[2D code image correction and enhancement] simulation of 2D code image correction and enhancement processing based on MATLAB

1. Software version

matlab2013b

2. Algorithm flow overview

The image region and boundary of the two-dimensional code are obtained by morphological processing ;

The convex hull algorithm is used to calculate the point set on the boundary ;

Then according to the point set to find the four vertices of the two-dimensional code ,

Then perspective transformation correction , The points in each lattice are obtained by two-dimensional code segmentation .

Normalize the two-dimensional code image . Complete QR code correction .

Then do experiments to compare with other methods using edge detection plus hough The recognition rate of the image corrected by transformation .

Perform illumination enhancement before binarization , Homomorphic filtering and histogram equalization are used to do , Then use ostu Method for binarization .

By locating the position of the three corners of the QR code , And then through expansion treatment , And connect the area . Delete the connected area that is not where the three probe elements are located , Then the remaining connected areas are corroded , Edge detection , The point sets on the obtained edges are connected by convex hull method ,

Roughly determine the boundary of the QR code , Then use the shortest distance to the four external lines to determine the four vertices .

3. Part of the source code

clc;
clear all;
close all;
warning off;
addpath 'func\'


%filename ='1.jpg';
%filename ='2.jpg';
%filename ='3.jpg';
filename ='4.jpg';

X        = imread(filename);  
% Get image related information 
[R,C,K]  = size(X);
if K == 3
   f = rgb2gray(X);
else
   f = X;
end

%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Use wavelet filtering + An improved median filtering scheme 
figure
subplot(141);
imshow(f);
title(' original image ');
f = imadjust(f,[0.1 0.8],[]);

f = func_wavelet_filter(f);
subplot(142);
imshow(f);
title(' Image after wavelet filtering and ray enhancement ');
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%


%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% be based on OSTU Method 
G   = f;
f   = func_ostu(f); 
f   =~f;
subplot(143);
imshow(f);
title('ostu Binary image processing ');
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%


%%
% Morphological expansion 
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
SE = strel('disk',8);
I  = imdilate(f,SE);
% Delete small areas 
I  = bwareaopen(I,20000);
% Find the center of gravity of the whole picture 
subplot(144);
imshow(I);
title(' Morphological dilation image ');
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%




%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Mark connected domains 
[L,num]=bwlabel(I,8);
figure
subplot(141);
imshow(L);
% Eliminate irrelevant connected domains , Here, the elimination measures are improved , In the previous method, many test images cannot be processed correctly 
[R,C,K] = size(I);
L2      = zeros(R,C);
for i=1:num
    [r,c]=find(L==i); % Calculate the coordinate 
    if isempty(r) == 0 & isempty(c) == 0 
       a2(i) = min(r);  % Calculate the coordinate 
       a1(i) = max(r);  % Calculate the coordinate 
       b2(i) = min(c);  % Calculate the coordinate 
       b1(i) = max(c);  % Calculate the coordinate 
       % Judge whether it is the correct area according to the area 
       Lss    = a1(i) - a2(i);
       Wss    = b1(i) - b2(i);
       if (Lss>=0.9*Wss & Lss<=1.1*Wss) | (Wss>=0.9*Lss & Wss<=1.1*Lss)
          for j = 1:length(r) 
              L2(r(j),c(j)) = L(r(j),c(j));
          end
       end
    end
end
SE = strel('disk',8);
T=imerode(L2,SE);
T=imfill(T,'holes');
subplot(142);
imshow(T);
title(' Morphological corrosion ');
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%



%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Edge extraction 
T2=edge(T,'prewitt');
subplot(143);
imshow(T2);
title(' Edge extraction ');
% Point set of convex hull to be judged , This part has been improved , The original method is incomplete , Will not be able to detect edge problems 
[y,x] = find(T2==1);
img   = ones(size(T2));
p     = [];
for i=1:length(x)
    img(y(i),x(i))=0; 
    p=[p;x(i),y(i)];     
end
subplot(144);
imshow(img);
% Let's calculate the convex hull 
[t,index] = max(p(:,2));  
% find y The biggest point 
tmp_p     = p(index,:);         
% Set a and y The largest point is parallel to the point 
tmp_heng  =[tmp_p(1)+100,tmp_p(2)];    
for i=1:length(p)           
    % Find the sum of each point y The angle of the largest point , The angle between oneself and oneself NAN
    Ang(i) = func_angle(tmp_heng,p(i,:),tmp_p);  
end
Ang   = Ang';
p     =[p,Ang];
% Sort by the third column , The third column is the included angle degrees 
p     = sortrows(p,3);    
%re It's like a stack 
re{1} = p(length(p),1:2);     
re{2} = p(1,1:2);
re{3} = p(2,1:2);
top   = 3; 
for i=3:length(p)-1
    while func_multi(p(i,1:2),re{top-1},re{top})>=eps      
        top=top-1;    
        if top<=1
           break;
        end
    end
    top=top+1;
    re{top}=p(i,1:2);
end
 
% Here is the line connecting the points found on the convex hull 
for i=2:top   
    imgs = drawline(img,re{i-1}(1),re{i-1}(2),re{i}(1),re{i}(2));
end
imgs = drawline(img,re{1}(1),re{1}(2),re{top}(1),re{top}(2));

figure
subplot(231);
imshow(imgs)
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%


%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% Calculate the four vertices 
jiaodian2             = func_cal_point(imgs);
% Here, the similarity matching method is used to modify the initial vertex 
[jiaodian3,jiaodian4] = func_cal_point_adjust(jiaodian2,G);
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%


%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% correction 
Z=func_adjust(jiaodian4,G);
subplot(232);
imshow(uint8(G))
hold on
for i = 1:4
    plot(jiaodian2(i,2),jiaodian2(i,1),'g.'); 
    hold on;
    text(jiaodian2(i,2),jiaodian2(i,1),num2str(i)); 
end

subplot(233);
imshow(uint8(G))
hold on
for i = 1:4
    plot(jiaodian4(i,2),jiaodian4(i,1),'r.'); 
    hold on;
    plot(jiaodian3(i,2),jiaodian3(i,1),'g.'); 
    hold on;
end

subplot(234);
imshow(uint8(G))
hold on
for i = 1:3
    line([jiaodian4(i,2),jiaodian4(i+1,2)],[jiaodian4(i,1),jiaodian4(i+1,1)],'Color',[0 1 0]); 
    hold on;
end
line([jiaodian4(end,2),jiaodian4(1,2)],[jiaodian4(end,1),jiaodian4(1,1)],'Color',[0 1 0]); 

subplot(235);
Z2 = histeq(uint8(Z));
imshow(Z2);

subplot(236);
thresh=graythresh(Z2);
f   = im2bw(Z2,thresh); 
imshow(f);
 

%%
% Segment the final result 
[R,C] = size(Z2);

Z3    = edge(Z2,'canny');

% Line scan 
tmp1  = 0;
tmp2  = 0;
for i = 2:R  
    tmp1    = f(i-1,:);
    tmp2    = f(i,:);
    diff1(i) = abs(mean(tmp1 - tmp2));
end
% Search minimum 
[pks1,locs1]=findpeaks(-1*diff1,'minpeakdistance',3); % Find peaks 



% Column scan 
tmp1  = 0;
tmp2  = 0;
for i = 2:C  
    tmp1    = f(:,i-1);
    tmp2    = f(:,i);
    diff2(i) = abs(mean(tmp1 - tmp2));
end
% Search minimum 
[pks2,locs2]=findpeaks(-1*diff2,'minpeakdistance',3); % Find peaks 
locs1 = [locs1];
locs2 = [locs2];
% Get normalized QR code 
QRcode = zeros(length(locs1),length(locs2));
for i = 1:length(locs1)
    for j = 1:length(locs2)
        QRcode(i,j) = f(locs1(i),locs2(j));
    end
end
% compensate 
QRcode = QRcode; 


figure;
subplot(3,2,1);
imshow(Z2);
subplot(3,2,2);
imshow(Z3);
subplot(3,2,3);
plot(diff1);
hold on;
plot(locs1,diff1(locs1),'k^','markerfacecolor',[1 0 0]);
title(' Horizontal edge projection ');
subplot(3,2,4);
plot(diff2); 
hold on;
plot(locs2,diff2(locs2),'k^','markerfacecolor',[1 0 0]);
title(' Vertical edge projection ');

subplot(3,2,5);   
imshow(Z2,[]);
title(' Perspective corrected image ');
subplot(3,2,6);   
imshow(QRcode,[]);
title(' Normalized QR code ');

4. Simulation results

 

 

 

 A10-38