Pattern recognition fingerprints seminar Mustansiriya University Department of Education Computer Science

2. Fingerprint
• A fingerprint is a unique pattern of ridges and
valleys on the surface of a finger of an
individual. A ridge is defined as a single
curved segment, and a valley is the region
between two adjacent ridges.

3. Fingerprint Principles
According to criminal investigators, fingerprints follow
3 fundamental principles:
• A fingerprint is an individual characteristic; no two
people have been found with the exact same
fingerprint pattern.
• A fingerprint pattern will remain unchanged for the
life of an individual; however, the print itself may
change due to permanent scars and skin diseases.
• Fingerprints have general characteristic ridge
patterns that allow them to be systematically
identified.

4. Fingerprint Classes
There are 3 specific classes for all fingerprints based
upon their visual pattern: arches, loops, and whorls.
Each group is divided into smaller groups
as seen in the lists below.
Arch
Plain arch
Tented arch
Loop
Radial Loop
Ulnar loop
Whorl
Plain whorl
Central pocket whorl
Double loop whorl
Accidentical

5. Interesting Info
Fingerprint Factoid:
60% of people have loops, 35% have whorls,
and 5% have arches

6. Arches
Arches are the simplest type of fingerprints that are formed by
ridges that enter on one side of the print and exit on the other.
No deltas are present.
Plain Arch
Ridges enter on one side and
exit on the other side.
Tented Arches
Similar to the plain arch,
but has a spike in the center.
Spike or “tent”

7. Loops
Loops must have one delta and one or more ridges that enter and
leave on the same side. These patterns are named for their positions
related to the radius and ulna bones, i.e. the bone the loop opening is
facing towards.
Delta
L – Radial Loop
R - Ulnar Loop
L – Ulnar Loop
R - Radial Loop

8. Whorls
Whorls have at least one ridge that makes (or tends to make) a
complete circuit. They also have at least two deltas. If a print has
more than two deltas, it is most likely an accidental.
Draw a line between the two deltas in the plain and central pocket
whorls. If some of the curved ridges touch the line, it is a plain
whorl. If none of the center core touches the line, it is a central
pocket whorl.
Plain
Whorl
Central
Pocket
Whorl

9. Whorls
Accidental Whorl
Accidental whorls contain two
or more patterns (not
including the plain arch), or
does not clearly fall under any
of the other categories.
Double Loop Whorl
Double loop whorls are
made up of any two loops
combined into one print.
Delta
Delta

10. Fingerprint Features
1. Global Ridge Pattern
 A core is the uppermost of the innermost
curving ridge
 a delta point is the junction point where three
ridge flows meet

11. 2. Local Ridge Pattern
• Local ridge details are the discontinuities of
local ridge structure referred to as minutiae
• A good quality image has around 40 to 100
minutiae

12. Bifurcation Bridge Dot Double bifurcation
Opposed
bifurcation
Island (short
ridge)
Hook (spur) Lake (enclosure)
Ridge crossing Ridge ending Trifurcation
Opposed
bifurcation/ridge
ending)

13. Fingerprint Recognition
• Fingerprint recognition (is referred as AFRS
(Automatic Fingerprint Recognition System)
• Fingerprint recognition is the process of
comparing questioned and known
fingerprint against another fingerprint to
determine if the impressions are from the
same finger

14. • It includes two sub-domains:
fingerprint verification (one to one matching) the
purpose of fingerprint verification is to verify the
identity of a person
fingerprint identification(one to many matching)
the goal of fingerprint identification is to
establish the identity of a person.

15. • Fingerprint recognition systems consist of the
following parts:
Image acquisition
Pre-processing
Feature extraction
Matching

16. Fingerprint Image Acquisition
• There are numbers of different techniques for
capturing a fingerprint image including optical,
capacitive, radio frequency, ultrasound, and
thermal methods.
• One common shortcoming of many conventional
fingerprint-sensing technologies is the frequent
occurrence of poor-quality images under a
variety of common operational circumstances.

17. • Bad-quality images mostly result in spurious
and missing features that then degrade the
performance of the systems depending on
these features. Hence, there is a need for a
good enhancement method applied on
fingerprint image to overcome these
problems

18. Pre-processing
1. Fingerprint image Binarization
• In Binarization, the grey scale image is
converted into binary image. Binary images are
easy to process. The basic principle of
converting an image into binary is to decide a
threshold value, and then the pixels whose value
are more than the threshold are converted to
white pixels, and the pixels whose value are
below or equal to the threshold value are
converted to black pixels.

19. 2. Finger print Image enhancement
• The captured fingerprint image may contain
various noises, thus cause poor matching
result
• To remove noise, some enhancement
techniques are applied.
3. Fingerprint image segmentation
• the primary purpose of segmentation is to
avoid extraction of feature in the background
that is in reality considered as a noisy area
• Segmentation indicates the separation of
fingerprint area or foreground from the image

20. 4. Fingerprint image thinning
• Thinning is to remove ridges edge pixels
from the binary fingerprint image, so that
only a single pixel describes the ridges, in
order to facilitate minutiae extraction.

21. Feature extraction &Matching
• these features are stored as template,
either to register new user, or to use it to
be compared with other fingerprint
template, stored in system database

22. important things
1- cost :- cost rang from $100 to $2000
2- Ease of use :- medium.
3- Authentication:-
Fingerprint recognition or fingerprint authentication refers
to the automated method of verifying a match between two
human fingerprint.
4- Identification :-
matching the characteristics of a fingerprint on file
to the one presented to system .
5- physiological and/or behavior characteristics :-
the fingerprint is physiological characteristics.

23. 6- Ability to applied: This system can be applied, but needs to H/W
and S/W whenever the devices have high specifications like (optical fingerprint
scanner) with strong ways in determining the feature all that raise security and
reliability ,if the cost of the system is high has increased security If the low-cost
(the scanner for fingerprint) we can use more than one way such as palm and
voice, So we get a high security at low cost.
7- Community acceptance :- low .
8- Automatic (real time) :- the fingerprint system divided into
off-line in the (pre-processing ,feature extraction) part.
on-line in the ( image acquisition , matching) part.
It takes a few minutes 3-5 sec.
9-Life cycle:-
fingerprint pattern will remain unchanged for the life of
an individual.
10- maintenance requirement :-
no need to maintenance.

24. THANK YOU…
The END!