Photoplethysmographic biometrics: A comprehensive survey

The wide diffusion of wearable sensors and mobile devices encouraged the study of biometric recognition techniques that require a low level of cooperation from users. Among them, the analysis of cardiac information extracted from plethysmographic (PPG) signals is attracting the research community due to the possibility of performing continuous authentications using low-cost devices that can acquire signals without any action required from the users. Although PPG-based biometric systems are relatively recent technologies, machine learning techniques and deep learning strategies have shown accuracy in heterogeneous application scenarios. This paper presents the first literature review of PPG-based biometric recognition approaches. First, we describe the application contexts suitable for PPG-based biometrics. Second, we analyze the systems in the literature, describe the acquisition sensors, and present a classification of the processing methods. Third, we summarize the available public datasets and the results achieved by recent state-of-the-art approaches. Finally, we analyze the open problems in this research field.