How can I extract text from image respecting the distance between words?

I am trying to extract text from an image of printed text. Along with the text itself, I am interested in detecting the spaces between the words as well. The spaces between words are not consistent (deliberate) and that is something I want detected.

To achieved this I first had to extract the text lines. I achieved that using the projection profile code attached (code copied from one of the answers by ImageAnalyst). The attached image shows the output of this code.

One way I thought of achieving this was by counting the number of white pixels between the words, if I know the number of pixels taken by a single space (say n), I could just determine the number of spaces by dividing the white pixels between the words by this 'n' to get the number of spaces.

I tried that but it did not go as planned, the results are very conflicting, even when compared against known ground truth values. Determining a baseline of every text line is proving to be difficult, for a single space between two words I am getting different pixel count. This is because as counting the white pixels from letter d to b is different from counting the white pixels from c to s (the white pixels within the curve of c is also sometimes counted.)

Any guidance or suggestions would be greatly appreciated.

Thank you

Answer 1

[Ben Drebing]

Try looking at this answer:

https://www.mathworks.com/matlabcentral/answers/260676-how-to-obtain-the-space-between-two-words-in-a-given-sentence#answer_203702

This code can only process 1 line of text at a time. But I was able to get fairly good results on the first line of your data when I set

   fontSize = 6;

[Abdellatif zouak]

thank you @ben Drebing. it still one problem is to know the space between the last word in the line n and the first word in line n+1. if you have an idea how I can do it I would be greatly appreciated.

[Ben Drebing]

I think you can modify that Untitled2.m file to concatenate all the lines into one long line and then you can use our solution on this image. You can create a variable called "allOneLine" which has all the text but in one line. Maybe something like

img = imread('Lines.png');

[rows, columns, dim] = size(img);
if dim > 1  
    grayImage = img(:, :, 2);
end

% Display the original gray scale image.

% Threshold the image.
binaryImage = grayImage < 210;  

% Get rid of small areaas of 14 pixels or less
binaryImage = ~bwareaopen(binaryImage, 15);

% Vertical Profile
verticalProfile = sum(binaryImage, 2); 

rowsWithText = verticalProfile < 600;  

% Find top and bottom lines
topLines = find(diff(rowsWithText) == 1);
bottomLines = find(diff(rowsWithText) == -1);
allOneLine = [];

for j = 1 : length(topLines) 
    topRow = topLines(j);
    bottomRow = bottomLines(j);
    thisLine = binaryImage(topRow:bottomRow, :);
    allOneLine = [ allOneLine , thisLine]; % Here we append the lines
end

imshow(allOneLine); % Show our new image