Why the study?
Conventional heart rate measurement techniques like ECG and PPG are intrusive and require continual contact with the human body.
Can a camera-based system integrating ICA and rPPGNet accurately extract heart rate signals from facial images?
Can a camera-based system integrating ICA and rPPGNet accurately extract heart rate signals from facial images?
A novel camera-based non-contact method integrating ICA and rPPGNet can successfully extract heart rate signals from facial images, offering an alternative to intrusive ECG and PPG.
Should not yet change clinical monitoring; leaves open prospective validation in real-world patient cohorts.
Health monitoring is crucial in assessing an individual’s health condition. Assessing our health can be easily done by measuring our heart rate. Variations in heart rate are common among individuals, and an abnormally elevated or reduced resting heart rate can indicate potential health issues. Various techniques, including ECG and PPG, can measure heart rate. These treatments have a drawback in that they are intrusive and involve continual contact with the human body. To address this issue, a novel solution that utilises a camera is suggested. This approach employs a blind source separation algorithm to extract the heart rate signal from the facial image. The Viola-Jones algorithm is employed for facial detection and tracking. The Fast Independent Component Analysis (ICA) algorithm is utilised to extract the heart rate information from any noise and artefacts. The rPPGNET algorithm is utilised to normalise the signal. The data has been effectively validated using real-time video.
No takes yet. Share an insight, caveat, or question.
Sasimekala et al. (2023) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: