Course description
- Introduction to Biometric Systems: identifiable biometric characteristics (physiological, behavioural), system components and phases of system operation (enrolment, verification, identification).
- Acquisition of Physiological (face, fingerprint, iris, hand palms and geometry) and Behavioural (voice, mimic, handwriting, and gait) Characteristics: contact and noncontact measurement, frequently used sensors. Testing the quality and genuineness of acquired data.
- Design of Uni-modal and Multi-modal Biometric Systems: sources of biometric information, levels and methods of biometric information fusion. Comparison of uni- and multi-modal systems.
- Evaluation of Biometric Systems: average enrolment and recognition time, biometric system errors (matching and decision errors), enrolment error, data acquisition error.
- Testing of Biometric Systems: test plan, person group, testing enrolment, verification and identification processes. Forgery tests. Databases for automated and repeatable tests.
- Biometric Standards and Privacy Issues. Ethical and Cultural Issues associated with biometric system applications.
- Seminars: development of uni- and multi-modal biometric systems: biometric systems in security (identification and travel documents, e-commerce, e-security systems) and others (smart rooms and environments, user-adapted content search) applications.
Course is carried out on study programme
2nd Cycle Postgraduate Study Programme in Electrical Engineering
Objectives and competences
The objective of the course is to provide the student with the knowledge of basic concepts and components of biometric systems that are used for the automatic recognition of people. The student is acquainted with the design of biometric systems and examples of the implementations of such systems. The acquired knowledge enables the design and development of the automatic systems for the biometric recognition of people that are based on the use of various biometric modalities, such as automatic face recognition, automatic speaker recognition, automatic fingerprint and iris recognition, etc. The student is also acquainted with the broader legal and ethical issues raised by the use of biometric technologies that relate to the protection of personal data and privacy.
Learning and teaching methods
The lectures provide a theoretical background of all the considered models and methods together with the examples of biometric systems that are based on different biometric modalities. Lecture notes with the slides from the lectures are available to the students as the basic study material. Practical work is carried out as part of the laboratory seminars, where the students carry out the selected seminar projects. As part of the seminars, the students also receive two homework assignments that include several programming tasks as well as the evaluation of a selected biometric method. The students report on the results of their seminar projects in written project reports. They also publicly present their work to the lecturer and to the other students who enrolled in the course.
Intended learning outcomes
After successful completion of the course, students should be able to:
- describe the basic concepts and components of biometric systems for the automatic recognition of people,
- explain the advantages and disadvantages of the use of biometric systems for the automatic recognition of people,
- explain the key ethical and social aspects associated with the use of biometric systems,
- use development tools and biometric databases for the development of biometric systems,
- develop biometric systems based on the selected biometric method for the automatic recognition of people, and
- to evaluate the accuracy and reliability of the given biometric systems.
Reference nosilca
- DOBRIŠEK, Simon, ŠTRUC, Vitomir, KRIŽAJ, Janez, MIHELIČ, France. Face recognition in the wild with the probabilistic Gabor-Fisher classifier. V: 11th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2015), Ljubljana, Slovenia, May 4-8, 2015. FG 2015. Danvers: IEEE, cop. 2015, b-Wild, str. 1-6.
- DOBRIŠEK, Simon. Pametni nadzorni sistemi : je to grožnja umetne inteligence. V: 1. dnevi prava zasebnosti in svobode izražanja, [Kranjska Gora, 9. in 10. april 2015]. Zbornik 2015. 1. natis. Ljubljana: IUS Software, GV založba, 2015, str. 134-138.
- DOBRIŠEK, Simon, GAJŠEK, Rok, MIHELIČ, France, PAVEŠIĆ, Nikola, ŠTRUC, Vitomir. Towards efficient multi-modal emotion recognition. International journal of advanced robotic systems, ISSN 1729-8814, 2013, vol. 10, no. 53, str. 1-10.
- GAJŠEK, Rok, MIHELIČ, France, DOBRIŠEK, Simon. Speaker state recognition using an HMM-based feature extraction method. Computer speech & language, ISSN 0885-2308, Jan. 2013, vol. 27, no. 1, str. 135-150.
- KRIŽAJ, Janez, ŠTRUC, Vitomir, DOBRIŠEK, Simon. Towards robust 3D face verification using Gaussian mixture models. International journal of advanced robotic systems, ISSN 1729-8814, 2012, vol. 9, no. 162, str. 1-11.
Study materials
- N. Pavešić: Razpoznavanje vzorcev (3. izdaja), Založba FE in FRI, 2012.
- K. Jain, A. A. Ross, K. Nandakumar, Introduction to Biometrics, Springer, 2011.
- R. M. Bolle et al.: Guide to Biometrics, Springer, 2004.