mmdLabeltext
Segmenting letters, words and paragraphs.

The text image is read.

Image f = mmReadgray("stext.tif");
mmShow(f);

f

The letters are the main connected components in the image. So we use the classical 8-connectivity criteria for identify each letter.

Image fl=mmLabel(f, mmSebox());
mmLblshow(fl);

fl

The words are made of closed letters. In this case we use a connectivity specified by a rectangle structuring element of 7 pixels high and 11 pixels width, so any two pixels that can be hit by this rectangle, belong to the same connected component. The values 7 and 11 were chosen experimentally and depend on the font size.

Image one(11, 7, 1, "uint8", (double)1);
Strel sew = mmImg2se(mmBinary(one));
Image fw = mmLabel(f, sew);
mmLblshow(fw);

fw

Similarly, paragraphs are closed words. In this case the connectivity is given by a rectangle of 35 by 20 pixels.

Image one2(35, 20, 1, "uint8", (double)1);
Strel sep = mmImg2se(mmBinary(one2));
Image fp = mmLabel(f, sep);
mmLblshow(fp);

fp