Efficient privacy-preserving biometric identification in largescale multibiometric systems
Doctoral thesis
Permanent lenke
https://hdl.handle.net/11250/2650398Utgivelsesdato
2020Metadata
Vis full innførselSamlinger
Sammendrag
In recent years, applications of biometric systems on national and international scale have appeared. Biometric identification is one of the important operational modes of such systems. It entails ascertaining the data subject identity corresponding to a given biometric sample, solely using the information from said biometric sample, i.e. effectively conducting a nearestneighbour search. The na¨ıve search method, i.e. an exhaustive (linear) search of the biometric enrolment database, suffers from two drawbacks, namely: high computational workload and increased probability of false positive occurrences.
Consequently, research into computationally efficient methods of biometricidentification is necessary; it is the main topic covered in this thesis. Specifically, the key contributions of this thesis are:
• Formulation of a taxonomy for conceptual categorisation of methods of efficient biometric identification. A comprehensive survey of the relevant existing publications and organisation thereof in the context of the developed taxonomy.
• Development of methods which substantially decrease (by space search and/or template comparison cost reduction) the computational workload requirements of the biometric identification transactions, including:
– Methods which take advantage of the intrinsic properties of certain types of biometric characteristics and/or biometric feature representations.
– Methods which can be applied irrespective of the type of biometric characteristic and the biometric feature representation.
– Methods which utilise biometric information fusion.
• Development of methods (both general purpose and biometric characteristic specific) of biometric template protection in the aforementioned context of computationally efficient biometric identification systems.
• Development of methods relevant to other (e.g. stress testing and usability) aspects of the operational biometric identification systems.
Består av
Paper 1: Drozdowski, Pawel; Rathgeb, Christian; Busch, Christoph. Computational workload in biometric identification systems: An overview. IET Biometrics 2019 ;Volum 8.(6) s. 351-368 "This paper is a postprint of a paper submitted to and accepted for publication in IET Biometrics and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library" http://dx.doi.org/10.1049/iet-bmt.2019.0076Paper 2: Drozdowski, Pawel; Fischer, Daniel; Rathgeb, Christian; Schiel, Christopher; Busch, Christoph. Database Binning and Retrieval in Multi-Fingerprint Identification Systems. I: 2018 IEEE International Workshop on Information Forensics and Security (WIFS). IEEE 2018 ISBN 978-1-5386-6536-7. s. 1-7 https://doi.org/10.1109/WIFS.2018.8630763 © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper: 3: Drozdowski, Pawel Grzegorz; Rathgeb, Christian; Busch, Christoph. Multi-iris indexing and retrieval: Fusion strategies for Bloom filter-based search structures. I: 2017 IEEE International Joint Conference on Biometrics (IJCB). IEEE 2017 ISBN 978-1-5386-1124-1. s. 46-53 https://doi.org/10.1109/BTAS.2017.8272681 " © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 4: Drozdowski, Pawel; Garg, Surabhi; Rathgeb, Christian; Gomez-Barrero, Marta; Chang, Donghoon. Privacy-Preserving Indexing of Iris-Codes with Cancelable Bloom Filter-based Search Structures. I: 2018 26th European Signal Processing Conference (EUSIPCO). IEEE Signal Processing Society 2018 ISBN 978-90-827970-1-5. s. 2360-2364 https://doi.org/10.23919/EUSIPCO.2018.8553053 " © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 5: Drozdowski, Pawel; Struck, Florian; Rathgeb, Christian; Busch, Christoph. Benchmarking Binarisation Schemes for Deep Face Templates. I: 2018 25th IEEE International Conference on Image Processing (ICIP). IEEE 2018 ISBN 978-1-4799-7061-2. s. 191-195 https://doi.org/10.1109/ICIP.2018.8451291 " © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 6: Drozdowski, Pawel; Buchmann, Nicolas; Rathgeb, Christian; Margraf, Marian; Busch, Christoph. On the Application of Homomorphic Encryption to Face Identification. I: International Conference of the Biometrics Special Interest Group (BIOSIG 2019). IEEE 2019 ISBN 978-3-88579-690-9. " © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 7: Drozdowski, Pawel; Mokroß, Benedikt-Alexander; Rathgeb, Christian; Busch, Christoph. Multi-biometric Identification with Cascading Database Filtering. IEEE Transactions on Biometrics, Behavior, and Identity Science 2020 https://doi.org/10.1109/TBIOM.2020.2977215 " © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 8: Drozdowski, Pawel; Rathgeb, Christian; Busch, Christoph. Turning a Vulnerability into an Asset: Accelerating Facial Identification with Morphing. I: 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). IEEE 2019 ISBN 978-1-4799-8131-1. s. 2582-2586 https://doi.org/10.1109/ICASSP.2019.8683326 " © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 9: Drozdowski, Pawel Grzegorz; Rathgeb, Christian; Hofbauer, Heinz; Wagner, Johannes; Uhl, Andreas; Busch, Christoph. Towards pre-alignment of near-infrared iris images. I: 2017 IEEE International Joint Conference on Biometrics (IJCB). IEEE 2017 ISBN 978-1-5386-1124-1. s. 359-366 https://doi.org/10.1109/BTAS.2017.8272718 " © 2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 10: Drozdowski, Pawel; Struck, Florian; Rathgeb, Christian; Busch, Christoph. Detection of Glasses in Near-Infrared Ocular Images. I: 2018 International Conference on Biometrics (ICB). IEEE 2018 ISBN 978-1-5386-4285-6. s. 202-208 https://doi.org/ 10.1109/ICB2018.2018.00039 " © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
Paper 11: Drozdowski, Pawel Grzegorz; Rathgeb, Christian; Busch, Christoph. Sic-Gen: A Synthetic Iris-Code Generator. In International Conference of the Biometrics Special Interest Group (BIOSIG) (September 2017), IEEE, pp. 61–69. "This paper is a postprint of a paper submitted to and accepted for publication and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library" https://doi.org/10.23919/BIOSIG.2017.8053520
Paper 12: Drozdowski, Pawel; Wiegand, Nikolai; Rathgeb, Christian; Busch, Christoph. Score Fusion Strategies in Single-Iris Dual-Probe Recognition Systems. I: 2018 2nd International Conference on Biometric Engineering and Applications. Association for Computing Machinery (ACM) © ACM 2018, This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in International Conference on Biometric Engineering and Applications. Association for Computing Machinery, 2018 ISBN 978-1-4503-6394-5. s. 13-17, https://doi.org/10.1145/3230820.3230823
Appendix A: Drozdowski, Pawel Grzegorz; Rathgeb, Christian; Busch, Christoph. Bloom Filter-based Search Structures for Indexing and Retrieving Iris-Codes. IET Biometrics (2018),7(3):260 "This paper is a postprint of a paper submitted to and accepted for publication in IET Biometrics and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library" http://dx.doi.org/10.1049/iet-bmt.2017.0007