None – however the course content will be complementary to the course IMT 4722
Expected learning outcomes
- The candidate possesses advanced knowledge in Biometrics.
- The candidate possesses thorough knowledge about theory and scientific methods relevant for design, development and operation of biometric access control systems.
- The candidate is capable of applying his/her knowledge in new fields of IT-security systems.
- The candidate is capable of analyzing existing theories, methods and interpretations in the field of biometrics and working independently on solving theoretical and practical problems.
- The candidate can use relevant scientific methods in independent research and development in biometrics.
- The candidate is capable of performing critical analysis of various literature sources and applying them in structuring and formulating scientific reasoning in biometrics.
- The candidate is capable of carrying out an independent limited research or development project in biometrics under supervision, following the applicable ethical rules.
- The candidate is capable of analyzing relevant professional and research ethical problems in biometrics.
- The candidate is capable of applying his/her biometric knowledge and skills in new fields, in order to accomplish advanced tasks and projects.
- The candidate can work independently and is familiar with biometric terminology.
- The candidate is capable of discussing professional problems, analyses and conclusions in the field of biometrics, both with specialists and with general audience.
- The candidate is capable of contributing to innovation and innovation processes.
After the course, the students should have acquired:
1. Knowledge about common statistical tools for biometrics
2. Insight into advantages and disadvantages of biometric characteristics
3. Understanding of multimodal biometrics
4. Knowledge of ethical and privacy issues in biometrics.
5. Understanding of the threats and protection mechanisms for biometric data
In this course, several key aspects of biometrics are covered. The course begins with an overview of applied statistics and hypothesis tests as well as other common statistical tools for biometrics, and then covers selected biometric concepts, particularly fingerprint recognition, vein recognition, face recognition and iris recognition. To this end, the relevant physiological characteristics, their variability, and potential problems are discussed before analyzing different approaches for each of the attributes to be investigated. In each case, not only benign applications are covered but also potential bottlenecks such as insufficient sample quality along the entire processing chain. The use of multi-biometrics including data fusion is discussed both in the context of robustness against attacks and improving the overall accuracy of the recognition process. The course continues with a discussion of the ethical and privacy-related issues in biometrics, along with possible limitations and technical mitigation mechanisms. Special attention is given to privacy enhancing technologies that provides protection of sensitive biometric data. In this line the course concludes with comparison-on-card approaches and template protection concepts that allow revocation of biometric references.
• Fingerprint recognition
• Vein recognition
• Face recognition
• Iris recognition
• Multimodal biometrics
• Attack mechanisms
• Privacy Enhancing Technologies
Teaching Methods (additional text)
Afternoon sessions with seminar discussion and practical tasks.
Students should provide a research report (term paper) on a topic that is chosen by the student in coordination with the lecturer.
The course will be made accessible for both campus and remote students. Every student is free to choose the pedagogic arrangement form that is best fitted for her/his own requirement. The lectures in the course will be given on campus and are open for both categories of students. All the lectures will also be available on Internet through GUC’s learning management system (ClassFronter).
Form(s) of Assessment
Form(s) of Assessment (additional text)
1. If the student decides to conduct a term paper the grading will be based on two elements with the following weighting:
- Written examination in English (3 hours): 67%
- Term paper and oral presentation of term paper results: 33%.
- Both parts of the assessment have to be passed to pass the course.
2. Otherwise the final exam will be weighted 100%.
Alphabetical Scale, A(best) – F (fail)
Written exam will be graded by an external examiner.
Term paper and oral presentation will be graded by an internal examiner
Re-sit examination for the written exam in August, no re-sit examination offered for the term-paper.
Dictionaries allowed (no calculator)
 LI , S . Z. , AND JAIN, A. K. , Eds. Handbook of Face Recognition. Springer, Heidelberg, Germany, 2011.
 MALTONI , D. , MAIO, D. , JAIN, A. K. , AND PRABHAKAR , S . Handbook of Fingerprint Recognition. Springer, 2009.
 WAYMAN, J . , JAIN, A. , MALTONI , D. , AND MAI O, D. , Biometric Systems. Springer, 2005.
 JAIN, L.C. , HALICI, U. , HAYASHI, I. ; LEE, S.B., TSUTSUI, S. Intelligent Biometric Techniques in Fingerprint and Face Recognition. CRC Press, 1999.
 TUYLS, P., SKROIC, B., KEVENAAR, T. Security with Noisy Data. Springer, 2007
In case there will be less than 5 students that will apply for the course, it will be at the discretion of Studieprogramansvarlig whether the course will be offered or not an if yes, in which form.