Remote assessment of heart rate by skin color processing

Oxy-hemoglobin and deoxy-hemoglobin, main blood chromatophores flowing through the arteries and veins, respectively, reflect sunlight differently. The biggest difference is at a specific wavelength in the visible spectrum. The amount of blood in the arteries varies during cardiac activity. As a result, the skin color changes, but its limits cannot be noticed in heart cycle. The authors present an algorithm, for video signal processing, to achieve remote heartbeat having the following steps: selection of the region of interest, filtering using principal component analysis and empirical mode decomposition. The proposed method uses fewer pixels than those used by other methods presented in the literature and was confirmed by testing on subjects in the room light conditions by using a pulse oximeter.