Master/Bachelor Thesis: fusion in multi-biometrics
Biometrics is a rapidly growing technology that aims to identify or verify people identities based on their physical or behavioral properties. Multi-modal biometrics uses more than one biometric recognition approach in a unified frame in an effort to solve problems faced by the conventional uni-modal biometrics. The Multi-modality aims to improve biometrics by increasing accuracy, intra class variations and robustness to noisy data. It also aims to solve uni-modal biometrics problems with non-universality and spoof attacks.
Develop a novel score-level fusion solution that considers the biometric data quality and the possibility of missed biometric modalities while achieving high performance
- Practical experience in programming (C++ and/or Matlab)
- Interest in machine learning
- Interest in mathematical statistics
Students of Informatics, Electrical Engineering and Mathematics are welcomed.
Naser Damer (email@example.com)
Abteilung Identifikation und Biometrie (IDB)
Fraunhofer-Institut für Graphische Datenverarbeitung IGD