fixed 8 and B problem and migrate to python3

[sstefanov]

[rmast]

I watched your PR. The original routine, which was not fully python3 did this conversion from this source picture:

https://user-images.githubusercontent.com/3341558/175789293-f39ddfdb-6f3e-4598-8d16-80a1f4a88b36.jpg

Your version gives this picture:

You can see the big text on the top now gets the wrong inversions.

[rmast]

When I run the original matlab code in Octave I get a better result, however missing most of the dots of the characters, so this jasonlfunk-translation does not fully represent the original matlab-code:

function[out_bw] = kasar_binarize(im)
%--------------------------------------------------------------------------
% COLOR TEXT BINARIZATION
% Author: Thotreingam Kasar
% MILE, Department of Electrical Enginerring, 
% Indian Institute of Science, Bangalore, INDIA.
% Last modified on: 08/11/2008
%--------------------------------------------------------------------------
% Ref: T Kasar, J Kumar and A G Ramakrishnan, "Font and background color
% independent text binarization", Proc. 2nd Intl. Workshop on Camera-Based 
% Document Analysis and Recognition, pp. 3-9, 2007.
%--------------------------------------------------------------------------
pkg load image
im = imread('175789293-f39ddfdb-6f3e-4598-8d16-80a1f4a88b36.jpg');
%figure,imshow(im);
img = rgb2gray(im);
[m,n,o] = size(im);
% Color Edge Detection
er = edge(im(:,:,1),'canny',[0.2 0.3],1);
eg = edge(im(:,:,2),'canny',[0.2 0.3],1);
eb = edge(im(:,:,3),'canny',[0.2 0.3],1);
e = er|eg|eb;

% Connected Component Analysis
[L,num]= bwlabel(e,8);
stats = regionprops(L,'BoundingBox','Area');
bbox = cat(1, stats.BoundingBox);
barea = cat(1,stats.Area);
aspect = bbox(:,4)./bbox(:,3);
% Heuristic Filtering
valid = find(not(xor(bbox(:,4)<0.8*m,bbox(:,3)<0.8*n))&(barea>15)&...
            (aspect>0.1 & aspect<10)&(bbox(:,3).*bbox(:,4)<...
             m*n/5*ones(size(bbox,1),1)));

% Edge-Box Filtering starts------------------------------------------------
vbox = bbox(valid,:);
remov_ind = [];
for i = 1:size(vbox,1)
    ref =  vbox(i,:);
    X = vbox(:,1);
    Y = vbox(:,2);
    W = vbox(:,3);
    H = vbox(:,4);
    subi = find((X>=ref(1)& X + W<ref(1)+ref(3))&...
        (X>ref(1)& X + W<=ref(1)+ref(3))&...
        (Y>=ref(2)& Y + H<ref(2)+ref(4))&...
        (Y>ref(2)& Y + H<=ref(2)+ref(4)));
    ff  = isempty(subi);
    if ff ~=1
        if(length(subi)<3)
            remov_ind = [remov_ind ;subi];
        else
            remov_ind = [remov_ind ;i];
        end
    end
end
vbox(remov_ind,:) = [];
%Edge-Box Filtering ends---------------------------------------------------

%figure,imshow(e);%Display the final set of CC considered for binarization
% hold on;
vbox = round(vbox);
out_bw = ones(size(img));
offset  = 1; % parameter for selecting the background pixels
for i  =1:size(vbox,1)
    bx(:,:,i) = [vbox(i,1)              vbox(i,2)
        vbox(i,1)              vbox(i,2) + vbox(i,4)
        vbox(i,1) + vbox(i,3)  vbox(i,2) + vbox(i,4)
        vbox(i,1) + vbox(i,3)  vbox(i,2)
        vbox(i,1)              vbox(i,2)]';
%     line_handle = line(bx(1,:,i),bx(2,:,i));
%     set(line_handle,'Color',[1 1 0],'linewidth',2);

    % Estimate the foreground and background intensities for each CC
    block = img(vbox(i,2):vbox(i,2) + vbox(i,4)-1,...
        vbox(i,1):vbox(i,1) + vbox(i,3)-1);
    blocke = e(vbox(i,2):vbox(i,2) + vbox(i,4)-1,...
        vbox(i,1):vbox(i,1) + vbox(i,3)-1);
    FG = block(blocke==1);
    foregr = mean(FG); % foreground intensity
    bg = [];
    if (vbox(i,2)-offset>1)&(vbox(i,1)-offset>1)
        bg = [bg img(vbox(i,2)-offset,vbox(i,1)-offset) img(vbox(i,2)-offset,vbox(i,1)) img(vbox(i,2),vbox(i,1)-offset) ];
    end
    if(vbox(i,2) + vbox(i,4) + offset<m)&(vbox(i,1)-offset>1 )
        bg = [bg img(vbox(i,2) + vbox(i,4) + offset ,vbox(i,1) - offset) img(vbox(i,2) + vbox(i,4),vbox(i,1)-offset) img(vbox(i,2) + vbox(i,4)+offset,vbox(i,1))];
    end
    if (vbox(i,2) + vbox(i,4) + offset<m)&(vbox(i,1)+vbox(i,3)+offset<n)
        bg = [bg img(vbox(i,2) + vbox(i,4) + offset ,vbox(i,1)+vbox(i,3)+offset) img(vbox(i,2) + vbox(i,4),vbox(i,1)+vbox(i,3)+offset) img(vbox(i,2) + vbox(i,4) + offset ,vbox(i,1)+vbox(i,3))];
    end
    if (vbox(i,2)-offset>1 )&(vbox(i,1)+vbox(i,3)+offset<n)
        bg = [bg img(vbox(i,2)-offset,vbox(i,1)+vbox(i,3)+offset) img(vbox(i,2)-offset,vbox(i,1)+vbox(i,3)) img(vbox(i,2),vbox(i,1)+vbox(i,3)+offset)];
    end
    backgr = median(double(bg)); % Background intensity
    bin_im = double(block)>(foregr);
    if foregr>=backgr
        out_bw(vbox(i,2):vbox(i,2) + vbox(i,4)-1,vbox(i,1):vbox(i,1) + vbox(i,3)-1) = not(bin_im);
    elseif  foregr<backgr
        out_bw(vbox(i,2):vbox(i,2) + vbox(i,4)-1,vbox(i,1):vbox(i,1) + vbox(i,3)-1) = bin_im;
    end
end


imwrite(out_bw,"Kasar2.png");