Could someone explain about character segmentation and normalization for Optical character recognition? Complete with it's code?

Question

0 Stimmen

Could someone explain about character segmentation and normalization (especially high normalization) for Optical character recognition? Complete with it's code. If available especially for Arabic character image.

I've seen the code below (segmentation) and it's simple explanation, is there more complete explanation? but especially for optical character recognition segmentation and normalization.

stats = regionprops(img3); %segmentation
S = ' ';
for index=1:length(stats)
if stats(index).Area > 200 && stats(index).BoundingBox(3)*stats(index).BoundingBox(4) < 30000
      x = ceil(stats(index).BoundingBox(1));
      y= ceil(stats(index).BoundingBox(2));
      widthX = floor(stats(index).BoundingBox(3)-1);
      widthY = floor(stats(index).BoundingBox(4)-1);
      subimage(index) = {img3(y:y+widthY,x:x+widthX,:)};