Dataset icon

Dataset

Seeing Red: PPG Biometrics Using Smartphone Cameras

Documentation:
This folder contains the dataset used in the paper "Seeing Red: PPG Biometrics Using Smartphone Cameras", published in the 15th IEEE Computer Vision Society Workshop on Biometrics (https://www.vislab.ucr.edu/Biometrics2020/). The folder 'videos' contains the videos used for the paper. These are .mp4 videos taken with an iPhone X camera while the participant placed his index finger on top of the camera. Out of 15 participants, only 14 gave permission to share their data and are therefore present here. Each video contains one session, i.e., the participant sits and provides a 30 seconds long measurement. For a video anonymized_videos//.mp4 the folder identifies the participant, the is the relative timestamp in seconds from the time the first measurement was taken (across the whole dataset). 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%.

Actions

  • Cite

  • Print

Access Document

Files:

Authors/Creators

More by this author/creator
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Data collector, Data manager, Data curator, Contributor, Creator
More by this author/creator
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Creator
More by this author/creator
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Creator

More from this funder
Funding agency for:
Turner, H
Lovisotto, G
Grant:
EP/P00881X/1
EP/N509711/1

Publisher:
University of Oxford
Publication date:
2020

Keywords:
Subjects:
Pubs id:
1480702
UUID:
uuid:1a04e852-e7e1-4981-aa83-f2e729371484
Local pid:
pubs:1480702
Deposit date:
2020-04-15
ARK identifier:

Terms of use

Views and Downloads





If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP