Bio

4TU.CybSec Syllabus Introduction to Biometrics (Bio)
4TU Delft
4TU Eindhoven
4TU Twente
4TU Wageningen

Credits: 5EC

Motivation: An important aspect of cyber security is physical access control to services, such as online banking, and devices, such as SCADA terminals. Authentication of the rightful user is an essential step of access control. Biometric recognition of individuals in physical or logical access control systems provides an efficient and convenient alternative to knowledge-based or token-based security systems that can guarantee that the rightful user is physically present during authentication.

Synopsis: The course studies the recognition of individuals based on physiological characteristics or behavioural traits in order to provide an efficient and convenient alternative to knowledge-based or token-based security systems. Other application domains that are discussed are the use of biometrics for search and surveillance and forensic biometrics. The lecture covers the most important modalities in today’s biometric systems: fingerprint recognition, face recognition, and iris recognition. The course includes background theory, biometric systems, performance analysis, and multibiometrics.

Aim: The goal of the course is to develop:

  • An understanding of the principles used in biometric systems.
  • Knowledge of the most important biometric approaches.
  • The capability to assess the performance and the security properties of a biometric system.
  • An understanding of the relationships between biometric systems and environmental conditions and their impact on performance.
  • The capability to select a suitable biometric system for a given application context.
  • Sufficient background knowledge to read and understand scientific publications on this topic.

Learning outcomes: These are reflected in the goals.

Lecturers: Prof Dr Raymond Veldhuis, Dr Luuk Spreeuwers, and Prof Dr Didier Meuwly. All (UT/EWI).

Examination: Two compulsory Matlab assignments to be completed in teams of 2 students. Final assignment: A team of two to four students writes a research proposal, performs the research, and writes a 6-page paper

Contents: Introduction: definition; advantages, disadvantages and expectations; examples; 
applications. Biometric systems: usage; biometric system architecture; recognition, enrolment, training. Performance: error and recognition rates, decision error trade-off characteristic, receiver operating characteristic, cumulative match graph, verification and identification experiments. Face Recognition: principles, problems, 3D face recognition, applications. Fingerprint recognition: principles, minutiae based, non-minutiae based, applications. Iris Recognition: principles, preprocessing, iris code, applications. Forensic biometrics: hypotheses, Bayesian approach, likelihood ratio. Multibiometrics: multi-modal fusion, multi-algorithm fusion, multi-instance fusion, score-level fusion, decision-level fusion, feature level fusion. Classification theory: verification, identification, Neyman-Pearson approach, likelihood ratio, Bayesian approach, MAP approach, types of classifiers, feature extraction, PCA, LDA

Core text: Various papers from the literature

Credits: 5EC

Motivation: An important aspect of cyber security is physical access control to services, such as online banking, and devices, such as SCADA terminals. Authentication of the rightful user is an essential step of access control. Biometric recognition of individuals in physical or logical access control systems provides an efficient and convenient alternative to knowledge-based or token-based security systems that can guarantee that the rightful user is physically present during authentication.

Synopsis: The course studies the recognition of individuals based on physiological characteristics or behavioural traits in order to provide an efficient and convenient alternative to knowledge-based or token-based security systems. Other application domains that are discussed are the use of biometrics for search and surveillance and forensic biometrics. The lecture covers the most important modalities in today’s biometric systems: fingerprint recognition, face recognition, and iris recognition. The course includes background theory, biometric systems, performance analysis, and multibiometrics.

Aim: The goal of the course is to develop:

  • An understanding of the principles used in biometric systems.
  • Knowledge of the most important biometric approaches.
  • The capability to assess the performance and the security properties of a biometric system.
  • An understanding of the relationships between biometric systems and environmental conditions and their impact on performance.
  • The capability to select a suitable biometric system for a given application context.
  • Sufficient background knowledge to read and understand scientific publications on this topic.

Learning outcomes: These are reflected in the goals.

Lecturers: Prof Dr Raymond Veldhuis, Dr Luuk Spreeuwers, and Prof Dr Didier Meuwly. All (UT/EWI).

Examination: Two compulsory Matlab assignments to be completed in teams of 2 students. Final assignment: A team of two to four students writes a research proposal, performs the research, and writes a 6-page paper

Contents: Introduction: definition; advantages, disadvantages and expectations; examples; 
applications. Biometric systems: usage; biometric system architecture; recognition, enrolment, training. Performance: error and recognition rates, decision error trade-off characteristic, receiver operating characteristic, cumulative match graph, verification and identification experiments. Face Recognition: principles, problems, 3D face recognition, applications. Fingerprint recognition: principles, minutiae based, non-minutiae based, applications. Iris Recognition: principles, preprocessing, iris code, applications. Forensic biometrics: hypotheses, Bayesian approach, likelihood ratio. Multibiometrics: multi-modal fusion, multi-algorithm fusion, multi-instance fusion, score-level fusion, decision-level fusion, feature level fusion. Classification theory: verification, identification, Neyman-Pearson approach, likelihood ratio, Bayesian approach, MAP approach, types of classifiers, feature extraction, PCA, LDA

Core text: Various papers from the literature

Bio

Credits: 5EC

Motivation: An important aspect of cyber security is physical access control to services, such as online banking, and devices, such as SCADA terminals. Authentication of the rightful user is an essential step of access control. Biometric recognition of individuals in physical or logical access control systems provides an efficient and convenient alternative to knowledge-based or token-based security systems that can guarantee that the rightful user is physically present during authentication.

Synopsis: The course studies the recognition of individuals based on physiological characteristics or behavioural traits in order to provide an efficient and convenient alternative to knowledge-based or token-based security systems. Other application domains that are discussed are the use of biometrics for search and surveillance and forensic biometrics. The lecture covers the most important modalities in today’s biometric systems: fingerprint recognition, face recognition, and iris recognition. The course includes background theory, biometric systems, performance analysis, and multibiometrics.

Aim: The goal of the course is to develop:

  • An understanding of the principles used in biometric systems.
  • Knowledge of the most important biometric approaches.
  • The capability to assess the performance and the security properties of a biometric system.
  • An understanding of the relationships between biometric systems and environmental conditions and their impact on performance.
  • The capability to select a suitable biometric system for a given application context.
  • Sufficient background knowledge to read and understand scientific publications on this topic.

Learning outcomes: These are reflected in the goals.

Lecturers: Prof Dr Raymond Veldhuis, Dr Luuk Spreeuwers, and Prof Dr Didier Meuwly. All (UT/EWI).

Examination: Two compulsory Matlab assignments to be completed in teams of 2 students. Final assignment: A team of two to four students writes a research proposal, performs the research, and writes a 6-page paper

Contents: Introduction: definition; advantages, disadvantages and expectations; examples; 
applications. Biometric systems: usage; biometric system architecture; recognition, enrolment, training. Performance: error and recognition rates, decision error trade-off characteristic, receiver operating characteristic, cumulative match graph, verification and identification experiments. Face Recognition: principles, problems, 3D face recognition, applications. Fingerprint recognition: principles, minutiae based, non-minutiae based, applications. Iris Recognition: principles, preprocessing, iris code, applications. Forensic biometrics: hypotheses, Bayesian approach, likelihood ratio. Multibiometrics: multi-modal fusion, multi-algorithm fusion, multi-instance fusion, score-level fusion, decision-level fusion, feature level fusion. Classification theory: verification, identification, Neyman-Pearson approach, likelihood ratio, Bayesian approach, MAP approach, types of classifiers, feature extraction, PCA, LDA

Core text: Various papers from the literature

Credits: 5EC

Motivation: An important aspect of cyber security is physical access control to services, such as online banking, and devices, such as SCADA terminals. Authentication of the rightful user is an essential step of access control. Biometric recognition of individuals in physical or logical access control systems provides an efficient and convenient alternative to knowledge-based or token-based security systems that can guarantee that the rightful user is physically present during authentication.

Synopsis: The course studies the recognition of individuals based on physiological characteristics or behavioural traits in order to provide an efficient and convenient alternative to knowledge-based or token-based security systems. Other application domains that are discussed are the use of biometrics for search and surveillance and forensic biometrics. The lecture covers the most important modalities in today’s biometric systems: fingerprint recognition, face recognition, and iris recognition. The course includes background theory, biometric systems, performance analysis, and multibiometrics.

Aim: The goal of the course is to develop:

  • An understanding of the principles used in biometric systems.
  • Knowledge of the most important biometric approaches.
  • The capability to assess the performance and the security properties of a biometric system.
  • An understanding of the relationships between biometric systems and environmental conditions and their impact on performance.
  • The capability to select a suitable biometric system for a given application context.
  • Sufficient background knowledge to read and understand scientific publications on this topic.

Learning outcomes: These are reflected in the goals.

Lecturers: Prof Dr Raymond Veldhuis, Dr Luuk Spreeuwers, and Prof Dr Didier Meuwly. All (UT/EWI).

Examination: Two compulsory Matlab assignments to be completed in teams of 2 students. Final assignment: A team of two to four students writes a research proposal, performs the research, and writes a 6-page paper

Contents: Introduction: definition; advantages, disadvantages and expectations; examples; 
applications. Biometric systems: usage; biometric system architecture; recognition, enrolment, training. Performance: error and recognition rates, decision error trade-off characteristic, receiver operating characteristic, cumulative match graph, verification and identification experiments. Face Recognition: principles, problems, 3D face recognition, applications. Fingerprint recognition: principles, minutiae based, non-minutiae based, applications. Iris Recognition: principles, preprocessing, iris code, applications. Forensic biometrics: hypotheses, Bayesian approach, likelihood ratio. Multibiometrics: multi-modal fusion, multi-algorithm fusion, multi-instance fusion, score-level fusion, decision-level fusion, feature level fusion. Classification theory: verification, identification, Neyman-Pearson approach, likelihood ratio, Bayesian approach, MAP approach, types of classifiers, feature extraction, PCA, LDA

Core text: Various papers from the literature