require a code for automatic licencse plate recognition of vehicles.
4 次查看(过去 30 天)
显示 更早的评论
Hi...
I am doing a project on the concept of AUTOMATIC NUMBER PLATE RECOGNITION (ANPR) using matlab using artificial neural network for OCR(Optical Character Recognition). here we initially take an image of car number plate or license plate and perform Image enhancement, Image Segmentation and Character Recognition process to display the license plate characters as output of matlab code. I have executed half of the matlab code till dilation process and have got output successfully.. now I have the entire code of the project but I am getting an error and I am unable to remove it.. so can u please suggest ways to remove it or can u please correct that code... or can u please help me in writing a new code regarding this project... or if u have any ideas.. can u please send me the code...
fi = imread('noplate.jpg');
%imshow(fi)
fin = rgb2gray(fi);
imshow(fin);
d=double(fin)
%imshow(fin)
[r c]= size(d)
% Mexican filter operator
filter = [ 0 0 0 -1 -1 -1 0 0 0 ;
0 -1 -1 -3 -3 -3 -1 -1 0;
0 -1 -3 -3 -1 -3 -3 -1 0;
-1 -3 -3 6 13 6 -3 -3 -1;
-1 -3 -1 13 24 13 -1 -3 -1;
-1 -3 -3 -6 13 6 -3 -3 -1;
0 -1 -3 -3 -1 -3 -3 -1 0;
0 -1 -1 -3 -3 -3 -1 -1 0;
0 0 0 -1 -1 -1 0 0 0 ];
% creating image matrix for mexican hat operator
gm = zeros(r,c);
for i=5:2:r-5
for j=5:2:c-5
gm(i,j) = sum(sum(double(fin(i-4:i+4,j-4:j+4)).*filter,2));
end;
end;
% removing the unwanted edges by using a threshold
fh = gm>1200;
%Dilation operation
x = 1;
y =1;
fs = double(fh);
se = ones(3,3);
for x= 3:3:r-20
for y = 3:3:c-20
if(x+50<=r)
xend = x+50;
else
xend = r;
end;
if(y+100<=r)
yend = y + 150;
else
yend = c;
end;
if(sum(fh(x:xend,y))<=35||sum (fh(x,y:yend,2)<=60))
if(sum(fh(x,y:y+3),2)<=3) && (sum(fh(x,y:y+3),2)>2)
fs(x-2:x+2,y-2:y+2)=bwmorph(fh(x-2:x+2,y-2:y+2),'dilate',se);
end;
end;
end;
end;
%imshow(fin)
%image with dilation performed
f=double(fs);
[row col]=size(f);
%initialising a matrix for a segmented image
g=zeros(row,col);
gl=zeros(row,col);
label=1;
n=1;
x=1;
iter=[];
it=0;
ss_prev=0;
nn=[];
sss_mat=[];
for i=1:2:row
for j=1:2:col
r_pt=i;
c_pt=j;
if(g(r_pt,c_pt)==0)
while(true)
|%using 4 neighbour rule|
if(f(r_pt(n),c_pt(n))==1 && g(r_pt(n),c_pt(n))==0)
g(r_pt(n),c_pt(n))=label;
if(r_pt(n)+1<=row)
if(f(r_pt(n)+1,c_pt(n))==1)
r_pt=[r_pt r_pt(n)+1];
c_pt=[c_pt c_pt(n)];
x=x+1;
end;
end;
if(c_pt(n)-1>=1)
if(f(r_pt(n),c_pt(n)-1)==1)
r_pt=[r_pt r_pt(n)];
c_pt=[c_pt c_pt(n)-1];
x=x+1;
end;
end;
if(c_pt(n)+1<=col)
if(f(r_pt(n),c_pt(n)+1)==1)
r_pt=[r_pt r_pt(n)];
c_pt=[c_pt c_pt(n)+1];
x=x+1;
end;
end;
if(r_pt(n)-1>=1)
if(f(r_pt(n)-1,c_pt(n))==1)
r_pt=[r_pt r_pt(n)-1];
c_pt=[c_pt c_pt(n)];
x=x+1;
end;
end;
end;
if(n>=x)
break;
end;
n=n+1;
end;
y1=min(r_pt);
y2=max(r_pt);
x1=min(c_pt);
x2=max(c_pt);
a1=g(min(r_pt):max(r_pt),min(c_pt):max(c_pt));
f1=d(min(r_pt):max(r_pt),min(c_pt):max(c_pt));
[ra ca]=size(a1);
| if(n>=50)|
b1=bwlabel(a1);
ss=regionprops(b1,'euler number');
sss=struct2array(ss);
sss=min(sss);
sss_mat=[sss_mat sss];
if(sss<ss_prev && sss<0 && ca <=190 && ra<=60 && ca>=50 && ra >=15 && mean(mean(f1))<=220)
x_cor1=x1;
y_cor1=y1;
x_cor2=x2;
y_cor2=y2;
ss_prev=sss;
end;
label=label+1;
else
g(r_pt,c_pt)=0;
end;
end;
x=1;
n=1;
it=1;
end;
end;
if(exist('y_cor1')==1)
d(y_cor1:y_cor1+2,x_cor1:x_cor2)=255;
d(y_cor2:y_cor2+2,x_cor1:x_cor2)=255;
d(y_cor1:y_cor2,x_cor1:x_cor1+2)=255;
d(y_cor1:y_cor2,x_cor2:x_cor2+2)=255;
end;
% Segmented licence plate image
d=mat2gray(d);
|lp=d(y_cor1:y_cor2,x_cor1:x_cor2);|
%%%2. Character Segmentation
%License plate image, characters of wcich are to be segmented
lp1 = d(y_cor1:y_cor2,x_cor1:x_cor2);
[rl cl] = size(lp1);
% Median Filtering
lp = medfilt2(lp1,[3 3]);
% Contrast Enhancement
lpf = imadjust(lp,stretchlim(lp,[0.1 0.5]));
%creating output image matrix
output= zeros(rl,cl);
% Window for local threshold operation
dis = round(cl/7);
% Local threshold operation
for i=1:dis:cl
if(i+dis-1<=cl)
t=threshcal(lpf(:,i:i+dis-1),a);
for i=1:dis:cl
if(i+dis-1<=cl)
t=threshcal(lpf(:,i:i+dis-1),a);
output(:,i:i+dis-1)=lpf(:,i:i+dis-1)<=t;
else
t=threshcal(lpf(:,i:cl),a);
for z1=2:rl-1
for z2=i+5:cl-5
if(mean(mean(lpf(z1-1:z1+1,z2-5:z2+5)))<=t)
output(z1,z2)=1;
end;
end;
end;
output(:,i:cl)=lpf(:,i:cl)<=t;
end;
end;
end;
end;
% Structuring element for erosion operation
se = [1 1 1 1 1 1 1 1 1 1 1 1 1 1 1]
output = output - imerode(output,se);
[of lab lpdet] = reggrowl(logical(output),number);
% Segmented characters
lpdet = logical(lpdet);
% Character Recognition
% output String giving licence plate information
lpstr=[];
for i= 1:lab-1
R = lpdet(:,st:st+9);
st = st+10;
b = bwlabel(R);
% Feature extraction
ar = struct2array(regionprops(b,'area'));
or = struct2aarray(regionprops(b,'orientation'))/90;
eu = struct2array(regionprops(b,'eulernumber'))/10;
pe = struct2array(regionprops(b,'perimeter'));
mi = struct2array(regionprops(b,'minoraxislength'));
ma = struct2array(regionprops(b,'majoraxislength'));
temp = logical(R);
% Reflection X and Y coefficient determination
v1 = temp;
v1(:,6:10)=flipdim(temp(:,1:5),2);
vx = (v1 + temp)/2;
vx = vx>=0.5;
xcoef = sum(sum(temp),2)/sum(sum(vx),2);
v2 = temp;
v2(1:12,:) = flipdim(temp(13:24,:),1);
vy = (v2 + temp)/2;
vy = vy >= 0.5;
ycoef = sum(sum(temp),2)/sum(sum(vy),2);
ed = struct2array(regionprops(b,'equivdiameter'))/100;
[val pos] = max(fa);
vcoeff = pe(pos)/ar(pos);
mcoeff = ed(pos);
Rp = [xcoef/ycoef;pe(pos)/ar(pos);mi(pos)/ma(pos)];
answer=find(compet(A2)==1);
if(i<=numel(lpnum))
if(alphamat(answer)==lpnum(i))
numrc = numrc+1;
else
answ = find(alphamat==lpnum(i));
err(answ) = err(answ) + 1;
end;
end;
lpstr = [lpstr alphamat(answer)];
end;
numc = numc + numel(lpnum);
if(strcmp(lpstr,lpnum)==1)
tr = tr + 1;
sr = strcat(num2str(num),'/',num2str(1),'//');
casep = [casep sr];
else
fr = fr +1;
sr = strcat(num2str(num),'/',num2str(1),'/',num2str(answer),'//');
casen = [casen sr];
end;
Thanking you, With regards, Rakshitha
12 个评论
Walter Roberson
2017-1-16
Hammad Sarwar: the person who posted this question has not been active for nearly 4 years, and will not be notified of your comment. You would be more likely to get a response if you started a new Question and described what you need to do.
Image Analyst
2017-1-16
Hammad, see my File Exchange for several color segmentation demos http://www.mathworks.com/matlabcentral/fileexchange/?term=authorid%3A31862. In addition, try the Color Thresholder app on the Apps tab of the tool ribbon of MATLAB.
采纳的回答
mahjoub el attar
2012-4-4
function [LPImageGray,LPImageBW,BW2,BW3,stats,LPImageTH,EdgeImage,imrefdata,ids,im] = AnprEngine( LPImage,thresh)
%ANPRENGINE Summary of this function goes here
% Process image input analytics and output licence plate alphanumeric string
% Based on static image
tic
Variables Initialization EligibleBands = zeros(3,2); Pointer = 1; Sensing = 0; MinimalHeight = 15;
srcData = load('AnprSysData.mat');
imrefdata = srcData.AlphaNumRef;
im = [];
C = zeros(109);
% toc
Pre-process LPImage
LPImageGray = rgb2gray(LPImage);
LPImageTH = imtophat(LPImageGray,strel('ball',12,7));%Close ball 18 7/ Far ball 12 4
imadjust(LPImageTH,[0;0.1],[0;1]);
%[EdgeImage, thr, gv, gh] = edge(LPImageGray,'sobel','nothinning');
[EdgeImage, ~, ~] = edge(LPImageGray,'sobel');
LPImageBW = ~im2bw(LPImageTH,thresh);
%LPImageVH = edge(LPImageGray, 'sobel',0.11,'vertical');
%sz = size(LPImage);
toc
Skew detection Spacial Transformation correction
Process Image ROI candidates, Heuristic and Bands Elimamination
toc
ProjectionVH = sum(LPImageVH,2);%Compute sum of Horizontal Projection of vertical lines
maxIndexValue = find(ProjectionVH == max(ProjectionVH), 1,'last');%Find Max Index Value of ProjectionVH 1*m Matrix
% Locate most significative eligible bands.
sensor = mean(ProjectionVH);% Define standard deviation of ProjectionVH to find eligible bands
for idx = 1:sz(1,1)
if(ProjectionVH(idx) > sensor && Sensing == 0)
Sensing = 1;
EligibleBands(Pointer, 1) = idx;
end
if(ProjectionVH(idx) < sensor && Sensing == 1)
Sensing = 0;
EligibleBands(Pointer, 2) = idx;
if((EligibleBands(Pointer, 2)-EligibleBands(Pointer, 1))>MinimalHeight)
Pointer = Pointer + 1;
end
end
end
for i = 1:sz(1,1)
if(i < EligibleBands(1,1) || i > EligibleBands(1,2))
LPImageBW(i,:) = 0;
end
end
Locate Licence Plate Bands
Blobs Analysis
CC = bwconncomp(LPImageBW);
stats = regionprops(CC, 'Area','BoundingBox','Image');
ids = find([stats.Area] > 8 & [stats.Area] < 250);
BW2 = ismember(labelmatrix(CC),ids);
toc
Blobs Analysis
CC2 = bwconncomp(~LPImageBW);
stats2 = regionprops(CC2,'Area','BoundingBox','Eccentricity');
ids2 = find([stats2.Area] > 20 & [stats2.Eccentricity] > 0.95);
BW3 = ismember(labelmatrix(CC2),ids2);
%BW3 = [];% ismember(labelmatrix(CC2),ids2);
toc
Pre-OCR
for k=1:length(ids)
imOriginal = stats(ids(k)).Image;
BB = stats(ids(k)).BoundingBox;
NormIm{1,1} = resizem(imOriginal,[60,30]);
NormIm{2,1} = BB(4)/BB(3);
[NormIm{3,1} NormIm{4,1}, NormIm{5,1}] = getMaxCorrelationRate(NormIm{1,1},imrefdata);
if(BB(4)/BB(3)>=1.4 && BB(4)/BB(3)<=2 || BB(4)/BB(3)>=3 && BB(4)/BB(3)<=10)
im = [im NormIm];
%imshow(cell2mat(PD(1,:))) %to display all column in first row on NormIm
%output
%imshow(cell2mat(E2(2)))
end
end
toc
OCR Function
function [Rate,id, Letter] = getMaxCorrelationRate(imOriginal,imrefdata)
for n=1:length(imrefdata)
Rates(n) = corr2(imOriginal,cell2mat(imrefdata(1,n)));
end
[Rate,id] = max(Rates);
if(Rate>0.48)
Letter = imrefdata{2,id};
else
Letter ='';
end;
end
OCR AlphaNumerical resolution
LPNumber = 'Hello Plate';
%%Output
end
% It uses correlation instead of ANN.
% All is in AnprSysData.mat file Chars are indexed from 1 to 109
% Author Mahjoub El attar 2002-2006 for smartKam. For more information feel free to contact me at my profile email contact address.
8 个评论
mahjoub el attar
2012-4-6
Hello, "bwconncomp" is an image processing built-in function.
On binary connected component!
更多回答(3 个)
Ahmad Madzarul Musa
2017-1-3
Undefined function or variable 'y_cor1'.
Error in trynerror (line 278) lp=d(y_cor1:y_cor2,x_cor1:x_cor2);
mahjoub el attar
2012-4-4
fi = imread('noplate.jpg');
%imshow(fi)
fin = rgb2gray(fi);
imshow(fin);
d=double(fin)
%imshow(fin)
[r c]= size(d)
% Mexican filter operator
filter = [ 0 0 0 -1 -1 -1 0 0 0 ; 0 -1 -1 -3 -3 -3 -1 -1 0; 0 -1 -3 -3 -1 -3 -3 -1 0; -1 -3 -3 6 13 6 -3 -3 -1; -1 -3 -1 13 24 13 -1 -3 -1; -1 -3 -3 -6 13 6 -3 -3 -1; 0 -1 -3 -3 -1 -3 -3 -1 0; 0 -1 -1 -3 -3 -3 -1 -1 0; 0 0 0 -1 -1 -1 0 0 0 ];
% creating image matrix for mexican hat operator
gm = zeros(r,c);
for i=5:2:r-5
for j=5:2:c-5
gm(i,j) = sum(sum(double(fin(i-4:i+4,j-4:j+4)).*filter,2));
end;
end;
% removing the unwanted edges by using a threshold
fh = gm>1200;
%Dilation operation
x = 1;
y =1;
fs = double(fh);
se = ones(3,3);
for x= 3:3:r-20
for y = 3:3:c-20
if(x+50<=r)
xend = x+50;
else
xend = r;
end;
if(y+100<=r)
yend = y + 150;
else
yend = c;
end;
if(sum(fh(x:xend,y))<=35||sum (fh(x,y:yend,2)<=60))
if(sum(fh(x,y:y+3),2)<=3) && (sum(fh(x,y:y+3),2)>2)
fs(x-2:x+2,y-2:y+2)=bwmorph(fh(x-2:x+2,y-2:y+2),'dilate',se);
end;
end;
end;
end;
%imshow(fin)
%image with dilation performed
f=double(fs);
[row col]=size(f);
%initialising a matrix for a segmented image
g=zeros(row,col);
gl=zeros(row,col);
label=1;
n=1;
x=1;
iter=[];
it=0;
ss_prev=0;
nn=[];
sss_mat=[];
for i=1:2:row
for j=1:2:col
r_pt=i;
c_pt=j;
if(g(r_pt,c_pt)==0)
while(true)
%using 4 neighbour rule
if(f(r_pt(n),c_pt(n))==1 && g(r_pt(n),c_pt(n))==0)
g(r_pt(n),c_pt(n))=label;
if(r_pt(n)+1<=row)
if(f(r_pt(n)+1,c_pt(n))==1)
r_pt=[r_pt r_pt(n)+1];
c_pt=[c_pt c_pt(n)];
x=x+1;
end;
end;
if(c_pt(n)-1>=1)
if(f(r_pt(n),c_pt(n)-1)==1)
r_pt=[r_pt r_pt(n)];
c_pt=[c_pt c_pt(n)-1];
x=x+1;
end;
end;
if(c_pt(n)+1<=col)
if(f(r_pt(n),c_pt(n)+1)==1)
r_pt=[r_pt r_pt(n)];
c_pt=[c_pt c_pt(n)+1];
x=x+1;
end;
end;
if(r_pt(n)-1>=1)
if(f(r_pt(n)-1,c_pt(n))==1)
r_pt=[r_pt r_pt(n)-1];
c_pt=[c_pt c_pt(n)];
x=x+1;
end;
end;
end;
if(n>=x)
break;
end;
n=n+1;
end;
y1=min(r_pt);
y2=max(r_pt);
x1=min(c_pt);
x2=max(c_pt);
a1=g(min(r_pt):max(r_pt),min(c_pt):max(c_pt));
f1=d(min(r_pt):max(r_pt),min(c_pt):max(c_pt));
[ra ca]=size(a1);
| if(n>=50)|
b1=bwlabel(a1);
ss=regionprops(b1,'euler number');
sss=struct2array(ss);
sss=min(sss);
sss_mat=[sss_mat sss];
if(sss<ss_prev && sss<0 && ca <=190 && ra<=60 && ca>=50 && ra >=15 && mean(mean(f1))<=220)
x_cor1=x1;
y_cor1=y1;
x_cor2=x2;
y_cor2=y2;
ss_prev=sss;
end;
label=label+1;
else
g(r_pt,c_pt)=0;
end;
end;
x=1;
n=1;
it=1;
end;
end;
if(exist('y_cor1')==1)
d(y_cor1:y_cor1+2,x_cor1:x_cor2)=255;
d(y_cor2:y_cor2+2,x_cor1:x_cor2)=255;
d(y_cor1:y_cor2,x_cor1:x_cor1+2)=255;
d(y_cor1:y_cor2,x_cor2:x_cor2+2)=255;
end;
% Segmented licence plate image
d=mat2gray(d);
lp=d(y_cor1:y_cor2,x_cor1:x_cor2);
%%%2. Character Segmentation
%License plate image, characters of wcich are to be segmented
lp1 = d(y_cor1:y_cor2,x_cor1:x_cor2);
[rl cl] = size(lp1);
% Median Filtering
lp = medfilt2(lp1,[3 3]);
% Contrast Enhancement
lpf = imadjust(lp,stretchlim(lp,[0.1 0.5]));
%creating output image matrix
output= zeros(rl,cl);
% Window for local threshold operation
dis = round(cl/7);
% Local threshold operation
for i=1:dis:cl
if(i+dis-1<=cl)
t=threshcal(lpf(:,i:i+dis-1),a);
for i=1:dis:cl
if(i+dis-1<=cl)
t=threshcal(lpf(:,i:i+dis-1),a);
output(:,i:i+dis-1)=lpf(:,i:i+dis-1)<=t;
else
t=threshcal(lpf(:,i:cl),a);
for z1=2:rl-1
for z2=i+5:cl-5
if(mean(mean(lpf(z1-1:z1+1,z2-5:z2+5)))<=t)
output(z1,z2)=1;
end;
end;
end;
output(:,i:cl)=lpf(:,i:cl)<=t;
end;
end;
end;
end;
% Structuring element for erosion operation
se = [1 1 1 1 1 1 1 1 1 1 1 1 1 1 1]
output = output - imerode(output,se);
[of lab lpdet] = reggrowl(logical(output),number);
% Segmented characters
lpdet = logical(lpdet);
% Character Recognition
% output String giving licence plate information
lpstr=[];
for i= 1:lab-1
R = lpdet(:,st:st+9);
st = st+10;
b = bwlabel(R);
% Feature extraction
ar = struct2array(regionprops(b,'area'));
or = struct2aarray(regionprops(b,'orientation'))/90;
eu = struct2array(regionprops(b,'eulernumber'))/10;
pe = struct2array(regionprops(b,'perimeter'));
mi = struct2array(regionprops(b,'minoraxislength'));
ma = struct2array(regionprops(b,'majoraxislength'));
temp = logical(R);
% Reflection X and Y coefficient determination
v1 = temp;
v1(:,6:10)=flipdim(temp(:,1:5),2);
vx = (v1 + temp)/2;
vx = vx>=0.5;
xcoef = sum(sum(temp),2)/sum(sum(vx),2);
v2 = temp;
v2(1:12,:) = flipdim(temp(13:24,:),1);
vy = (v2 + temp)/2;
vy = vy >= 0.5;
ycoef = sum(sum(temp),2)/sum(sum(vy),2);
ed = struct2array(regionprops(b,'equivdiameter'))/100;
[val pos] = max(fa);
vcoeff = pe(pos)/ar(pos);
mcoeff = ed(pos);
Rp = [xcoef/ycoef;pe(pos)/ar(pos);mi(pos)/ma(pos)];
answer=find(compet(A2)==1);
if(i<=numel(lpnum))
if(alphamat(answer)==lpnum(i))
numrc = numrc+1;
else
answ = find(alphamat==lpnum(i));
err(answ) = err(answ) + 1;
end;
end;
lpstr = [lpstr alphamat(answer)];
end;
numc = numc + numel(lpnum);
if(strcmp(lpstr,lpnum)==1)
tr = tr + 1;
sr = strcat(num2str(num),'/',num2str(1),'//');
casep = [casep sr];
else
fr = fr +1;
sr = strcat(num2str(num),'/',num2str(1),'/',num2str(answer),'//');
casen = [casen sr];
end;
%%Now your code is a little more clear....
5 个评论
Mutturaj Hubballi
2015-2-3
this code showing an error in the lp line..what is that lp variable its not taking into it
Twinkle Pajiyar
2015-9-21
its giving an error on line lp=d(y_cor1:y_cor2,x_cor1:x_cor2); as Undefined function or variable 'y_cor1'.
mahjoub el attar
2012-4-6
Hi, You must use it as this. A = AnprEngine(Image, 0.17); Ok.... let me zip all files with the User-Interface "GUI" and testing snapshots.
7 个评论
Shaik Vaseem
2020-2-4
Can you please suggest us a solution that how the frames are called into the code automatically to detect the number plate from that frames.
Walter Roberson
2020-2-4
No, we cannot suggest any solution to that. License plates can look like anything . If you were to look at a car and not see any obvious plate, but happened to notice that the car had one pink tailpipe and one green tailpipe, then the exact color and positions of the tailpipes could be the license plate. The "baby on board" sticker on the side of the car could be the license plate.
In order for a solution to be practical, you would need to restrict your scope to only specific kinds of license plates. And even then note what I wrote above about "Do not assume that license plates will contrast with the color of the car."
另请参阅
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!