Title
Non-Contact Based Heart Rate Monitoring from RGB Camera Face Videos
Abstract
Heart Rate is a crucial physiological parameter which provides basic information about the state of the human body in cardiovascular system, as like medical diagnostics, and fitness assessments. At present day, it has been demonstrated that facial video-based photoplethysmographic signal captured using a low-cost RGB camera can be possible to retrieve remote heart rate. Traditional heart rate measurement is mostly in direct contact with the human body, and prolonged contact will cause discomfort to the subjects, so it is inconvenient for long-term heart rate measurement. In this thesis, we propose a non-contact based remote heart rate measuring approach of the subject which depend on color intensity variation of the subject’s face skin. We applied our proposed method on two regions forehead and cheek using three different algorithms i.e. Fast Fourier Transform (FFT), Independent Component Analysis (ICA) and Principal Component Analysis (PCA) to extract heart rate. Our method average accuracy is 89.25% for all algorithms of both regions. It is also noteworthy that FastICA algorithm given the higher average accuracy more than 92% for both regions. The proposed method given 1.94% more average accuracy from the traditional method.