How to detect marker with specific feature on it?

Hi, image processing experts.

I'm having problem with detecting a specific marked marker.

Here's an example photo that i drew.

Marker is circle shaped. But as you know, marker could be ellipse shaped when the camera is not vertical with the marker.

What I want to do is, I want to find a marker with point marked inside the marker.

Want to get advice of detecting specific marker with point on it.

Thanks.

[Dyuman Joshi]

Questions about detecting ellipses and detecting points inside a closed region have been asked many times on this forum, you can find answers by searching.

MATLAB Answers Help Point #1 - Search for Questions and Answers

I strongly suggest you do this.

Answer 1

[Image Analyst]

Try this. Note that I only found 2 markers because one of them is not surrounded by a solid black circle -- it has a gap, like a "C". By the way, I'll be traveling the next 5 days and may not answer.

% Demo by Image Analyst
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 = 16;
markerSize = 20;

%--------------------------------------------------------------------------------------------------------
%    READ IN TEST IMAGE
folder = [];
baseFileName = 'jaeyoung.jpeg';
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
grayImage = 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(grayImage)
if numberOfColorChannels > 1
    % It's not really gray scale like we expected - it's color.
    fprintf('It is not really gray scale like we expected - it is color\n');
    % Extract the blue channel.
    grayImage = grayImage(:, :, 3);
end

%--------------------------------------------------------------------------------------------------------
% Display the image.
subplot(2, 2, 1);
imshow(grayImage, []);
impixelinfo;
axis('on', 'image');
title('Original Gray Scale Image', 'FontSize', fontSize, 'Interpreter', 'None');
% Update 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(grayImage)
% Maximize window.
g = gcf;
g.WindowState = 'maximized';
drawnow;

%--------------------------------------------------------------------------------------------------------
subplot(2, 2, 2);
imhist(grayImage);
grid on;
title('Histogram of Image', 'FontSize', fontSize, 'Interpreter', 'None');

%--------------------------------------------------------------------------------------------------------
% Flatten background.
% grayImage = adapthisteq(grayImage);

%--------------------------------------------------------------------------------------------------------
% Get mask by thresholding at 116.
lowThreshold = 136;
highThreshold = 255;
% 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] = threshold(lowThreshold, highThreshold, grayImage)
mask = grayImage >= lowThreshold & grayImage <= highThreshold;
% Draw line at threshold.
xline(lowThreshold, 'Color', 'r', 'LineWidth', 2);
subplot(2, 2, 3);
imshow(mask);
impixelinfo;
axis('on', 'image');
title('Initial Mask Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
% Clean up the initial mask
mask = imclearborder(mask);
% Get rid of blobs smaller than 10k pixels.
mask = bwareaopen(mask, 10000);
% Now the blobs in this mask have very small pinpoint holes in them (like 1-12 pixels).
% But we want only "markers"/"holes" bigger than a certain area, like 300 or so.
% So invert the mask, clear the border, and call bwareaopen
% to extract only those that are big enough
holeMask = imclearborder(~mask);
% Extract only blobs bigger than 300 pixels.
holeMask = bwareaopen(holeMask, 300);
% Find blobs and their areas.
props = regionprops(holeMask, 'Area', 'Centroid');
allHoleAreas = [props.Area]
holeCentroids = vertcat(props.Centroid)
subplot(2, 2, 4);
imshow(holeMask);
impixelinfo;
axis('on', 'image');
caption = sprintf('Found %d Markers', numel(props));
title(caption, 'FontSize',fontSize);
% Plot circles around them
hold on;
for k = 1 : numel(props)
    x = holeCentroids(k, 1);
    y = holeCentroids(k, 2);
    plot(x, y, 'ro', 'MarkerSize', markerSize);
end

[Image Analyst]

See my Image Segmentation Tutorial in my File Exchange:

Image Analyst's File Exchange

It's a generic, general purpose demo of how to threshold an image to find blobs, and then measure things about the blobs, and extract certain blobs based on their areas or diameters.