Abstract
The photoplethysmogram (PPG) is a biomedical signal that can be used to estimate volumetric blood flow changes in the peripheral circulation. During the past few years, several works have been published in order to assess the potential for PPGs to be used in biometric authentication systems, but results are inconclusive. In this paper we perform an analysis of the feasibility of using the PPG as a realistic biometric alternative in the long term. Several feature extractors (based on the time domain and the Karhunen–Loève transform) and matching metrics (Manhattan and Euclidean distances) have been tested using four different PPG databases (PRRB, MIMIC-II, Berry, and Nonin). We show that the false match rate (FMR) and false non-match rate (FNMR) values remain constant in different time instances for a selected threshold, which is essential for using the PPG for biometric authentication purposes. On the other hand, obtained equal error rate (EER) values for signals recorded during the same session range from 1.0% for high-quality signals recorded in controlled conditions to 8% for those recorded in conditions closer to real-world scenarios. Moreover, in certain scenarios, EER values rise up to 23.2% for signals recorded over different days, signaling that performance degradation could take place with time.
Highlights
Authentication is the process of ascertaining that somebody truly is who he/she claims to be
No single approach is better than the others per se; the selection of a particular method depends on a deep study on the application scenario, with it being possible that the best option, for some, may be a combination of approaches
In order to go from the broad authentication methodology performance to the specific detailed findings in the long term smoothly, results are provided following a three-step approach
Summary
Authentication is the process of ascertaining that somebody truly is who he/she claims to be. In this context, authorization refers to rules that determine who is allowed to do what. It is widely accepted that there are three approaches [1] to authenticating a user: with something the user knows (e.g., passwords, PINs, etc.), with something the user has (e.g., smart cards, digital certificates, etc.) and with something the user is (biometrics). Biometric authentication can be run into two different operational modes: authentication (verification) and identification [1,8]. In the authentication mode the user claims an identity and shows his/her credentials.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
