Biometric Identification

Page 1
Lets Define !

“A biometric is a physiological or behavioral

characteristic of a human being that can
distinguish one person from another and that
theoretically can be used for identification or
verification of identity”.

Page 2
Biometrics as Authentication

Authentication depends on
• What you have
• What you know
• What you ARE !

Page 3
Why Biometrics?

• Increased security
• Increased convenience
• Identity thefts
• Something you know can be stolen
• Predicted or hacked
• Less reliability on manual verification

Page 4
Biometrics

•Each biometric system has a characteristic ROC plot

– (receiver operator curve)
(false non-match)

secure
false rejects

trade-off

convenient

false accepts
(false match)
Page 5
Biometrics: forms

• Iris
– Analyze pattern of iris : excellent uniqueness, fast matching
• Retina scan
– Excellent uniqueness but not popular for non-criminals
• Fingerprint
– Reasonable uniqueness
• Hand geometry
– Low guarantee of uniqueness
• Signature, Voice
– Behavior dependent
– Tend to have low recognition rates
• Facial geometry

Page 6
Fingerprints

Patterns :

Enclosure

Ridge ending

Island

Bifurcation

Page 7
Fingerprint recognition
Calculates ridge endings
• Comparisons
• Authentication
•

Disadvantages
Dirt and wounds
• Placement of finger
•

Page 8
Hand Geometry

• Geometry of users hands

• More reliable than fingerprinting
• Balance in performance and usability

Disadvantage
• Very large scanners

Page 9
Retinal Scanning
• Scans retina into database
• User looks straight into retinal reader
• Scan using low intensity light
• Very efficient

Disadvantages
• User has to look “directly”
• Acceptability concerns
– Light exposure
– Hygiene

Page 10
 Face recognition
User faces camera
Neutral expression required
Apt lighting and position

•
•
•

Disadvantages
Identification across expression
Easily spoofed
Tougher usability

•
•
•

Page 11
Issues with Face Recognition
• Plenty of expressions!!!

Page 12
Voice Recognition: Behavioral characteristic
• Speech input
– Frequency
– Duration
• Neutral tone

Disadvantages
• Background noise
• Illness , emotional behavior
• Time consuming process

Page 13
Biometric: authentication process
1. Sensing
– User’s characteristic must be presented to a sensor
– Output is a function of:
• Biometric measure
• The way it is presented
• Technical characteristics of sensor

2. Signal Processing
– Feature extraction
– Extract the desired biometric pattern
• remove noise and signal losses
• discard qualities that are not distinctive/repeatable
• Determine if feature is of “good quality”

Page 14
Biometric: authentication process

3. Pattern matching
– Sample compared to original signal in database
– Closely matched patterns have “small distances”
between them
– Distances will hardly ever be 0 (perfect match)

4. Decisions
– Decide if the match is close enough
– Trade-off:
increased security leads to decreased convenience

Page 15
Usability issues in Biometrics

• User acceptability
• Knowledge of technology
• Familiarity with biometric characteristic
• Experience with device
• Time consuming tasks

Page 16
Biometric solutions

• Educate
• Train
• Explain Interfaces
• Use Trainers

Page 17
Current applications

• Banks
• Immigration facilities
• Offices
• High security areas

Page 18
The end.

Page 19