Biometric Technologies for Computer Security

Biometric Technologies for Computer Security

Faculty of Engineering
Ph.D. PROGRAM In Electronic and Computer Science Engineering

 

Lecturer: Prof. Gian Luca Marcialis - marcialis[at]diee[dot]unica[dot]it

Last update on 16/01/2017

 

Goal of the course.
This series of lectures is aimed to introduce the fundamentals of biometric technologies for personal recognition.

A biometric system for personal verification is made up of the following modules: sensor, feature extractor, matcher. These modules will be described with respect to two biometrics: fingerprint and facial traits. Multi-modal biometrics, that is, systems which combine information from multiple biometrics, will be also presented. Finally, some open research issues will be introduced. Scientific and technological issues, and a focus on the pros and cons of each biometric system, will be discussed. The course can be considered as a follow up of the “Pattern Recognition” course, since biometrics are a particular application of the concepts explained in that course. Students will visit the “Fingerprint Liveness Detection” Laboratory where they could use some proof-of-concept systems developed by the PRA Lab.
 
 
Requirements.
Fundamentals of statistical pattern recognition.
 
 
Topics:
  • 2 hours – Statistical and pattern recognition foundamentals
  • 7 hours – Fingerprint
  • 7 hours – Faces
  • 4 hours – Multimodal biometrics
  • 2 hours – Commercial products and Ambient Intelligence

 

Programme:
  1. Introduction. Motivation and potentialities of biometric systems. Personal verification and recognition.
  2. Pattern recognition. Sensoring. Feature extraction, processing. Classification. Performance parameters. Hypothesis verification tests.
  3. Fingerprints. Definition. Sensoring. Feature extraction. Matching algorithms. Vulnerabilities. Fake fingerprint detection.
  4. Faces. Definition. Sensoring. Feature extraction. Matching algorithms.
  5. Multimodal biometrics. Definition. Fusion algorithms: feature-level and match score-level.
  6. Commercial products. Main products for fingerprint and face recognition. Novel applications and ambient intelligence.
Slides can be downloaded at this link.
 
Credits: 

•    PhD students – final test mandatory : 3

•    Undergraduate students - with final test: 2

 

Important Dates (2017):
Each lesson will take 4 hours :
  • 2, 3, 6, 15, 16, 17 feb. 2017, h15.00-19.00 room B1 DIEE (on february 3 the lesson will be held in room B0).
  • Guest speakers: Dr. Pietro Sanna (E-Gnosis, Biometrics and E-learning applications), Dr. Luca Didaci (DIEE - Biometric applications using Python), Prof. Massimo Farina (Biometrics and privacy issues).