For Complex Background can i get automatic leaf segmentation code?

Sir now I am using the code below but for a complex background. This code isn't working properly.

I am facing a lot of segmentation problems.

% Demo to find leaf.  By Image Analyst, Nov. 1, 2020.
clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clearvars;
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 16;
fprintf('Beginning to run %s.m ...\n', mfilename);
%-----------------------------------------------------------------------------------------------------------------------------------
% Read in image.
folder = [];
baseFileName = 'C:\Users\Manoj Prasad\Downloads\SHAREit\vivo 1601\photo\j.jpg';
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
% It's not an RGB image!  It's an indexed image, so read in the indexed image...
rgbImage = imread(fullFileName);
[rows, columns, numberOfColorChannels] = size(rgbImage)
% Display the test image.
subplot(2, 2, 1);
imshow(rgbImage, []);
axis('on', 'image');
caption = sprintf('Image : "%s"', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Set up figure properties:
% Enlarge figure to full screen.
hFig1 = gcf;
hFig1.Units = 'Normalized';
hFig1.WindowState = 'maximized';
% 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.
hFig1.Name = 'Demo by Image Analyst';
[mask, maskedRGBImage] = createMask(rgbImage);
% Take just the largest regions:
mask = bwareafilt(mask, 1);
% Fill Holed.
mask = imfill(mask, 'holes');
% Display the initial mask image.
subplot(2, 2, 2);
imshow(mask, []);
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
axis('on', 'image');
title('Mask', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
% Mask the image using bsxfun() function to multiply the mask by each channel individually.  Works for gray scale as well as RGB Color images.
maskedRgbImage = bsxfun(@times, rgbImage, cast(mask, 'like', rgbImage));
% Display the final masked image.
subplot(2, 2, 3);
imshow(maskedRgbImage, []);
axis('on', 'image');
title('Masked Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Display the final masked image of the background by inverting the mask.
% Mask the image using bsxfun() function to multiply the mask by each channel individually.  Works for gray scale as well as RGB Color images.
backgroundImage = bsxfun(@times, rgbImage, cast(~mask, 'like', rgbImage));
subplot(2, 2, 4);
imshow(backgroundImage, []);
axis('on', 'image');
title('Background Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
%-------------------------------------------------------------------------------------------------------------
% Make measurements
props = regionprops(mask, 'Area', 'Centroid')
allAreas = [props.Area];
xyCentroids = vertcat(props.Centroid);
subplot(2, 2, 2);
hold on;
function [BW,maskedRGBImage] = createMask(RGB)
%createMask  Threshold RGB image using auto-generated code from colorThresholder app.
%  [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
%  auto-generated code from the colorThresholder app. The colorspace and
%  range for each channel of the colorspace were set within the app. The
%  segmentation mask is returned in BW, and a composite of the mask and
%  original RGB images is returned in maskedRGBImage.
% Auto-generated by colorThresholder app on 01-Nov-2020
%------------------------------------------------------
% Convert RGB image to chosen color space
I = rgb2hsv(RGB);
% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.183;
channel1Max = 0.400;
% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.000;
channel2Max = 1.000;
% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.000;
channel3Max = 1.000;
% Create mask based on chosen histogram thresholds
sliderBW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
	(I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
	(I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;
% Initialize output masked image based on input image.
maskedRGBImage = RGB;
% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;
end

and this is the complex background image where I have used for this particular code.

[Image Analyst]

You forgot to attach g.jpg.

You may need to adjust the threshold parameters but it still looks like you can just segment the green regions. Try the Color Threshold on the Apps tab of the tool ribbon.

[Manoj Prasad S.G]

Sir not only this image for many further images is not working. this are the few images

we have to change in the code. when we run the code automatically it has to segment though if we have complex background also.

Answer 1

[Image Analyst]

Just use the color thresholder to find hue and brightness ranges that will work across all your images.

Then call bwareafilt() to extract the largest green blob to get a single leaf.

What is the source of the images? What kind of database would have single leaves on all kinds of backgrounds? Seems highly artificial. Is there any real world use that these images came from, or are these just made up homework images for you to practice color segmentation or leaf detection on?

[Manoj Prasad S.G]

Sir actually there is a project for us called leaf segmentation we have 10 leafs with 100 different background. And we clicked all leafs with complexity background there is no artificial. Now we are learning matlab but we don't have much time learn everything because we have submit this project as fast as possible.

[Manoj Prasad S.G]

i don't understand that bwarefilt() so whatever changes we have to do could please change that particular part and resend back to us and where we have to use that color threshold in the code. Slowly we are learning everything.

[Image Analyst]

Sounds kind of artificial, like a homework assignment, rather than an application where people out in the wild could take images of virtually anything with their cell phones and then you tell them what kind of plant it was, like "PlantNet" smartphone app. But ok, good luck. There are lots of leaf identification posts here in this forum, but I think you already have a good start with your (my) code. You just need to adjust the thresholds.

[Manoj Prasad S.G]

Sir please i need code where it as to work for all dataset that what i have collected.

[Image Analyst]

Try this:

mask = bwareafilt(mask, 1); % Extract biggest blob only.