mmdPieces
Classify two dimensional pieces.

The binary image of the pieces is read.

Image a = mmBinary(mmReadgray("pieces_bw.tif"));
mmShow(a);

a

A thickening that preserves the number of connected objects is applied to reduce contour noise.

unsigned char _rA[9] = {0,1,0,1,0,1,0,0,0};
unsigned char _rB[9] = {0,0,0,0,1,0,0,0,0};
Strel seA = mmImg2se(Image(3,3,1,"binary",(char *)_rA));
Strel seB = mmImg2se(Image(3,3,1,"binary",(char *)_rB));
Interval iAB = mmSe2hmt(seA,seB);
printf("%s\n", (char *)mmIntershow(iAB));
Image b = mmThick(a, iAB);
mmShow(b);

. 1 . 
1 0 1 
. . .

b

The homotopic skeleton by thinning is created.

Image c = mmThin(b);
mmShow(c);

c

The open lines of the skeleton are pruned by the end point thinning. The remaining skeleton components will be loops, identifying the rings.

Image d = mmThin(c,mmEndpoints());
mmShow(c,d);

c,d

Extraction of the rings by reconstruction of the thicked image from the filtered skeleton.

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

e

Restriction of the objects detected to the input-image.

Image f = mmIntersec(a,e);
mmShow(f);

f

It eliminates the skeleton of the rings.

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

g

It removes sucessively 4 end-points to let T junctions just on T-pins.

Image h = mmThin(g, mmEndpoints(), 4);
mmShow(h);

h

It detects triple points, applying the union of matchings with the template rotated 90 degrees. These points will identify (mark) the T-pins.

unsigned char _sA[9] = {0,1,0,1,1,1,0,0,0};
unsigned char _sB[9] = {1,0,1,0,0,0,0,1,0};
Strel seA2 = mmImg2se(Image(3,3,1,"binary",(char *)_sA));
Strel seB2 = mmImg2se(Image(3,3,1,"binary",(char *)_sB));
Image i = mmSupcanon(h, mmSe2hmt(seA2,seB2));
mmShow(h,mmDil(i,mmSedisk(2)));

h,mmDil(i,mmSedisk(2))

Detection of the T-pins by reconstruction of the ticked image from the T-pin markers.

Image j = mmInfrec(i,b,mmSebox());
mmShow(j);

j

Restriction of the objects detect to the input image

Image k = mmIntersec(a,j);
mmShow(k);

k

The nails are imediatly detected by the subtration of the images of the rings and T-pints from the input image.

Image l = mmSubm(mmSubm(a,f),k);
mmShow(l);

l

The result of the classification is presented in a pseudo color image.

Image m = mmGray(f,"uint8",1);
Image n = mmGray(k,"uint8",2);
Image o = mmGray(l,"uint8",3);
Image p = mmUnion(m,n,o);
mmLblshow(p);

p