<p>Biometrics have been extensively utilized in the realm of identity recognition. However, each biometric method has its inherent limitations in specific scenarios. For example, identity recognition based on facial images is contactless but can be forged; finger vein recognition is very secure but generally requires contact collection to ensure accurate identification. In some scenarios with high security requirements, there is often a need for contactless acquisition of biometric features that cannot be forged to recognize identity. Therefore, a novel biometric, facial tissue oxygen saturation (StO2) with the advantages of robust anti-spoofing capabilities and non-contact measurement, is proposed for identity recognition. To more comprehensively verify the feasibility of facial StO2 for identity recognition, a Facial StO2 Identity Dataset (FSID148) containing 148 identities is collected and the feasibility of facial StO2 identity recognition is validated by performing verification, close-set identification, and open-set identification tasks. In order to enhance the performance of facial StO2 identity recognition, an attention-guided contrastive learning framework that enables backbones to derive discriminative identity representations from both local and global facial StO2 regions is proposed. The method proposed has achieved accuracies of 96.11%, 94.60%, and 88.51% in the aforementioned tasks, positioning facial StO2 as a promising biometric for a wide array of application scenarios.</p>