Finger Print

30
Fingerprint Encoding and Matching

Transcript of Finger Print

Page 1: Finger Print

Fingerprint Encoding and

Matching

Page 2: Finger Print
Page 3: Finger Print
Page 4: Finger Print

FINGERPRINT IDENTIFICATION

Using Graph Method

Using minutiae and texture Method

Using Euclidian Distance

Page 5: Finger Print
Page 6: Finger Print
Page 7: Finger Print

Fingerprint identification

using Graph matching

This technique use ridges, Not x-y coordinates and angle.

Page 8: Finger Print

Identification of fingerprint

features

Page 9: Finger Print

Ridge Orientation

Page 10: Finger Print

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.

Page 11: Finger Print

Example

Page 12: Finger Print

Level Numbering

Page 13: Finger Print

Graph Representation

Page 14: Finger Print

Example of fingerprint

minutiae and their graph

representation

Page 15: Finger Print

Repairing fingerprints

defects

Page 16: Finger Print

Special minutiae and their

graph

Page 17: Finger Print

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

Page 18: Finger Print

Information Extracted

Page 19: Finger Print

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.

Page 20: Finger Print

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.

Page 21: Finger Print

Image alignment

Page 22: Finger Print

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 valuesused 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.

Page 23: Finger Print

CONCLUSIONS

Page 24: Finger Print

24

Algorithm Level Design

•Minutia Encoding

•Matching

•Return Match Score

Minutia Matcher:

Page 25: Finger Print

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

Page 26: Finger Print

Given Parametero X and Y coordinates of minutia

o Orientation of the minutia

o Type of minutia ridge/bifurcation.

Parameter neededo X and Y coordinates of minutia

o Orientation of the minutia

26

Minutia Encoding

Page 27: Finger Print

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

Page 28: Finger Print

Algorithm

28

Database image Input image

Encoding of database

imageEncoding 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

Page 29: Finger Print

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

Page 30: Finger Print

30

Fingerprint Verification

Thanks