Damer, Naser ; Boutros, Fadi ; Terhörst, Philipp ; Braun, Andreas ; Kuijper, Arjan (2018)
P-Score: Performance Aligned Normalization and an Evaluation in Score-Level Multi-Biometric Fusion.
European Signal Processing Conference (EUSIPCO). Rome, Italy
doi: 10.23919/EUSIPCO.2018.8553553
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Normalization is an important step for different fusion, classification, and decision making applications. Previous normalization approaches considered bringing values from different sources into a common range or distribution characteristics. In this work we propose a new normalization approach that transfers values into a normalized space where their relative performance in binary decision making is aligned across their whole range. Multi-biometric verification is a typical problem where information from different sources are normalized and fused to make a binary decision and therefore a good platform to evaluate the proposed normalization.We conducted an evaluation on two publicly available databases and showed that the normalization solution we are proposing consistently outperformed state-of-the-art and best practice approaches, e.g. by reducing the false rejection rate at 0.01% false acceptance rate by 60- 75% compared to the widely used z-score normalization under the sum-rule fusion.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2018 |
| Autor(en): | Damer, Naser ; Boutros, Fadi ; Terhörst, Philipp ; Braun, Andreas ; Kuijper, Arjan |
| Art des Eintrags: | Bibliographie |
| Titel: | P-Score: Performance Aligned Normalization and an Evaluation in Score-Level Multi-Biometric Fusion |
| Sprache: | Englisch |
| Publikationsjahr: | 2018 |
| Ort: | Los Alamitos |
| Verlag: | IEEE |
| Buchtitel: | 2018 26th European Signal Processing Conference (EUSIPCO) |
| Veranstaltungstitel: | European Signal Processing Conference (EUSIPCO) |
| Veranstaltungsort: | Rome, Italy |
| DOI: | 10.23919/EUSIPCO.2018.8553553 |
| URL / URN: | https://doi.org/10.23919/EUSIPCO.2018.8553553 |
| Kurzbeschreibung (Abstract): | Normalization is an important step for different fusion, classification, and decision making applications. Previous normalization approaches considered bringing values from different sources into a common range or distribution characteristics. In this work we propose a new normalization approach that transfers values into a normalized space where their relative performance in binary decision making is aligned across their whole range. Multi-biometric verification is a typical problem where information from different sources are normalized and fused to make a binary decision and therefore a good platform to evaluate the proposed normalization.We conducted an evaluation on two publicly available databases and showed that the normalization solution we are proposing consistently outperformed state-of-the-art and best practice approaches, e.g. by reducing the false rejection rate at 0.01% false acceptance rate by 60- 75% compared to the widely used z-score normalization under the sum-rule fusion. |
| Freie Schlagworte: | Multibiometrics, Information fusion, Biometric fusion, Biometrics |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Mathematisches und angewandtes Visual Computing |
| Hinterlegungsdatum: | 01 Jul 2019 08:47 |
| Letzte Änderung: | 27 Feb 2023 11:25 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum