Forgery Image Detection (Image Authentication) in Matlab

Introduction:

Nowadays, digital images and video are gradually replacing their conventional analog counterparts .This is quite understandable because digital format is easy to edit, modify, and exploit. Digital images and videos can be readily shared via computer networks and conveniently processed for queries in databases. Also, digital storage does not age or degrade with usage. On the other hand, thanks to powerful editing programs, it is very easy even for an amateur to maliciously modify digital media and create "perfect" forgeries. It is usually much more complicated to tamper with analog tapes and images.

Robust authentication scheme:

here is a scheme to ensure the authenticity of digital images is presented. Their authentication technique is able to detect malicious tamperingof images even if they have been incidentally distorted by common image processingoperations.

Code:

Step 1: (Gaussian window function)

 function [window]=gaussian_window()  
 % gaussian window  
 N_window=7;   % window length  
 sigma=1;      
 [x, y] = meshgrid(-(ceil(sigma*2)):4*sigma/(N_window-1):ceil(sigma*2));  
 window = (1/(2*pi*sigma^2)).*exp(-0.5.*(x.^2+y.^2)./sigma^2);  
 return  

Step 2: (Function to calculate Variance)

 function [var_map] = getVarianceMap(im,Bayer,dim)  
   
 % extend pattern over all image  
   
 pattern = kron(ones(dim(1)/2,dim(2)/2), Bayer);  
   
   
 % separate acquired and interpolate pixels for a 7x7 window  
   
 mask = [1, 0, 1, 0, 1, 0, 1;  
     0, 1, 0, 1, 0, 1, 0;  
     1, 0, 1, 0, 1, 0, 1;  
     0, 1, 0, 1, 0, 1, 0;  
     1, 0, 1, 0, 1, 0, 1;  
     0, 1, 0, 1, 0, 1, 0;  
     1, 0, 1, 0, 1, 0, 1];  
   
 % gaussian window fo mean and variance  
   
 window = gaussian_window().*mask;  
 mc = sum(sum(window));  
 vc = 1 - (sum(sum((window.^2))));  
 window_mean = window./mc;  
   
 % local variance of acquired pixels  
   
 acquired = im.*(pattern);  
 mean_map_acquired = imfilter(acquired,window_mean,'replicate').*pattern;  
 sqmean_map_acquired = imfilter(acquired.^2,window_mean,'replicate').*pattern;  
 var_map_acquired = (sqmean_map_acquired - (mean_map_acquired.^2))/vc;  
   
 % local variance of interpolated pixels  
   
 interpolated = im.*(1-pattern);  
 mean_map_interpolated = imfilter(interpolated,window_mean,'replicate').*(1-pattern);  
 sqmean_map_interpolated = imfilter(interpolated.^2,window_mean,'replicate').*(1-pattern);  
 var_map_interpolated = (sqmean_map_interpolated - (mean_map_interpolated.^2))/vc;  
   
   
 var_map = var_map_acquired + var_map_interpolated;  
   
   
 return  

Step 3: (Output)

Face Recognition using Local Sparse Representaion in Matlab

The Below tutorial is regarding Face Recognition  Implementation using Local sparse representation in matlab.

Step 1:

           Create GUI in matlab using the below code.

function varargout = FR_Processed_histogram(varargin)

gui_Singleton = 1;

gui_State = struct('gui_Name',       mfilename, ...

                   'gui_Singleton',  gui_Singleton, ...

                   'gui_OpeningFcn', @FR_Processed_histogram_OpeningFcn, ...

                   'gui_OutputFcn',  @FR_Processed_histogram_OutputFcn, ...

                   'gui_LayoutFcn',  [] , ...

                   'gui_Callback',   []);

if nargin && ischar(varargin{1})

    gui_State.gui_Callback = str2func(varargin{1});

end

if nargout

    [varargout{1:nargout}] = gui_mainfcn(gui_State, varargin{:});

else

    gui_mainfcn(gui_State, varargin{:});

end

% End initialization code - DO NOT EDIT

%--------------------------------------------------------------------------

% --- Executes just before FR_Processed_histogram is made visible.

function FR_Processed_histogram_OpeningFcn(hObject, eventdata, handles, varargin)

% This function has no output args, see OutputFcn.

% hObject    handle to figure

% eventdata  reserved - to be defined in a future version of MATLAB

% handles    structure with handles and user data (see GUIDATA)

% varargin   command line arguments to FR_Processed_histogram (see VARARGIN)

% Choose default command line output for FR_Processed_histogram

handles.output = hObject;

% Update handles structure

guidata(hObject, handles);

% UIWAIT makes FR_Processed_histogram wait for user response (see UIRESUME)

% uiwait(handles.figure1);

global total_sub train_img sub_img max_hist_level bin_num form_bin_num;

total_sub = 40;

train_img = 200;

sub_img = 10;

max_hist_level = 256;

bin_num = 9;

form_bin_num = 29;

%--------------------------------------------------------------------------

% --- Outputs from this function are returned to the command line.

function varargout = FR_Processed_histogram_OutputFcn(hObject, eventdata, handles) 

% varargout  cell array for returning output args (see VARARGOUT);

% hObject    handle to figure

% eventdata  reserved - to be defined in a future version of MATLAB

% handles    structure with handles and user data (see GUIDATA)

% Get default command line output from handles structure

varargout{1} = handles.output;

%--------------------------------------------------------------------------

% --- Executes on button press in train_button.  

function train_button_Callback(hObject, eventdata, handles)

% hObject    handle to train_button (see GCBO)

% eventdata  reserved - to be defined in a future version of MATLAB

% handles    structure with handles and user data (see GUIDATA)

global train_processed_bin;

global total_sub train_img sub_img max_hist_level bin_num form_bin_num;

train_processed_bin(form_bin_num,train_img) = 0;

K = 1;

train_hist_img = zeros(max_hist_level, train_img);

for Z=1:1:total_sub 

  for X=1:2:sub_img    %%%train on odd number of images of each subject

    

    I = imread( strcat('ORL\S',int2str(Z),'\',int2str(X),'.bmp') );        

    [rows cols] = size(I);

    

    for i=1:1:rows

       for j=1:1:cols

           if( I(i,j) == 0 )

               train_hist_img(max_hist_level, K) =  train_hist_img(max_hist_level, K) + 1;                            

           else

               train_hist_img(I(i,j), K) = train_hist_img(I(i,j), K) + 1;                         

           end

       end   

    end   

     K = K + 1;        

  end  

 end  

[r c] = size(train_hist_img);

sum = 0;

for i=1:1:c

    K = 1;

   for j=1:1:r        

        if( (mod(j,bin_num)) == 0 )

            sum = sum + train_hist_img(j,i);            

            train_processed_bin(K,i) = sum/bin_num;

            K = K + 1;

            sum = 0;

        else

            sum = sum + train_hist_img(j,i);            

        end

    end

    train_processed_bin(K,i) = sum/bin_num;

end

display ('Training Done')

save 'train'  train_processed_bin;

%--------------------------------------------------------------------------

% --- Executes on button press in Testing_button.    

function Testing_button_Callback(hObject, eventdata, handles)

% hObject    handle to Testing_button (see GCBO)

% eventdata  reserved - to be defined in a future version of MATLAB

% handles    structure with handles and user data (see GUIDATA)

global train_img max_hist_level bin_num form_bin_num;

global train_processed_bin;

global filename pathname I

load 'train'

test_hist_img(max_hist_level) = 0;

test_processed_bin(form_bin_num) = 0;

 [rows cols] = size(I);

  

    for i=1:1:rows

       for j=1:1:cols

           if( I(i,j) == 0 )

               test_hist_img(max_hist_level) =  test_hist_img(max_hist_level) + 1;                            

           else

               test_hist_img(I(i,j)) = test_hist_img(I(i,j)) + 1;                         

           end

       end   

    end   

    

  [r c] = size(test_hist_img);

  sum = 0;

    K = 1;

    for j=1:1:c        

        if( (mod(j,bin_num)) == 0 )

            sum = sum + test_hist_img(j);            

            test_processed_bin(K) = sum/bin_num;

            K = K + 1;

            sum = 0;

        else

            sum = sum + test_hist_img(j);            

        end

    end

  

 test_processed_bin(K) = sum/bin_num;

    

sum = 0;

K = 1;

    for y=1:1:train_img

        for z=1:1:form_bin_num        

          sum = sum + abs( test_processed_bin(z) - train_processed_bin(z,y) );  

        end         

        img_bin_hist_sum(K,1) = sum;

        sum = 0;

        K = K + 1;

    end

    [temp M] = min(img_bin_hist_sum);

    M = ceil(M/5);

    getString_start=strfind(pathname,'S');

    getString_start=getString_start(end)+1;

    getString_end=strfind(pathname,'\');

    getString_end=getString_end(end)-1;

    subjectindex=str2num(pathname(getString_start:getString_end));

    if (subjectindex == M)

      axes (handles.axes3)

      %image no: 5 is shown for visualization purpose

      imshow(imread(strcat('ORL\S',num2str(M),'\5.bmp')))    

      msgbox ( 'Correctly Recognized');

    else

     display ([ 'Error==>  Testing Image of Subject >>' num2str(subjectindex) '  matches with the image of subject >> '  num2str(M)])

     axes (handles.axes3)

     %image no: 5 is shown for visualization purpose

     imshow(imread(strcat('ORL\S',num2str(M),'\5.bmp')))    

     msgbox ( 'Recognized');

    end

display('Testing Done')

Step 2:

Run the matlab function and add the database images to path and train the images using train button.

Step 3:

      Now Select the input image button to locate input image.

          

Step 4:

             Click the Testing button to get the recognized images from database.

Note:

          You should download the database before running the code. Instruction to download the database is in the comment section of the file.

Soccer Game in matlab

This a Post related to Create simple gaming in Matlab environment.

To do the below things you need Matlab with Visual C++ compiler and True time Packages.

You can download true time packages from http://www.control.lth.se/truetime


Add the above folder into matlab execution path.

run the socceer.mdl file under examples\soccer folder.

The ouputs will be like below,