image matching with template in database

hi,

how can i compare an image with a template in a database? the object of interest in this case is a marker consisted of dots. first, the marker template is save in the database, then another image with the marker is placed for comparison. i have to make sure that it can still recognise the marker regardless of the scale, orientation, illumination, etc. the method that i have in mind is SIFT but is that any other ways?

thanks for replying

Answer 1

[Image Analyst]

You could use normalized cross correlation. Here's a demo:

% Demo to use normxcorr2 to find a template (a white onion)
% in a larger image (of a pile of vegetables)
clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
imtool close all;  % Close all imtool figures.
clear;  % Erase all existing variables.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;

% Check that user has the Image Processing Toolbox installed.
hasIPT = license('test', 'image_toolbox');
if ~hasIPT
  % User does not have the toolbox installed.
  message = sprintf('Sorry, but you do not seem to have the Image Processing Toolbox.\nDo you want to try to continue anyway?');
  reply = questdlg(message, 'Toolbox missing', 'Yes', 'No', 'Yes');
  if strcmpi(reply, 'No')
    % User said No, so exit.
    return;
  end
end

% Read in a standard MATLAB color demo image.
folder = fullfile(matlabroot, '\toolbox\images\imdemos');
baseFileName = 'peppers.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]);

% Let's get our template by extracting a small portion of the original image.
templateWidth = 71
templateHeight = 49
smallSubImage = imcrop(rgbImage, [192, 82, templateWidth, templateHeight]);
subplot(2, 2, 2);
imshow(smallSubImage, []);
axis on;
title('Template Image to Search For', 'FontSize', fontSize);

% Ask user which channel to search for a match.
% channelToCorrelate = menu('Correlate which color channel?', 'Red', 'Green', 'Blue');
% It actually finds the same location no matter what channel you pick, 
% for this image anyway, so let's just go with red (channel #1).
channelToCorrelate = 1;  
correlationOutput = normxcorr2(smallSubImage(:,:,1), rgbImage(:,:, channelToCorrelate));
subplot(2, 2, 3);
imshow(correlationOutput, []);
axis on;
title('Normalized Cross Correlation Output', 'FontSize', fontSize);

% Find out where the normalized cross correlation image is brightest.
[maxCorrValue, maxIndex] = max(abs(correlationOutput(:)));
[yPeak, xPeak] = ind2sub(size(correlationOutput),maxIndex(1))
% Because cross correlation increases the size of the image, 
% we need to shift back to find out where it would be in the original image.
corr_offset = [(xPeak-size(smallSubImage,2)) (yPeak-size(smallSubImage,1))]

% Plot it over the original image.
subplot(2, 2, 4); % Re-display image in lower right.
imshow(rgbImage);
axis on; % Show tick marks giving pixels
hold on; % Don't allow rectangle to blow away image.
% Calculate the rectangle for the template box.  Rect = [xLeft, yTop, widthInColumns, heightInRows]
boxRect = [corr_offset(1) corr_offset(2) templateWidth, templateHeight]
% Plot the box over the image.
rectangle('position', boxRect, 'edgecolor', 'g', 'linewidth',2);
% Give a caption above the image.
title('Template Image Found in Original Image', 'FontSize', fontSize);
uiwait(helpdlg('Done with demo!'));

[Ayush Sharma]

Respected, I have edited your code to detect a pre-defined image from the user and fortunately, it is running well. But I want my system to show no box in case the matched image is not present. How can I edit the code if I need to avoid displaying the green rectangular box in case there is such match found.

Kindly help me in this regard.

Thank you

[Image Analyst]

Just return/exit if maxCorrValue is not high enough:

if maxCorrValue < 0.8 % Whatever....
    return;
end

[Ayush Sharma]

Respected, After trying what you suggested, the image is successfully omitting the green box.

But, when i try to implement it on a frame taken at a real time from the webcam, the output is not correct. I selected the template as my lunch box, as shown. and the webcam takes the snapshot as given.

But the code fails to recognize it correctly. It shows a mxCorrValue of ~0.55 and that too in a wrong position. Can you guide me where is the problem. Is the any error in selecting the template? Do I need to select the size of the template image as mentioned in your code? (ie: Width = 71,Height = 49) or is there any other issue!

Kindly revert on this. Regards

[Ayush Sharma]

I modified the code and now the code is continuously taking each frame, detects and gives the out in frame by frame as a video.

The code is now somewhat detecting the template with less accuracy. I need to bring the template in the center of the camera and close to it and as i shifts the camera slightly backwards and at an angle, the detections stops detecting with accuracy.

Why soo much of error? How can I rectify this? I want this code to detect road sign on a moving car.

Shall wait for your revert.

Best Regards

[Image Analyst]

Try Hu's moments: http://www.youtube.com/watch?v=Nc06tlZAv_Q

or feautre based object recognition: https://www.mathworks.com/products/computer-vision/features.html#object-detection-and-recognition