10. Concept of Neighbors
In order to capture ridge-adjacency information, the
concept of neighbors is introduced. Neighbors come in
two varieties: end neighbors and side neighbors.
•End neighbors are those ridges that share a common
joining.
•Ridge Ri is said to "see" ridge Rj as a neighbor
if a perpendicular emanating from some point on Ri
intersects Rj without crossing any other ridge.
17. Solid-state fingerprint
sensor
1. Challenge for
traditional algorithms
2. Small contact area
0:6"0:6"
3. Less minutiae points
Optical Digital Biometrics
sensor
1. Contact area 1” X 1”
2. 480 X 508 pixels
3. More minutiae points
19. Suitable approach?
The minutiae based
matching schemes
will not perform well
in such situations
due to the lack of a
sufficient number of
minutiae points
between the two
impressions.
20. Suitable approach
Hybrid approach to fingerprint matching that
combines a minutiae-based representation of
the fingerprint with a Gabor-filter
(texture-based) representation for matching
purposes.
22. Matching
Matching an input image with a stored template
involves computing the sum of the squared
differences between the two feature vectors after
discarding missing values. This distance is
normalized by the number of valid feature values
used to compute the distance. The matching
score is combined with that obtained from the
minutiae-based method, using the sum rule of
combination. If the matching score is less than a
predefined threshold, the input image is said to
have successfully matched with the template.
25. Euclidian distance
o Find Euclidian distance of first minutia by itself and all
of the other minutia's.
o Find the Euclidean distance of the database image as
above.
25
•Minutia Encoding
26. Given Parameter
o X and Y coordinates of minutia
o Orientation of the minutia
o Type of minutia ridge/bifurcation.
Parameter needed
o X and Y coordinates of minutia
o Orientation of the minutia
26
Minutia Encoding
27. X-axis Y-axis Theta type
150 260 3.86 1
112 235 2.56 1
124 256 2.50 0
160 459 1.45 0
For database image
oX and Y coordinates of minutia
oOrientation of the minutia
oType of minutia ridge/bifurcation
For database image
oX and Y coordinates of minutia
oOrientation of the minutia
oType of minutia ridge/bifurcation
27
Minutia Encoding
X-axis Y-axis Theta type
260 260 5.86 1
431 245 7.56 1
114 156 1.50 0
120 359 1.45 0
28. Algorithm
28
Database image Input image
Encoding of database
image
Encoding of input
image
Not matched
Matching
If (e1-e2)<10
&(θ1-θ2)<2
i=i+1
If(i>20)
Match
yes
no
yes no
e1=Euclidean dist of 1st image
e2=Euclidean dist of second image
i=counter
29. Fingerprint Encoding and
matching
Distance between neighboring minutiae
• Delaunay triangulation
• This method can be accessed in MATLAB via the
Delaunay function.
• The smallest value from the resulting list of distance
values is then chosen, which gives us the distance from
the minutiae to its nearest neighboring point.
29