Module I: Seminar on Biometric Systems

The course offers an in-depth look into the field of biometric technologies that enable automates identification and verification of individuals based on their biological or behavioral characteristics.

The introductory part focuses on the basic building blocks of biometric systems, their operational modes, and introduces the characteristics of various biometric modalities, such as face, fingerprint, iris, voice, signature, or gait. The course presents existing approaches for capturing biometric characteristics, along with procedures for verifying the quality and authenticity of the captured data. Special attention is given to the construction of uni-modal and multi-modal biometric systems that process information using various data sources and fusion techniques, while also introducing procedures for evaluating biometric systems, including approaches for assessing registration and capture errors, matching and decision errors, and other important performance characteristics.

Practical aspects of the course include approaches for testing biometric systems, where students learn to plan and conduct tests with the right population, identify and analyze potential errors, and use biometric databases for automated and repeatable experiments. The course also addresses the standardization and protection of biometric data, as well as ethical and cultural issues associated with their use. In the seminar part of the course, students develop and present their projects related to uni- and multi-modal biometric systems and their application in various contexts. 

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.

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.