How to segment cursive/connected (Arabic) word into characters?

Question

ana ain 2016-1-6

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/262787-how-to-segment-cursive-connected-arabic-word-into-characters

编辑： Image Analyst 2020-3-2

I want to segment the connected character. Based on the histogram/profile, i assume that I could segment the character based on it's baseline. but, I still couldn't built an appropriate code to make it works.

I hope, anyone could help :)

The following is the code that could segment isolated character very well. But, still not work for connected character.

% // Original Code by Soumyadeep Sinha //
  % Saving each  single segmented character as one file 
    function [segm] = trysegment (a)
    myFolder = 'D:\1. Thesis FINISH!!!\Data set\trial';
    level = graythresh (a);
    bw = im2bw (a, level);
    b = imcomplement (bw);
    i= padarray(b,[0 10]);
    verticalProjection = sum(i, 1);
    set(gcf, 'Name', 'Trying Segmentation for Cursive', 'NumberTitle', 'Off') 
    subplot(2, 2, 1);imshow(i); 
    subplot(2,2,3);
    plot(verticalProjection, 'b-'); %histogram show by this code
    % hist(reshape(input,[],3),1:max(input(:))); 
    grid on;
    % % t = verticalProjection;
    % % t(t==0) = inf;
    % % mayukh = min(t)
    % 0 where there is background, 1 where there are letters
    letterLocations = verticalProjection > 0; 
    % Find Rising and falling edges
    d = diff(letterLocations);
    startingColumns = find(d>0);
    endingColumns = find(d<0);
    % Extract each region
    y=1;
    for k = 1 : length(startingColumns)
      % Get sub image of just one character...
      subImage = i(:, startingColumns(k):endingColumns(k)); 
    %   se = strel('rectangle',[2 4]);
    %   dil = imdilate(subImage, se); 
      th = bwmorph(subImage,'thin',Inf);
      n = imresize (th, [64 NaN], 'bilinear');
      figure, imshow (n);  
    [L,num] = bwlabeln(n);
    for z= 1 : num
    bw= ismember(L, z);
    % Construct filename for this particular image.
    baseFileName = sprintf('char %d.png', y);
    y=y+1;
    % Prepend the folder to make the full file name.
    fullFileName = fullfile(myFolder, baseFileName);
    % Do the write to disk.
    imwrite(bw, fullFileName);
    % subplot(2,2,4);
    % pause(2);
    % imshow(bw);
    end
    % y=y+1;
    end;
    segm = (n);

This is the sample of image.

%

11 个评论
显示 9更早的评论隐藏 9更早的评论

Mohamed sidhoum 2020-3-1

编辑：Image Analyst 2020-3-2

Hey ana,

I want just a help. I saw in ResearchGate that a professor sent you the method on how to segment an Arabic handwriitng word with MATLAB, (with each letter of the word in a picture). Can please email me? I need the code for my mastery final project and I'm stuck.

email : sidhoummohamedcherif@gmail.com

Have a nice day .

Image Analyst 2020-3-2

编辑：Image Analyst 2020-3-2

Mohamed, please see my attached demo for the Bengali language. Maybe it's similar enough for you to adapt.

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

chandrapal Singh 2017-12-1

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/262787-how-to-segment-cursive-connected-arabic-word-into-characters#answer_294140

segmentation_code.m

Blob analysis

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 2

Image Analyst 2017-12-1

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/262787-how-to-segment-cursive-connected-arabic-word-into-characters#answer_294152

在 MATLAB Online 中打开

See http://www.visionbib.com/bibliography/contentschar.html#OCR,%20Document%20Analysis%20and%20Character%20Recognition%20Systems

4.8 Other Character Sets
4.8.1 Devanagari, Indic, Hindi, Hindu, Bangla, Bengali, Telugu, Characters
4.8.2 Arabic Character Recognition
4.8.3 Arabic Recognition, Word Level, Word Spotting
4.8.4 Farsi, Persian Character Recognition