Real-Time Pulse Counting Using Palm Images


Gangal O. B., ÖZTÜRK M.

26th IEEE Signal Processing and Communications Applications Conference (SIU), İzmir, Türkiye, 2 - 05 Mayıs 2018 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Doi Numarası: 10.1109/siu.2018.8404381
  • Basıldığı Şehir: İzmir
  • Basıldığı Ülke: Türkiye
  • Recep Tayyip Erdoğan Üniversitesi Adresli: Hayır

Özet

In this study, real-time pulse counting was performed using palm images obtained from a standard webcam. The signals obtained from the real-time palm images taken from the webcam were subjected to various signal processing operations and the number of heartbeats per minute was counted. First, skin color was determined from palm images, and the change of the mean value of the green channel area related to the skin color was examined with respect to time. The number of heartbeats per minute was calculated from the obtained signals by counting the number of peaks of the signal in a certain time interval and determining the dominant frequency component of the signal by frequency analysis. The results were compared with those of the pulse oximeters available in the market and the photoplethysmogram measurement programs available on smartphones. The study also examined the effect of the number of frames per second taken from the camera on the heartbeats measurements.