Local Remote Photoplethysmography Signal Analysis for Application in Presentation Attack Detection

Abstract

This paper presents a method to analyze and visualize the local blood flow through human skin tissue within the face and neck. The method is based on the local signal characteristics and extracts and analyses the local propagation of blood flow from video recordings. In a first step, the global pulse rate is identified in RGB images using normalized green color channel intensities. We then calculate for an image sequence, a local remote photoplethysmography (rPPG) signal that is presented by a chrominancebased signal. This local rPPG signal is analyzed and then used to extract the local blood flow propagation from signal-to-noise ratio (SNR) and pulse transit time (PTT) maps. These maps are used to visualize the propagation of the blood flow (PTT) and reveal the signal quality of each spatial position (SNR). We further proved a novel pulse rate based skin segmentation method, that is based on the global pulse rate and the statistical properties of the SNR map. This skin segmentation method allows a direct application in liveliness detection, e.g., for presentation attack detection (PAD). Based on the described local blood flow analysis, we propose a PAD system, that specializes in identifying a partial face and neck coverage in the video. The system is tested using datasets showing a person with different facial coverings, such as a mask or a thick layer of makeup. All tested masks can be detected and identified as presentation attacks.