Master Thesis - Department of Computer Science
Master Thesis - Department of Computer Science
Master Thesis - Department of Computer Science
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
(a) (b)<br />
(c)<br />
(d)<br />
Minutia<br />
Figure A.1: (a) and (b) A local window containing ridge valley structures; (c) and (d)<br />
Curve (i.e. x-signature) obtained along the direction normal to the ridge orientation.<br />
image is divided into a set <strong>of</strong> W × W nonoverlapping blocks and a single local<br />
ridge orientation is defined for each block.<br />
• A frequency image (F ): A frequency image, F , is an N × N image, where<br />
F (i, j) represents the local ridge frequency <strong>of</strong> the ridge and valley structures<br />
in a local neighborhood along a direction normal to the local ridge orientation.<br />
The ridge and valley structures in a local neighborhood where minutiae or<br />
singular points appear do not form a well-defined sinusoidal-shaped wave (see<br />
Fig. A.1). In such situations, the frequency is defined as the average frequency<br />
in the neighborhood <strong>of</strong> block (i, j). Like orientation image, frequency image is<br />
specified block-wise.<br />
A.1.2 Normalization<br />
Let I(i, j) denote the gray-level value at pixel (i, j), M and V AR denote the estimated<br />
mean and variance <strong>of</strong> I, respectively, and G(i, j) denote the normalized gray-level<br />
value at pixel (i, j). The normalized image is defined as follows:<br />
⎧<br />
⎪⎨ M0 +<br />
G(i, j) =<br />
⎪⎩<br />
� V AR0(I(i,j)−M) 2<br />
V AR<br />
�<br />
V AR0(I(i,j)−M)<br />
M0 −<br />
2<br />
V AR<br />
124<br />
if I(i, j) > M<br />
Otherwise<br />
⎫<br />
⎪⎬<br />
⎪⎭<br />
(A.3)