Biometrics

1
Biometrics Current technology

• Face recognition
• Hand Geometry
• Finger Printing
• Iris recognition

2
Biometric Technologies

• Utilizing biometrics for personal authentication
  is becoming convenient and considerably more
  accurate than current methods (passwords or
  PINs). Complex passwords are easy to forget while
  simple passwords are easily guessed by
  unauthorized persons
• Some BI Technologies include
• facial recognition
• digital fingerprinting
• hand geometry
• iris and retina scanning
• voice recognition

3
Characteristics required

• Universality
• Uniqueness
• Permanence
• Collectibility
• Performance
• Acceptability
• Circumvention

4
Biometric Authentication

• Identification ensure a person is not in the
  system under several identities
• Verification authenticates a persons named
  identity

No Match
Capture
Process
Store
Enrol
Compare
Capture
Process
Verify
Match
5
Face Recognition

• Automatic face recognition has great potential in
  a large array of application areas, including
• banking and security system access control,
  video surveillance, mug-shot matching for law
  enforcement, duplicate ID card detection, and
  multimedia information retrieval, etc
• Another version of FR is sketch-based face
  recognition which enables us to search through a
  photo database using a sketch drawing

6
How it works

• NODAL POINTS
• Distance between eyes
• Dimensions of nose
• Depth of eye sockets
• Cheek Bones
• Jaw Line
• Chin
• Face hallucination or face super-resolution is a
  technique useful where the detail of facial
  features are lost in low-resolution images

7
Fingerprint scanning

• There are a greater variety of fingerprint
  devices available than any other biometric.
• This type of ID cannot easily be forgotten,
  misplaced, lost, or stolen and is the
  front-runner for mass-market biometric-ID systems
• Has a high degree of accuracy as it looks at the
  subsurface (below the top layers of skin) of the
  finger.

8
Fingerprints

• Needs to be able to detect temperature,
  blood-oxygen level, pulse, blood flow, humidity,
  etc.
• Two types
• Optical method (starts with a visual image of a
  finger)
• Semiconductor-generated electric field to image a
  finger
• Fairly cheap compared to other methods

9
Hand Geometry

• It has been in existence for nearly 20 years used
  to measure specific characteristics of a person's
  hand
• Hand geometry devices employed today take over 90
  measurements of the length, width, thickness, and
  surface area of a persons hand and fingers

10
Hand Geometry

• A digital camera is used to record the hand's
  three-dimensional shape.  Unlike fingerprint
  imaging systems, hand geometry readers do not
  take into account natural and environmental
  surface details, such as lines, scars, dirt, and
  fingernails
• Hand can change because of injury, arthritis
• Can operate in extreme environments hot, dirty,
  dusty

11
Eye Recognition

• There are two distinct parts of the human eye
  that can be used to positively identify the
  identity an individual
• The iris
• The retina

12
Iris Recognition

• Employs the unique characteristics and features
  of the human iris (which without injury to the
  eyeball remains unchanged throughout an
  individuals lifetime).
• The iris-scan process begins with a photograph. A
  specialized camera uses an infrared imager to
  illuminate the eye and capture a very
  high-resolution photograph which can then be used
  for matching and verification of a persons
  identity
• Iris patterns are extremely complex, carry an
  astonishing amount of information and have over
  200 unique spots, is also very resistant to false
  matching and fraud.

13
Benefits of Using Iris Technology

• The iris is a thin membrane on the interior of
  the eyeball. Iris patterns are extremely complex.
  
• Patterns are individual (even in fraternal or
  identical twins).
• Patterns are formed by six months after birth,
  stable after a year. They remain the same for
  life.
• Imitation is almost impossible.
• Patterns are easy to capture and encode

14
Uses of Iris recognition

• Airports have begun to use iris-scanning for such
  diverse functions as
• employee identification/verification for movement
  through secure areas
• allowing registered frequent airline passengers a
  system that speeds up their path through passport
  control

15
Retina Recognition

• The alternative method of authenticating the
  identity of an individual using the eye is via
  retina scanning.
• This technology employs a more intrusive
  technique by way of requiring the individual to
  place their eye close up to a binocular or
  monocular type device.
• However, retina scanning is highly accurate and
  has been in use for military applications since
  the early seventies.

16
Retina Recognition

• The principle behind retinal scanning is that
  blood vessels at the retina provide a unique
  pattern which may be used as a tamper-proof
  personal identifier.
• To read this characteristic, a small beam of
  coherent light is beamed through the cornea to
  illuminate the blood vessels which are then
  photographed and analysed.

17
Other Biometrics

• Handwriting
• Voice
• Vein scan
• Facial thermography
• DNA
• Blood pulse
• Gait
• Ear shape
• ..

18
What Security issues are there?

• Reliability
• False positives
• False negatives
• Enrolment/authentication speed
• Privacy
• Invasiveness
• Cost

19
Some useful URLs

• http//computer.howstuffworks.com/fingerprint-scan
  ner.htm
• http//computer.howstuffworks.com/facial-recogniti
  on.htm
• http//findbiometrics.com/tech-showcases/viewshowc
  ase.php?showcase_id9sc_titleFingerprint
• http//www.biometricsinfo.org/
• http//www.biometrics.org/html/examples/examples.h
  tml
• http//www.hrsltd.com/identification_technology/bi
  ometrics.htm
• http//www.epic.org/privacy/facerecognition/
• http//faculty.washington.edu/chudler/java/faces.h
  tml