Contactless Blood Pressure Estimation System Using a Computer Vision System

Blood pressure (BP) is one of the most common vital signs related to cardiovascular diseases. BP traditionally measured by mercury, aneroid, or digital sphygmomanometers; however, these approaches are restrictive, inconvenient, and need a cuff be attached directly patient. Therefore, it clinically important develop an innovative system that can accurately measure without for any direct physical contact with people. This work aims create new computer vision remotely measures using camera cuff. The proposed extracts optical properties photoplethysmographic signals in two regions forehead captured calculates based on specific formulas. experiments were performed 25 human participants different skin tones repeated at times under ambient light conditions. Compared systolic/diastolic readings obtained from commercial sphygmomanometer, achieves accuracy 94.6% root mean square error (RMSE) 9.2 mmHg systolic 95.4% RMSE 7.6 diastolic readings. Thus, has potential being promising tool upcoming generation monitoring systems.