, 1));
    if indexOfRightBlob > 1
        % Extract the right blob only.
        labeledImage = bwlabel(thisRow);
        thisRow = ismember(labeledImage, indexOfRightBlob);
        % Put back into the mask
        mask(row, :) = thisRow;
    end
end
% Display the mask.
subplot(3, 2, 4);
imshow(mask, []);
title('Cleaned Mask', 'FontSize', fontSize, 'Interpreter', 'None');
axis('on', 'image');
% Find the left and right sides.
leftCol = nan(1, columns);
rightCol = nan(1, columns);
for row = 1 : rows
    t = find(mask(row, :), 1, 'first');
    if ~isempty(t)
        leftCol(row) = t;
        rightCol(row) = find(mask(row, :), 1, 'last');
    end
end
% Plot right edge in red:
y = 1 : rows;
hold on;
plot(rightCol, y, 'r-', 'LineWidth', 2);
% Plot left edge in yellow:
plot(leftCol, y, 'y-', 'LineWidth', 2);
% Get the widths
widths = rightCol - leftCol;
% Get the average width
meanWidth = mean(widths)
% Scan down and if any width is more than 1.5 * the mean width, crop it.
factor = 1.3;
for row = 1 : rows
    thisWidth = widths(row);
    if isnan(thisWidth)
        continue;
    end
    if thisWidth > factor * meanWidth
        % Find the column we need to zero out to
        col = round(rightCol(row) - factor * meanWidth)
        % Zero out on the left up until there.
        mask(row, 1:col) = false;
    end
end
% Display the mask.
subplot(3, 2, 5);
imshow(mask, []);
title('Cleaned Mask', 'FontSize', fontSize, 'Interpreter', 'None');
axis('on', 'image');
msgbox('Done!');