Introduction to Fingerprint Biometrics

1
Introduction to Fingerprint Biometrics

• By Tamar Bar

2
Why use biometrics?

•   Biometric templates are unique to an
  individual.
•   Unlike password, pin number, or smart card,
  they cannot be forgotten, misplaced lost or
  stolen.
•   The person trying to access is recognized by
  his ID- represented by his unique biometric
  signature.

3
Why use Fingerprint as a biometric?

• Fingerprint scanning has a high accuracy rate.
• Fingerprint authentication is a good choice for
  in-house systems.
• scanners are small, ease of integration - can be
  easily adapted to keyboards.
• Relatively low costs make it an affordable,
  simple choice for workplace access security.
• The most common and oldest biometric used.
• Fingerprints are credited as reliable in a court
  of law.

4
Fingerprint basic terms

• Ridges
• Furrows
• Minutiae Points
• Whorl
• Arch
• Loop

5
Samples of Minutiae points
4 3 2 1
8 7 6 5
12 11 10 9
16 15 14 13
6
Identification Vs. Verification

• one-to-one comparison - Identification and
  recognition are, essentially synonymous terms. In
  both processes, a sample is presented to the
  biometric system during enrollment. The system
  then attempts to find out who the sample belongs
  to, by comparing the sample with a database of
  samples in the hope of finding a match.
• one-to-many comparison - Verification process is
  when the biometric system attempts to verify an
  individual's identity.
• Identification and recognition involve
  matching a sample against a database of many,
  whereas verification involves matching a sample
  against a database of one.

7
Fingerprint Processing Stages

• Scanning (acquisition, capture)- Optical
  Method- Semiconductor generated electric field
• Processing -Specific image enhancing algorithms
  improving the image.-Using Image processing
  operators to recognize patterns in the image.-
  all the patterns recognized by the operators
  and constructing a new entity representing the
  sample this entity can be a collection of the
  objects from the image.
• Matching comparing of the 2 samplestwo well
  known matching techniques are Minutiae Point
  comparison and Correlation (of the grayscale
  component values).- Minutiae Point - has
  problem with global pattern of ridges and
  furrows.- Correlation - requires precise
  location and affected by image translation and
  rotation.
• Decision - match/ non-match result

8
Search Methods for Fingerprint Identification
Using Classification

• Tree Structure
• Hashing

9
Accuracy and Integrity

• false negatives are more likely to occur than
  false positives good for highly secure system
  less for a costumer serving type of system.
• presenting a fake sample has solutions like
  measuring temperature, blood-oxygen level, pulse,
  blood flow, humidity heart rate temp.
• Technical problems - dirty scanner.

10
Discussion Point

• What types of systems really need biometrics as a
  security systems
• Dangers in using personal bodily assets-
  harming people to get hold of that assets.-
  forging profs that are court admissable- privacy
  issues.