TFLD: Thermal Face and Landmark Detection for Unconstrained Cross-spectral Face Recognition

Automated thermal-to-visible face recognition has received increased attention due to benefits related to low-light applications. Towards improvement of related matching accuracy, we hereby present TFLD, a detector of face and landmarks operating in the thermal spectrum. Our proposed TFLD is based on the architecture of YOLOv5, integrating sequential modules for face and landmark detection. We introduce a thermal face restoration scheme, in order to enhance thermal image quality and hence detection accuracy. We address data scarcity by transferring landmarks in paired visible and thermal images. Our experimental results showcase that our proposed detector accurately detects faces, as well as landmarks in a wide range of adversarial conditions. Further, TFLD achieves promising results on three benchmark multi-spectral face and landmark datasets, namely ARL-VTF, SF-TL54 and RWTH-Aachen; thereby improving the matching accuracy in cross-spectral face recognition by providing robust face alignment based on estimated facial landmarks.