Subject description
The course relies mostly on computer vision, as most biometrics technologies are based on it. Students interested in cutting edge technology, much of which is still in a research stage, are the intended target for the course. The main content (will evolve due to developments in the field):
-
Biometry basics
-
Biometrical modalities
-
Structure of a typical biometric system
-
Recognition/verification/identification
-
Metrics
-
Conditions for correct comparisons of the systems (databases, frameworks)
-
Performance and usefulness of the systems
-
Computer vision as the foundation of the biometric systems
—–
-
Fingerprint
-
Acquisition
-
Quality assessment and quality improvement
-
Processing
-
Singular points, minutiae, ridges
-
Matching
—–
-
-
Iris
-
Acquisition
-
Quality improvement
-
Processing (segmentation, normalization, coding)
-
Feature points
-
Matching
—–
-
-
Face
-
Acquisition
-
Sub-modalities
-
Processing
-
Feature points (appearance/
model/texture-based approach) -
Matching
—–
-
-
Gait
-
Acquisition
-
Influence of dynamics
-
Processing (appearance/
model-based approach) -
Dynamic feature points
-
Matching
—–
-
-
Ear
-
Acquisition
-
Processing
-
Feature points
-
Matching
—–
-
-
Multi-biometric systems / multi-modality / fusions
-
Key problems of modalities/systems (research challenges)
The lectures introduce the approaches and explain their operation. At tutorial the knowledge is applied to practical problems in Matlab and open source tools.
The subject is taught in programs
Objectives and competences
Objectives of the course:
-
Student gains good overview over the biometry and with it related computer vision methods that set foundations of biometric systems.
-
Student gets acquainted with the flow of the research work.
-
Student gets good foundation for doctoral study.
Gained student competences:
- Knows the terminology and principles of identity analysis.
- Knows the scope of the biometric technologies and their (dis)advantages.
- Knows how the system works from the acquisition to decision.
- Understands the processing flow for each biometric modality.
- Knows some limitations of biometric systems.
- Is able to critically consider older and newer modalities and how they can work together.
- Is familiar with some open problems/challenges in biometry.
Teaching and learning methods
Lectures and tutorial, individual work on assignments/project, presentations of outcomes.
Expected study results
After successful completion of the course, students will be able to:
– explain the design cycle of the biometric system
– differentiate between specifics of different modalities
– choose computer vision algorithms for biometric pipeline
– implement biometric pipeline
– evaluate the quality of each step in the pipeline
– build multi-biometric system
– argument the choice of metrics, databases, protocols
– identify open research questions
– write a technical report.
Basic sources and literature
-
Anil K. Jain, Arun A. Ross, Karthik Nandakumar, Introduction to Biometrics, Springer, 2011 (glavna, izhodiščna literatura / primary literature)
-
Ruud M. Bolle, Jonathan Connell, Sharath Pankanti, Nalini K. Ratha, Andrew W. Senior, Guide to Biometrics, 2003
Vsebine bodo podprte tudi s članki iz pomembnih konferenc in revij. /
Content will be backed also with articles from important conferences and journals.
Stay up to date
University of Ljubljana, Faculty of Electrical Engineering Tržaška cesta 25, 1000 Ljubljana