A method for distinguishing between a real face and a two-dimensional image of the face detection process in a biometric
暂无分享,去创建一个
The invention relates to a method for distinguishing between a real face and a two-dimensional image of the face in a biometric acquisition process, in which (a) in time series consecutively at least two digital images of the face or of its illustration made, (b) each of the shots in is divided a plurality of picture elements, each picture element comprises a plurality of pixels, (c) the displacements of individual picture elements of the first shot are determined for the second recording by correlation and from a displacement vector field is generated, and (d) the displacement vector field is analyzed, to decide whether the footage of the real face or from his picture made. Further, the invention relates to a method for identifying a person in a distributed IT infrastructure, in particular a cloud environment, wherein the received at least two digital images of the face of the person at a location remote from the person computer and the method according to one of the preceding claims to is one or spread over several remote from the person computer performed with the images of the face of the person are also used to identify the person.
[1] Harvey F. Silverman,et al. A Class of Algorithms for Fast Digital Image Registration , 1972, IEEE Transactions on Computers.
[2] Shang-Hong Lai,et al. An Optical Flow-Based Approach to Robust Face Recognition Under Expression Variations , 2010, IEEE Transactions on Image Processing.
[3] Kuo-Chin Fan,et al. Distinguishing falsification of human faces from true faces based on optical flow information , 2009, 2009 IEEE International Symposium on Circuits and Systems.