Smartphone-based heart-rate measurement using facial images and a spatiotemporal alpha-trimmed mean filter.

Abstract

Currently, cardiovascular disease affects a relatively high proportion of the world's population. Thus, developing simple and effective methods for monitoring patients with cardiovascular disease is critical for research. Monitoring the heart rate of patients is a relatively simple and effective method for managing patients with this condition. For patients, the desired heart rate monitoring equipment should be portable, instantaneous, and accurate. Because smartphones have become the most prevalent mobile device, we utilized this technology as a platform for developing a novel heart-rate measurement system. Catering to the phenomenon of people using the front camera of their smartphones as a mirror, the proposed system was designed to analyze facial-image sequences captured using the front camera. A spatiotemporal alpha-trimmed mean filter was developed to estimate a user's heart rate quickly and accurately. The experimental results show that in addition to achieving these objectives, the developed system outperforms a similar personal computer-based system. In addition, the system performs effectively even when users are wearing glasses. Hence, the proposed system demonstrates practical value for people who must monitor their heart rate daily.