Author/Authors :
Xu, Yuanyuan College of Information Science and Engineering - Huaqiao University, China , Yan, Wan Xiamen Star Clouds Network Technology Co., Ltd., China , Yang, Genke Department of Automation - Shanghai Jiaotong University, China , Luo, Jiliang College of Information Science and Engineering - Huaqiao University, China , Li, Tao Central Laboratory of Health Quarantine - Shenzhen International Travel Health Care Center and Shenzhen Academy of Inspection and Quarantine - Shenzhen Customs District, China , He, Jianan Central Laboratory of Health Quarantine - Shenzhen International Travel Health Care Center and Shenzhen Academy of Inspection and Quarantine - Shenzhen Customs District, China
Abstract :
Face detection and alignment in unconstrained environment is always deployed on edge devices which have limited memory storage and low computing power. This paper proposes a one-stage method named CenterFace to simultaneously predict facial box and landmark location with real-time speed and high accuracy. The proposed method also belongs to the anchor-free category. This is achieved by (a) learning face existing possibility by the semantic maps, (b) learning bounding box, offsets, and five landmarks for each position that potentially contains a face. Specifically, the method can run in real time on a single CPU core and 200 FPS using NVIDIA 2080TI for VGA-resolution images and can simultaneously achieve superior accuracy (WIDER FACE Val/Test-Easy: 0.935/0.932, Medium: 0.924/0.921, Hard: 0.875/0.873, and FDDB discontinuous: 0.980 and continuous: 0.732).
Keywords :
CenterFace , Face as Point , Joint Face , Detection
