mmdRuler
Detect defects in a ruler.

The gray-scale image of the ruler is read.

Image a = mmReadgray("mm3.tif");
mmShow(a);

a

The close top-hat operator followed by a thresholding is applied.

Image b = mmThreshad( mmCloseth(a,mmSebox(5)),40);
mmShow(b);

b

The vertical lines longer than 50 pixels are detected.

Image c = mmOpen(b,mmSeline(50,90));
mmShow(c);

c

It closes ruler tick marks gaps.

Image d =mmClose(c,mmSeline(15));
mmShow(d);

d

It detects all objects connected to the ruler tick markers.

Image e = mmInfrec(d,b);
mmShow(e);

e

It detects all objects vertically connected to the ruler tick mark. Note that the 3x1 rectangle is used as structuring element in the vertical reconstruction.

Image f = mmInfrec(d,b,mmSeline(3,90));
mmShow(f);

f

The residues obtained from the previous image.

Image g = mmSubm(e,f);
mmShow(g);

g

It uses an opening by an elementary cross structuring element to eliminate the artifacts.

Image h = mmOpen(g);
mmShow(h);

h

It detects the objects connected to ruler tick marks. A reconstruction from the ruler marks detected is applied.

Image i = mmInfrec(h, b);
mmShow(i);

i

Overlay the detected defect over the original image

mmShow(a,i);

a,i