NON-CONTACT HEART RATE MEASUREMENT USING HAARCASCADE ALGORITHM AND OPENCV

For sensitive populations, a non-contact method of measuring heart rate could be helpful, and the ability to calculate heart rate using a simple webcam could be useful in telemedicine. Previous research has shown that a color video of a person's face can be used to measure heart rate. The method, which uses independent component analysis on mean pixel color values within a region of interest (ROI) around the face, has been reimplemented. The idea is further developed by exploring new methods for choosing the ROI, such as facial pixel segmentation through a reimplementation of GrabCut, as well as assessing the algorithm's robustness to subject movement and bounding box noise. The algorithm's robustness to bounding box noise was improved by facial segmentation.