Post on 26-Dec-2015
Biometrics
Investigating Facial and Fingerprint Scanning
Technologies
prepared byGroup 202.10.02
What do we want to achieve?
• Introduce Biometrics
• Explain our focus
• Introduce the technologies
• Demonstrate the business value
• Give you an outlook where biometrics are headed
What are Biometrics?
“Biometrics are automated methods of recognizing a person based on a physiological or behavioral characteristic. Among the features measured are face, fingerprints, hand geometry, handwriting, iris, retinal, vein, and voice. “
Source: The Biometric Consortium
The Industry
• Facial-scan and Finger-scan make up the majority of the market
• Both are physiological biometrics
Our focus
• Finger Scan– Optical– Ultra Sound– Chip based
• Facial Scan– "Eigenface" – Feature Analysis– Neural Network Mapping technology– Automatic Face Processing (AFP)
Finger Scan
• A fingerprint is unique & immutable
• Acquisition and storage of the image of the fingerprint
AFIS: Automatic Fingerprint Identification Systems
• Uses optical scanners and performs one-to-many operations
• Two major types– forensic– civil
Fingerprint: The Business Value
• Physical attributes are much harder to fake than identity cards
• Cannot guess a fingerprint pattern like guessing a password
• Cannot misplace fingerprints, irises or voice like misplacing an access card
• Cannot forget fingerprints like forgetting a password
Fingerprint: The Business Value
• Benefits transfer in NY, LA, and Spain• Voter registration in Jamaica • Forensic AFIS used by the FBI, state and
local police to identify criminals
Fingerprint: Limitations
• Cold finger• Dry/oily finger• High or low humidity• Angle of placement• Location of finger on platen (poorly placed
core)• Cuts to fingerprint• Manual activity that would mar or affect
fingerprints (construction, gardening)
Facial Scan
• There are various facial-scan technologies used to recognize people
• We will focus on feature analysis • One thing that they all have in common is
that they focus on areas of the face that are not easily alterable.
– cheekbone area – the upper outlines of the eye sockets– the sides of one’s mouth– etc.
Feature Analysis
Nodal Points
Facial Scan: The technology
Business Value
• Easy Acceptance
• Identify People at a Distance
• Large Scale Automatic Scanning
• Existing Huge Facial Image Database
Facial Scan: Applications
• Verification– criminal suspects– access control
• Identification– general surveillance (CCTV)
• Examples– 2001 Super Bowl in Tampa– Virginia Beach CCTV network– Police Dept. in many US states and cities
Limitations
• Not very accurate
• Changes in Facial Features– surgeries, aging, etc.
• High ambient requirement
• Disguise
• Privacy issues
Conclusions and Outlook
Biometrics can add significant business value...
...but user perceptions of biometric technology are an essential element in their success.
More and more legislation that addresses biometrics is being passed:
– USA Patriot Act (signed in October 2001)– Aviation and Transportation Security Act (signed in
November 2001)– Enhanced Border Security and Visa Reform Act (signed
in May 2002)
Q&A
Thank you for your attention