How can i extract desired image from an image?

In the attached figure, I have to extract the visible part (i.e. rectangular eye part) in order to have focused eye region. I have tried imcrop function and it does what I need. But everytime i have to select the image co-ordinates. I want to do it automatically, like MATLAB itself sense the co-ordinates and extract that focused eye part. I mean there might be some algorithm which can vanish the black part and extract visible one. anybody have idea, how to do it?

cr1=imcrop(fmr_ext1,[500.5 388.5 85 117]);

Answer 1

[Image Analyst]

You can get the bounding box and then use crop:

measurements = regionprops(grayImage>0, 'BoundingBox');
croppedImage = imcrop(grayImage, measurements.BoundingBox);

[Usman]

it gives error in 2nd line

Error using imcrop>parseInputs (line 197) Too many input arguments.

Error in imcrop (line 94) [x,y,a,cm,spatial_rect,h_image,placement_cancelled] = parseInputs(varargin{:});

Error in trye (line 15) croppedImage = imcrop(a,measurements.BoundingBox);

[Image Analyst]

That was untested just off the top of my head. Alright, I guess I'll have to download your image and build you a full-blown demo. Give me time.

[Usman]

sure, I will be waiting. :)

[Image Analyst]

When I downloaded your image, I found out it was corrupted with a white border and bad JPG artifacts so I had to clean those up. DO NOT use JPG images for image processing. More robust code is below:

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 = 15;

%===============================================================================
% Read in a gray scale demo image.
folder = pwd;
% Get the full filename, with path prepended.
baseFileName = 'd.jpg';
fullFileName = fullfile(folder, baseFileName);

% Check if file exists.
if ~exist(fullFileName, 'file')
  % File doesn't exist -- didn't find it there.  Check the search path for it.
  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.  
% numberOfColorBands should be = 1.
[rows, columns, numberOfColorChannels] = size(grayImage);
if numberOfColorChannels > 1
  % It's not really gray scale like we expected - it's color.
  % Convert it to gray scale by taking only the green channel.
  grayImage = grayImage(:, :, 2); % Take green channel.
end
% Display the image.
subplot(2, 2, 1);
imshow(grayImage, []);
title('Original Grayscale Image', 'FontSize', fontSize, 'Interpreter', 'None');

% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);
% 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') 

% Threshold (binarize) the image.
binaryImage = grayImage > 10;
% Get rid of white border/frame that is there for some weird reason.
binaryImage = imclearborder(binaryImage);

% Because he used a JPG image instead of PNG, 
% there are tons of jpg artifacts.
% Take the largest blob.
binaryImage = bwareafilt(binaryImage, 1);
subplot(2, 2, 2);
imshow(binaryImage, []);
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');

% Find the bounding box.
labeledImage = bwlabel(binaryImage);
measurements = regionprops(labeledImage, 'BoundingBox');
croppedImage = imcrop(grayImage, measurements.BoundingBox);
% Display the cropped image.
subplot(2, 2, 3);
imshow(croppedImage, []);
title('Cropped', 'FontSize', fontSize, 'Interpreter', 'None');

[Usman]

boss you have achieved the result what i want. First of all thankyou for your prestigious effort and help. But i Got the error in

binaryImage = bwareafilt(binaryImage, 1);

Undefined function 'bwareafilt' for input arguments of type 'double'.

Error in trye (line 52)

binaryImage = bwareafilt(binaryImage, 1);

I guess this function is not defined in MATLAB. I am using MATLAB 2012b

[Usman]

thanks it works in 2015a..thankyou alot

[Image Analyst]

See my own function, attached, written before they came out with bwareafilt().