Heart Rate Measurement Using Remote Photoplethysmograph Based on Skin Segmentation

Abstract

The remote Photoplethysmograph (rPPG) is recently used in evaluating heart rate (HR) from registered skin color differences through a camera. It is based on extracting HR from the small periodic color difference in the skin due to heartbeats. Selection of Region of Interest (ROI) is a critical process and its necessity includes as many skin pixels as likely. In this paper, we focus on improving the quality of pulsatile signals by using skin segmentation to select the ROI. So, an automatically enhanced marker built in the watershed algorithm is offered for segmentation of human skin regions from the detected face. The suggested rPPG measurements are evaluated by using root mean square error (RMSE), and complexity time. Based on the simulation result, the proposed algorithm showed that using skin segmentation can significantly improve the performance of the rPPG process.