发明名称 System and method for biometric user authentication using 3D in-air hand gestures
摘要 A method authenticates users. During user enrollment, a computing device records 3D gesture samples captured by a depth sensor as performed by a first user. Each recorded gesture sample includes a temporal sequence of locations for multiple specified body parts. The device computes an average gesture, and selects an error tolerance. These are stored as a gesture template for the first user. A second user performs a gesture for authentication. The depth sensor captures a 3D gesture from the second user, where the captured 3D gesture includes a temporal sequence of locations for the multiple body parts. The device computes the distance between the captured 3D gesture and the average gesture. When the distance is less than the error tolerance, the second user is authenticated as the first user, and the device grants access to some secured features. Otherwise, the second user is not authenticated.
申请公布号 US9355236(B1) 申请公布日期 2016.05.31
申请号 US201414244839 申请日期 2014.04.03
申请人 FUJI XEROX CO., LTD. 发明人 Kratz Sven;Aumi Md Tanvir Islam
分类号 G06F21/32;G06F3/01 主分类号 G06F21/32
代理机构 Morgan, Lewis & Bockius LLP 代理人 Morgan, Lewis & Bockius LLP
主权项 1. A method of authenticating users, comprising: at a computing device with a depth sensor, one or more processors, and memory storing one or more programs for execution by the one or more processors: recording a plurality of 3D gesture samples from a first user, wherein the gesture samples correspond to a gesture selected by the first user and wherein each respective recorded gesture sample includes a respective temporal sequence of locations for a plurality of specified body parts;computing an average gesture T from the gesture samples;selecting an error tolerance ε corresponding to T, including computing a spread of the gesture samples, and when the spread is greater than a predefined maximum spread value, recording additional gesture samples and recomputing the average gesture T using the additional gesture samples;storing the average gesture T and the error tolerance ε as a gesture template for the first user;capturing a 3D gesture from a user for authentication, wherein the captured 3D gesture includes a temporal sequence of locations for the plurality of body parts;computing a distance d between the captured 3D gesture and the average gesture T;when the distance d is less than or equal to ε, authenticating the user as the first user, thereby granting the user access to a secured feature on the computing device; andwhen the distance d is greater than ε, not authenticating the user.
地址 Tokyo unknown