20.01.2013 Views

Master Thesis - Department of Computer Science

Master Thesis - Department of Computer Science

Master Thesis - Department of Computer Science

SHOW MORE
SHOW LESS

Create successful ePaper yourself

Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.

(a) (b)<br />

Figure A.12: Binarized images <strong>of</strong> two input fingerprints shown in Fig. A.2.<br />

slit-sums calculated in eight different directions. That is,<br />

Smax = max<br />

i=0,..,7 Si,<br />

Smin = min<br />

i=0,..,7 Si,<br />

Ssum =<br />

7�<br />

Si<br />

i=0<br />

Finally, the binarized image can be obtained by applying one <strong>of</strong> the following equa-<br />

tions.<br />

B(i, j) =<br />

B(i, j) =<br />

B(i, j) =<br />

⎧<br />

⎪⎨<br />

1 if H(i, j) ≥ Ssum/12<br />

⎫<br />

⎪⎬<br />

⎪⎩ 0 Otherwise<br />

⎪⎭<br />

⎧<br />

⎪⎨ 1<br />

⎫<br />

⎪⎬<br />

if (Smax + Smin) ≥ Ssum/4<br />

⎪⎩ 0 Otherwise<br />

⎪⎭<br />

⎧<br />

⎪⎨ 1<br />

⎫<br />

⎪⎬<br />

if (4H(i, j)Smax + Smin) ≥ 3Ssum/8<br />

⎪⎩ 0 Otherwise<br />

⎪⎭<br />

(A.31)<br />

(A.32)<br />

(A.33)<br />

We used the first equation for obtaining binarized image. Fig. A.12 shows the binarized<br />

output for the input fingerprints shown in Fig. A.2.<br />

A.4 Image Thinning<br />

For thinning, we used the method proposed by Zhang and Suen [142]. The input for<br />

this method is a binary fingerprint image with pixels <strong>of</strong> ridge and valley having value<br />

1 (black) and value 0 (white), respectively. A 3 × 3 window as shown in Fig. A.13<br />

135

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!