Separation of letters of license plates

Question

Blazej Staniak 2021-11-20

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1591384-separation-of-letters-of-license-plates

评论： Blazej Staniak 2021-11-22

Hello, as in the tilt, I would like to separate the individual letters of the registration plate. Can anyone tell me how to do this?

I would like to get the same effect as in the second photo

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

Blazej Staniak 2021-11-20

anyone know how to do it?

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Image Analyst 2021-11-20

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1591384-separation-of-letters-of-license-plates#answer_836344

Use ocr() in the Computer Vision Toolbox.

2 个评论
显示无隐藏无

Blazej Staniak 2021-11-20

I tried but I don't know how to use it exactly

Image Analyst 2021-11-21

在 MATLAB Online 中打开

Wow. Very strange. After getting the binary image from the screenshot you posted, I just did

% Do OCR on it.
txt = ocr(mask)
letters = strtrim(txt.Text)

and it worked fine. What did you do? Here is the full demo.

% Demo by Image Analyst
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 = 20;
markerSize = 40;
%--------------------------------------------------------------------------------------------------------
%    READ IN IMAGE
fileName = 'obraz_2021-11-20_110914.png';
grayImage = imread(fileName);
% Get the dimensions of the image.
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(grayImage)
if numberOfColorChannels > 1
    % It's not really gray scale like we expected - it's color.
    % Extract the blue channel.
    grayImage = grayImage(:, :, 3);
end
%--------------------------------------------------------------------------------------------------------
% Display the image.
subplot(3, 1, 1);
imshow(grayImage);
impixelinfo;
axis('on', 'image');
title('Original Gray Scale Image', 'FontSize', fontSize, 'Interpreter', 'None');
hold on
drawnow;
% Maximize window.
g = gcf;
g.WindowState = 'maximized'
drawnow;
% Crop the figure to get just the image, not all the tick labels and toolbars and surrounding blank space.
grayImage = grayImage(128:345, 189:1165)
% Display the image.
subplot(3, 1, 2);
imshow(grayImage);
impixelinfo;
axis('on', 'image');
title('Cropped Image', 'FontSize', fontSize, 'Interpreter', 'None');
hold on
drawnow;
%--------------------------------------------------------------------------------------------------------
% Get a mask using thresholding.
mask = ~imbinarize(grayImage);
mask = imclearborder(mask);
% Get rid of blobs less than 300 pixels in area.
% mask = bwareaopen(mask, 300);
% Display the image.
subplot(3, 1, 3);
imshow(mask, []);
impixelinfo;
axis('on', 'image');
title('Mask/Binary/Logical Image', 'FontSize', fontSize, 'Interpreter', 'None');
hold on
drawnow;
% Do OCR on it.
txt = ocr(mask)
letters = strtrim(txt.Text)
caption = sprintf('Mask/Binary/Logical Image.  Text = %s', letters);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

请先登录，再进行评论。

Answer 2

yanqi liu 2021-11-22

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1591384-separation-of-letters-of-license-plates#answer_837214

编辑：yanqi liu 2021-11-22

在 MATLAB Online 中打开

sir，may be use some image segment，such as

clc; clear all; close all;

img = imread('https://ww2.mathworks.cn/matlabcentral/answers/uploaded_files/807304/obraz_2021-11-20_110914.png');

img2 = imcrop(img, [94 129 1086 217]);

bw = im2bw(img2);

bw = ~bw;

bw = imclearborder(bw);

bw = bwareaopen(bw, round(numel(bw)*0.01));

[L,num] = bwlabel(bw);

stats = regionprops(L);

rects = cat(1, stats.BoundingBox);

rects = sortrows(rects, 1);

ims = [];

figure('Color','c');

for i = 1 : size(rects, 1)

ims{i} = imcrop(img2, round(rects(i,:)));

subplot(1,size(rects, 1),i); imshow(ims{i}, []);

end

figure; montage(ims, 'Size', [1 7], 'BackgroundColor', 'r', 'BorderSize', [2 2]);

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

Answer 3

Blazej Staniak 2021-11-22

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1591384-separation-of-letters-of-license-plates#answer_837234

This is not what I wanted, I have the code, the photo of this license plate I received from the whole photo of the car, so the effect of the cut plate is part of my program. Now I just need to separate the letters

2 个评论
显示无隐藏无

Image Analyst 2021-11-22

在 MATLAB Online 中打开

And what are you going to do once you have the letters into separate images? Get the number or letter they are, right? Well I did that for you and I got you the number. If you want to get each subimage, even though it is not necessary, you can use bwlabel and ismember

[labeledImage, numBlobs] = bwlabel(mask);
for k = 1 : numBlobs
    % Extract and save.
    thisBlob{k} = ismember(labeledImage, k);
    imshow(thisBlob{k});
    drawnow;
    pause(0.3); % Wait long enough to see it before showing the next one.
end