A robust heart rate detection using smart-phone video

Abstract

In this paper, the authors have presented a smartphone based robust heart rate measurement system. The system requires the user to place the tip of his/her index finger on the lens of a smart phone camera, while the flash is on. The captured video signal often contains noise generated due to (i) improper finger placement, (ii) imparting excessive pressure, which subsequently blocks normal blood circulation and (iii) movement of the fingertip. To mitigate the above issues, a two stage approach has been proposed. Firstly, the onset of good video signal is detected by formulating a finite state machine, which employs multiple window short time fast fourier transform. Only upon receiving sufficient acceptable video signal, the heart rate is computed. Results indicate that the proposed method has successfully identified and rejected noisy video signal, resulting in avoidance of erroneous output.