# How to extract only the object and get the extreme coordinates?

13 views (last 30 days)

Show older comments

Rhandrey Maestri
on 26 Nov 2023

Commented: Image Analyst
on 13 Mar 2024

Dear members, I would be truly grateful if you could assist me in extracting the object indicated in the image and obtaining the coordinates of its extreme points on the right and left. My goal is to calculate the distance between these extreme points and the centroid of the object. Could you please guide me on the correct approach for achieving this?

You can find the code I am working on, the tested image and a preliminar result with the elements that I am interested.

clc

clear all

close all

set(0, 'DefaultAxesFontName', 'Times New Roman');

set(0, 'DefaultUIControlFontName', 'Times New Roman');

set(0, 'defaultUitableFontName', 'Times New Roman');

set(0, 'defaultTextFontName', 'Times New Roman');

set(0, 'defaultUipanelFontName', 'Times New Roman');

font_size = 16;

line_width_size=2;

J=zeros;

number=1;

pixelTomm=50; %Physical scale conversion factor

%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%%%%%%%% importing Data %%%%%%%%%%%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

for framenumbers=53:576

% defining the range of the number of the images

close all

clear_all_but('number','framenumbers','xcentroid1','ycentroid1','xfit_Leading','yfit_Leading','Rfit_Leading','xfit_trailing','yfit_trailing','Rfit_trailing','Thetaleading','Thetatrailing')

%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%%%%%%%% importing Data %%%%%%%%%%%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

I = imread(sprintf('0000200test.jpg',framenumbers)); %Importing tif

I(:,:,3) = []; %%% removing the second and third layer of the image

I(:,:,2) = [];

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%%% Plotting the original image %%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

figure(1), set(gcf,'color','w');

sz_x = 400; sz_y = 400; % size of the figure

y_pos = 600; x_pos =1; % position on the screen

set(1,'pos', [x_pos, y_pos, sz_x, sz_y]);

axes('position',[.1 .15 .8 .8]) % size of the plot in the figure

title('Original image')

figure (1)

hold on

imshow(I, []); %showing the raw image

axis on

%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%%% Binarization of the image %%%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

numberOfcolum = size(I, 1);% calculating the size of the raw image

numberOfrows = size(I, 2);% calculating the size of the raw image

J=zeros(numberOfcolum,numberOfrows);

% defining the matrix to store the Binarized image

for i=1:numberOfcolum

for j=1:numberOfrows

if I(i,j) < 37

%%%%%%%%%%%%%Masking the lower intensity%%%%%%%%%%

J(i,j)=0;

else

J(i,j)=1;

end

j=j+1;

end

i=i+1;

end

figure,imshow(J); %showing the black and white image

J = bwareaopen(J,20000); %Remove small objects from binary image

figure,imshow(J);

%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%% Detect Entire droplet and fill the hollow region %%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

[~, threshold] = edge(J, 'sobel'); %findig the edge of the bubble

fudgeFactor = .9;

BWs = edge(J,'sobel', threshold * fudgeFactor);

figure, imshow(BWs), title('binary gradient mask');

%showing the detected bubble

%%%%%%%%%%%%% Fill Interior Gaps %%%%%%%%%%%%

BWdfill = imfill(BWs, 'holes');

figure, imshow(BWdfill);

Preprocessed_Image = imcrop(BWdfill,[778.5 10.5 783 2038]);

%Cropping the original image to remove the white border

figure, imshow(BWdfill);

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%%%%% Plotting cropped image %%%%%%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

figure(2), set(gcf,'color','w');

sz_x = 400; sz_y = 400; % size of the figure

y_pos = 600; x_pos =401; % position on the screen

set(2,'pos', [x_pos, y_pos, sz_x, sz_y])

axes('position',[.1 .15 .8 .8]) % size of the plot in the figure

title('Pre-processed image')

figure(2)

imshow(Preprocessed_Image);

axis on

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

%%% finding the centroid, leading and trailing edge of the bubble %%

%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%

stats = regionprops('table',Preprocessed_Image,'Centroid',...

'MajorAxisLength','MinorAxisLength');

xcentroid=stats.Centroid(1,1); % x of the centroid

x_centroid(number)=xcentroid; % storing x-location

ycentroid=stats.Centroid(1,2); % y of the centroid

y_centroid(number)=ycentroid; % storing y-location

MinorAxisLength=stats.MinorAxisLength(1); % length of Minor axis

MajorAxisLength=stats.MajorAxisLength(1); % length of Minor axis

Thanks!

##### 3 Comments

Walter Roberson
on 26 Nov 2023

BMP is good.

It looks like there might be a background grid, possibly intended to help determine the sizes of objects? Is that grid 0.1mm spacing? At the moment I do not know how hard it would be to extract the grid, but if it is a known size and can be extracted, that would give us a way to calculate absolute sizes on the images instead of relative sizes.

### Accepted Answer

Akira Agata
on 27 Nov 2023

Edited: Akira Agata
on 27 Nov 2023

How about the following?

% Load the image

I = imread('https://jp.mathworks.com/matlabcentral/answers/uploaded_files/1552757/2000000200.bmp');

% Binarize

BW = imbinarize(I);

% Extract the ROI

BW = ~BW;

se = strel("disk", 5);

BW = imopen(BW, se);

BW = imclearborder(BW);

BW = bwareafilt(BW, 1);

BW = imfill(BW, "holes");

% Calculate the centroid

s = regionprops(BW, "Centroid");

% Calculate the extreme points

idx = any(BW);

pt1 = find(idx, 1);

pt2 = find(idx, 1, "last");

% Visualize the result

imshow(I)

hold on

xline(pt1, "r", sprintf("X = %d", pt1), "FontSize", 18)

xline(pt2, "r", sprintf("X = %d", pt2), "FontSize", 18)

h = scatter(s.Centroid(1), s.Centroid(2), "r", "filled");

legend(h, "Centroid", "FontSize", 18)

##### 3 Comments

Image Analyst
on 13 Mar 2024

### More Answers (1)

### See Also

### Categories

### Products

### Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!