Multiple Thermal Face Detection in Unconstrained Environments Using Fully Convolutional Networks

Multiple thermal face detection in unconstrained environments has received increasing attention due to its potential in liveness detection and night-time surveillance. This paper presents an effective method based on fully convolutional network (FCN), density-based spatial clustering of applications with noise (DBSCAN) and non-maximum suppression (NMS) algorithm. Our proposed approach captures the thermal face features automatically using FCN. Then, an improved DBSCAN is used to detect all the faces in the thermal images. Finally, we use NMS to remove all of the bounding-boxes with an IOU (intersection over union). Experiments on RGB-D-T database show that the proposed method exceeds the state-of-the-art algorithms for single face detection on thermal images. We also build a new database with 10K multiple thermal face images in unconstrained environments. The results also show a high precision for multi-face detection tasks.