Biometric T echnologies Dr. Issa Traore ECE Department, University - PowerPoint PPT Presentation

Biometric T echnologies Dr. Issa Traore ECE Department, University of Victoria Information Security and Object T echnology (ISOT) Lab http://www.isot.ece.uvic.ca 1

Agenda  Introduction  Applications  Requirements  Biometric System  Biometric Examples  Biometric Errors  Selection Criteria  Conclusion 2

Introduction  Biometrics: automated methods of identifying a person or verifying the identity of a person based on physiological or behavioral characteristics. ◦ Physiological characteristics: inherent physical traits ◦ Behavioral characteristics: traits that are learned or acquired. 3

Applications  Foundation for an extensive array of highly secure identification and personal verification solutions. ◦ Access control ◦ Authentication ◦ Forensics ◦ Time-attendance ◦ Border security 4

Requirements  Any human physiological and/or behavioral characteristic can be used as a biometric characteristic as long as it satisfies the following requirements: ◦ Universality: each person should have the characteristic; ◦ Distinctiveness: any two persons should be sufficiently different in terms of the characteristic; ◦ Permanence: the characteristic should be sufficiently invariant over a period of time; ◦ Collectability: the characteristic can be measured quantitatively. 5

Requirements 6

Requirements (ctd.)  In addition, a practical biometric is required to address the following issues: ◦ Performance ◦ Acceptability ◦ Resistance to Circumvention ◦ Privacy preservation 7

Biometric System  Essentially a pattern recognition system that operates by acquiring biometric data from an individual, extracting a feature set from the data, and comparing this feature set against the template set in the database.  Involve, depending on the application, three modes of operation: enrollment , verification, and identification modes. 8

Biometric System (ctd.)  Enrolment Mode  Verification  Identification 9

Biometric Examples  Fingerprint scan Digitized fingerprint image with minutiae points extracted ◦ one of the most commercially successful biometric technologies ◦ consists of analyzing small unique marks of the finger image known as minutiae. 10

Biometric Examples (ctd.)  Face scan ◦ analyze the unique shape, pattern and positioning of facial features.  problems: ◦ people do change over time; wrinkles, beard, glasses and ◦ position of the 11 head can affect the

Biometric Examples (ctd.)  Hand Geometry ◦ takes three- dimensional image of the hand and measures the shape and length of fingers and knuckles ◦ does not achieve the highest levels 12 of accuracy but it is

Biometric Examples (ctd.)  Keystroke Dynamics Fly time between A and B ◦ behavioural biometric Key Down Key Up Key Down Key Up that aims to identify B B A A humans based on the analysis of their Dwell time Dwell time on A on B typing rhythms on a Time keyboard. ◦ measures:  dwell time: the length of time you hold down each key, 13 flight time: the time it takes

Biometric System Errors  T wo types of errors: mistaking ◦ biometric measurements from two different persons to be from the same person called false match 14 (FM) or false accept

Selection Criteria Hand Characteristic Fingerprints Geometry Retina Iris Face Signature Voice Ease of Use High High Low Medium Medium High High Lighting, Noise, Error Dryness, dirt, Hand injury, Poor age, Changing Glasses colds, incidence age age Lighting glasses, signatures weather hair Accuracy High Medium Very High Very High Medium Medium Medium Cost 2 4 8 8 3 1 2 User Medium Medium Medium Medium Medium Medium High acceptance Required High Medium High Very High Medium Medium Medium security level Long-term High Medium High High Medium Medium Medium stability 15

Conclusion  Fast growing field ◦ Multibillion market  Several new emerging technologies, e.g., mouse dynamics 16