![Page 1: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/1.jpg)
Introduction to Biometrics
Charles TappertSeidenberg School of CSIS, Pace
University
![Page 2: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/2.jpg)
Sources
Some images and material contained here are from:
Guide to Biometrics Bolle, Connell, Pankanti, Ratha, and Senior, Springer 2004
and our conference/journal/book publications
![Page 3: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/3.jpg)
What is Biometrics?
Definition from Bolle, et al. – the science of identifying, or verifying the identity of, a person based on physiological or behavioral characteristics
Note: biometric systems employ pattern recognition technology
![Page 4: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/4.jpg)
Traditional Modes of Person Authentication
Possessions – what you have Keys, passports, smartcards, etc.
Knowledge – what you know Secret information: passwords, etc.
Biometrics – what you are/do Characteristics of the human body
and human actions that differentiate people from each other
![Page 5: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/5.jpg)
Authentication Methods:Examples and Properties
most widely used
![Page 6: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/6.jpg)
Most Common & Other Biometrics
![Page 7: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/7.jpg)
Universality every person has the biometric characteristic
Uniqueness no two persons have the same biometric characteristic
Permanence biometric characteristic invariant over time
Collectability measurable with a sensing device
Acceptability user population and public in general should have no
strong objections to measuring/collecting the biometric
Attributes Necessary to Make a Biometric
Practical
![Page 8: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/8.jpg)
System accuracy Computational speed (DNA slow) Exception handling System cost (high for DNA) Security – can system be
compromised Privacy – data confidentiality
System Performance and Design Issues
![Page 9: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/9.jpg)
Identification versus Verification
Identification1-of-n
Verificationaccept/reject
![Page 10: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/10.jpg)
Identification versus Verification
Identification1-of-n
Verificationaccept/reject
![Page 11: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/11.jpg)
Acquisition Single 2D image Video sequence 3D image via stereo imaging, etc.
Michigan State University – Anil Jain http://biometrics.cse.msu.edu/
Presentations/AnilJain_FaceRecognition_KU10.pdf
Face Biometric
![Page 12: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/12.jpg)
Acquisition Inked finger impressions, scanners, etc.
Problem – elastic distortion Features
Fingerprint Biometric
![Page 13: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/13.jpg)
Acquisition Offline (static information) – scanned images Online (static and dynamic info) – digitizers
Categories of forger sophistication Zero-effort, home-improved, over-the-
shoulder, professional
Signature Biometric
![Page 14: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/14.jpg)
Acquisition Microphone – inexpensive, ubiquitous
Features from segmented “My name is”
Speech Biometrics Speaker Verification –
Voiceprint
![Page 15: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/15.jpg)
Basic Authentication System Matching Errors
True negative
(True Reject)
False negative
(False Reject, Miss)
b
False positive
(False Accept, False Alarm)
True positive
(True Accept, Hit)
w
bw
Pre
dict
ed
Actual
FAR
FRR
w = within class (same person), b = between class (different people)
![Page 16: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/16.jpg)
0 5 10 15 20 25 300
0.05
0.1
0.15
0.2within
between
FRRFAR
taccept reject
FAR = False Accept Rate, FRR = False Reject Rate
Basic Authentication System Matching Errors
![Page 17: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/17.jpg)
Receiver Operating Characteristic (ROC) Curve
Low Security/High Convenience (liberal) can be too open
Low Convenience/High Security (conservative) can be too restrictive
FAR = False Accept Rate
Requires imposter testing FRR = False Reject Rate EER = Equal Error Rate
![Page 18: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/18.jpg)
Biometric System Evaluation Types
Technical Evaluation Simulation tests – usual for academic
studies Scenario Evaluation
Testing facility that simulates the actual installation
Operational Evaluation Actual installation testing – most realistic
![Page 19: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/19.jpg)
Typical Error Rates
![Page 20: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/20.jpg)
Biometric Zoo
Sheep Dominant group, systems perform well for them
Goats Weak distinctive traits, produce many False
Rejects Lambs
Easy to imitate, cause “passive” False Accepts Wolves
Good at imitating, cause “active” False Accepts Chameleons
Easy to imitate and good at imitating others
![Page 21: Introduction to Biometrics Charles Tappert Seidenberg School of CSIS, Pace University](https://reader035.vdocument.in/reader035/viewer/2022062217/56649e735503460f94b727ca/html5/thumbnails/21.jpg)
http://www.dodcounterdrug.com/facialrecognition
http://atvs.ii.uam.es/fvc2006.html http://www.biometrics.org/html/research.html http://www.quantumsignal.com/
forensics_biometrics/biometrics_database/
Many Databases Available for Common
Biometrics