Seeing Red: PPG Biometrics Using Smartphone Cameras
Authors:
- 1 June 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 3565-3574
Abstract
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%.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- A novel feature ranking algorithm for biometric recognition with PPG signalsComputers in Biology and Medicine, 2014
- Mutual Information between Discrete and Continuous Data SetsPLOS ONE, 2014
- Effects of Skin Surface Temperature on PhotoplethysmographJournal of Healthcare Engineering, 2014
- Multiparameter Respiratory Rate Estimation From the PhotoplethysmogramIEEE Transactions on Biomedical Engineering, 2013
- Towards Using Photo-Plethysmogram Amplitude to Measure Blood Pressure During SleepAnnals of Biomedical Engineering, 2010
- Digital pulse contour analysis: investigating age-dependent indices of arterial compliancePhysiological Measurement, 2005
- Determination of age-related increases in large artery stiffness by digital pulse contour analysisClinical Science, 2002
- The peripheral pulse wave: Information overlookedJournal of Clinical Monitoring and Computing, 1996
- Left ventricular end-systolic pressure estimated from measurements in a peripheral arteryJournal of Cardiothoracic and Vascular Anesthesia, 1991
- Dynamic programming algorithm optimization for spoken word recognitionIEEE Transactions on Acoustics, Speech, and Signal Processing, 1978