Seeing Red: PPG Biometrics Using Smartphone Cameras
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...
| Asıl Yazarlar: | , , |
|---|---|
| Materyal Türü: | Dataset |
| Baskı/Yayın Bilgisi: |
University of Oxford
2020
|
| Konular: |
| _version_ | 1826261398228828160 |
|---|---|
| author | Lovisotto, G Eberz, S Turner, H |
| author2 | Lovisotto, G |
| author_facet | Lovisotto, G Lovisotto, G Eberz, S Turner, H |
| author_sort | Lovisotto, G |
| collection | OXFORD |
| description | 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/<USR>/<TIMESTAMP>.mp4 the <USR> folder identifies the participant, the
<TIMESTAMP> 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%. |
| first_indexed | 2024-03-06T19:20:47Z |
| format | Dataset |
| id | oxford-uuid:1a04e852-e7e1-4981-aa83-f2e729371484 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T19:20:47Z |
| publishDate | 2020 |
| publisher | University of Oxford |
| record_format | dspace |
| spelling | oxford-uuid:1a04e852-e7e1-4981-aa83-f2e7293714842022-03-26T10:52:24ZSeeing Red: PPG Biometrics Using Smartphone CamerasDatasethttp://purl.org/coar/resource_type/c_ddb1uuid:1a04e852-e7e1-4981-aa83-f2e729371484Biometric identificationORA DepositUniversity of Oxford2020Lovisotto, GEberz, STurner, HLovisotto, GLovisotto, GLovisotto, GLovisotto, GThis 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/<USR>/<TIMESTAMP>.mp4 the <USR> folder identifies the participant, the <TIMESTAMP> 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%. |
| spellingShingle | Biometric identification Lovisotto, G Eberz, S Turner, H 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 |
| topic | Biometric identification |
| work_keys_str_mv | AT lovisottog seeingredppgbiometricsusingsmartphonecameras AT eberzs seeingredppgbiometricsusingsmartphonecameras AT turnerh seeingredppgbiometricsusingsmartphonecameras |