发明名称 Method and system of identification and authentication using facial expression
摘要 The present invention employs a first step of stationary face recognition, followed by a facial expression test, a continuous movement tracking test, and a 3D perspective check to identify and authenticate a subject, prevent photo spoofing and facemask spoofing, and determining whether the subject is a living person. The method requires a subject to present her face before a camera, which can be the built-in or peripheral camera of a mobile communication device. The method also requires displaying to the subject certain instructions and the real-time video feedback of the subject face on a display screen, which can be the built-in or peripheral display screen of the mobile communication device or mobile computing device. The 3D perspective check uses a single camera to take two images of the subject's face for the calculating the stereoscopic view data of the subject's face.
申请公布号 US9619723(B1) 申请公布日期 2017.04.11
申请号 US201615045601 申请日期 2016.02.17
申请人 Hong Kong Applied Science and Technology Research Institute Company Limited 发明人 Chow Felix;Tang Arvin Wai Kai
分类号 G06K9/00 主分类号 G06K9/00
代理机构 Spruson & Ferguson (Hong Kong) Limited 代理人 Spruson & Ferguson (Hong Kong) Limited
主权项 1. A method for personal identification and authentication using face recognition and facial expression analysis comprising: conducting a stationary face recognition of a subject by a device for personal identification and authentication, wherein the device comprises one or more computer processors, a camera, and a display screen, wherein the stationary face recognition comprising: image-capturing the subject's face in a first captured image and verifying the first captured image is of a human face and identity of the subject by matching the first captured image against a database of pre-recorded face data records; conducting a facial expression test on the subject by the device, the facial expression test comprising: generating a random sequence of different facial expression requirements; andvideo-capturing the subject's facial expressions and analyzing the subject's facial expressions and comparing them against the generated facial expression requirements; conducting a continuous movement tracking test on the subject by the device, the continuous movement tracking test comprising: generating a random sequence of different movement requirements; andvideo-capturing the subject's movements and analyzing the subject's movements and comparing them against the generated movement requirements; and conducting a three-dimensional perspective check on the subject by the device, the three-dimensional perspective check comprising: obtaining two three-dimensional-perspective-check images of the subject's face at two different locations with respect to the device;locating two sets of facial landmarks in a first of the two three-dimensional-perspective-check images, wherein the two sets of facial landmarks lying on two different three-dimensional spatial planes in the first of the two three-dimensional-perspective-check images;locating the same two sets of facial landmarks in a second of the two three-dimensional-perspective-check images;estimating a three-dimensional spatial plane for each of the two sets of facial landmarks in the second of the two three-dimensional-perspective-check images; andcalculating a relative displacement between the two three-dimensional spatial planes in the two three-dimensional-perspective-check images for determining the three-dimensional perspective check result.
地址 Hong Kong Science Park, Shatin, New Territories, Hong Kong CN