Seeing red: PPG biometrics using smartphone cameras

In this paper, we propose a system that enables photoplethysmogram (PPG)-based authentication by using a smartphone camera. PPG signals are obtained by recording a video from the camera as users are resting their finger on top of the camera lens. The signals can be extracted based on subtle changes...

全面介紹

書目詳細資料
Main Authors: Lovisotto, G, Turner, H, Eberz, S, Martinovic, I
格式: Conference item
語言:English
出版: Institute of Electrical and Electronics Engineers 2020
_version_ 1826291179765891072
author Lovisotto, G
Turner, H
Eberz, S
Martinovic, I
author_facet Lovisotto, G
Turner, H
Eberz, S
Martinovic, I
author_sort Lovisotto, G
collection OXFORD
description In this paper, we propose a system that enables photoplethysmogram (PPG)-based authentication by using a smartphone camera. PPG signals are obtained by recording a video from the camera as users are resting their finger on top of the camera lens. The signals can be extracted based on subtle changes in the video that are due to changes in the light reflection properties of the skin as the blood flows through the finger. We collect a dataset of PPG measurements from a set of 15 users over the course of 6-11 sessions per user using an iPhone X for the measurements. We design an authentication pipeline that leverages the uniqueness of each individual’s cardiovascular system, identifying a set of distinctive features from each heartbeat. We conduct a set of experiments to evaluate the recognition performance of the PPG biometric trait, including cross-session scenarios which have been disregarded in previous work. We found that when aggregating sufficient samples for the decision we achieve an EER as low as 8%, but that the performance greatly decreases in the cross-session scenario, with an average EER of 20%.
first_indexed 2024-03-07T02:55:32Z
format Conference item
id oxford-uuid:af24f330-4bb1-40da-a3eb-0a9c20a02b0c
institution University of Oxford
language English
last_indexed 2024-03-07T02:55:32Z
publishDate 2020
publisher Institute of Electrical and Electronics Engineers
record_format dspace
spelling oxford-uuid:af24f330-4bb1-40da-a3eb-0a9c20a02b0c2022-03-27T03:47:49ZSeeing red: PPG biometrics using smartphone camerasConference itemhttp://purl.org/coar/resource_type/c_5794uuid:af24f330-4bb1-40da-a3eb-0a9c20a02b0cEnglishSymplectic ElementsInstitute of Electrical and Electronics Engineers2020Lovisotto, GTurner, HEberz, SMartinovic, IIn this paper, we propose a system that enables photoplethysmogram (PPG)-based authentication by using a smartphone camera. PPG signals are obtained by recording a video from the camera as users are resting their finger on top of the camera lens. The signals can be extracted based on subtle changes in the video that are due to changes in the light reflection properties of the skin as the blood flows through the finger. We collect a dataset of PPG measurements from a set of 15 users over the course of 6-11 sessions per user using an iPhone X for the measurements. We design an authentication pipeline that leverages the uniqueness of each individual’s cardiovascular system, identifying a set of distinctive features from each heartbeat. We conduct a set of experiments to evaluate the recognition performance of the PPG biometric trait, including cross-session scenarios which have been disregarded in previous work. We found that when aggregating sufficient samples for the decision we achieve an EER as low as 8%, but that the performance greatly decreases in the cross-session scenario, with an average EER of 20%.
spellingShingle Lovisotto, G
Turner, H
Eberz, S
Martinovic, I
Seeing red: PPG biometrics using smartphone cameras
title Seeing red: PPG biometrics using smartphone cameras
title_full Seeing red: PPG biometrics using smartphone cameras
title_fullStr Seeing red: PPG biometrics using smartphone cameras
title_full_unstemmed Seeing red: PPG biometrics using smartphone cameras
title_short Seeing red: PPG biometrics using smartphone cameras
title_sort seeing red ppg biometrics using smartphone cameras
work_keys_str_mv AT lovisottog seeingredppgbiometricsusingsmartphonecameras
AT turnerh seeingredppgbiometricsusingsmartphonecameras
AT eberzs seeingredppgbiometricsusingsmartphonecameras
AT martinovici seeingredppgbiometricsusingsmartphonecameras