Skin Depolarization for Living-skin Tissue Segmentation: A Quantitative Comparison with PPG Imaging

Conventional living-skin detection methods based on remote photoplethysmographic imaging (PPGI) are not suitable for face anti-spoofing nor skin segmentation for video health monitoring. Therefore, we refer to a novel algorithm based on an entirely new principle for these tasks, i.e., multi-spectral depolarization (MSD) of skin tissues. The effectiveness of MSD remains to be quantified in different application scenarios. In this paper, we conduct laboratory and clinical trials to make a detailed quantitative comparison between two approaches (MSD and PPGI) for skin segmentation. The laboratory result shows that MSD can distinguish the non-live human in the fraud video, whereas the PPGI method failed to identify the liveness. The clinical experiments show that MSD outperforms PPGI in skin pigmentation, with improvements of almost 20%, 15%, and 10% in precision, recall, and F1-score, respectively, highlighting the effectiveness of MSD.