Incorporating Metadata in Multibiometric Score-Level Fusion: an Optimized Architecture

Abstract

This manuscript presents a review on multibiometrics using ancillary information, in addition to the main biometric data. The proposed method involves taking non-biometric information into account in the biometric recognition process to improve system performance. This ancillary information can come from the user (the skin color), the sensor (the camera flash, etc.) or the operating environment (the ambient noise). Moreover, the paper presents an extension of the adapted sequential fusion framework through a complete description of the method used for the score-level fusion architecture presented at the IEEE BioSmart 2019 Proceedings. An optimized score-level fusion architecture is proposed. An introduction of new concepts (namely “biochemical features” and “multi origin biometrics”) is also made. The first part of the paper highlights the various biometric systems developed up to now, their architecture and characteristics. Then, the manuscript discussed about multibiometrics through its advantages, its diversity and the different levels of fusion. An attention was paid to the score-level fusion before addressing the consideration of ancillary information (or metadata) in multibiometrics. Dealing with the affective computing, the influence of emotion on the performance of biometric systems is explored. Finally, a typology of biometric adaptation is discussed. As an application, the proposed methodology will implement a multibiometric system using the face, contactless fingerprint and skin color. A single sensor will be used (a camera) with two shots while the skin color will be extracted automatically from the facial image.