Structural models for face detection

Despite the success in the last two decades, the state-of-the-art face detectors still have problems in dealing with images in the wild for the large appearance variations. Instead of taking appearance variations as black boxes and leaving them to statistical learning algorithms, we propose a structural face model to explicitly represent them. Our hierarchical part based structural face model enables part subtype option to describe appearance variations of the local part, and part deformation to capture the deformable variations between different poses and expressions. In the process of detection, the input candidate is first fitted by the structural model to infer the part location and part subtype, and the confidence score is then computed based on the fitted configuration to reduce the influence of structure variation. Besides the face model, we utilize the co-occurrence of face and body to further boost the face detection performance. We present a method for training phrase based body detectors, and propose a structural context model to jointly use the results of face detector and various body detectors. Experiments on the challenging FDDB show that our method has state-of-the-art performance, compared with other commercial and academic systems.