摘要:
A method for discriminating between a real face and a two-dimensional reproduction of the face, in a biometric detection process, the method comprising: (a) making at least two digital recordings of the face or its reproduction in time sequence, one after the other; (b) dividing each of the recordings into a number of image components wherein each image component comprises a number of pixels; (c) determining the displacement of the individual image components from the first recording to the second recording by correlation and generating a displacement vector field therefrom; and (d) analyzing the displacement vector field for determining whether the recording has been made from a real face or from its reproduction.
摘要:
The method according to the invention is based on a first image of a first eye region of a person and a second image of a second eye region of the person, wherein the first eye region contains one of the eyes of the person, for example the right eye, and the second eye region contains the other eye of the person, for example the left eye; one of the images is mirrored, and the mirrored and the non-mirrored image are combined in the position space and/or in the feature space, in order to generate a template of an overlaid image. The template contains biometric features for person recognition.
摘要:
The method according to the invention is based on a first image of a first eye region of a person and a second image of a second eye region of the person, wherein the first eye region contains one of the eyes of the person, for example the right eye, and the second eye region contains the other eye of the person, for example the left eye; one of the images is mirrored, and the mirrored and the non-mirrored image are combined in the position space and/or in the feature space, in order to generate a template of an overlaid image. The template contains biometric features for person recognition.