Idemia Identity & Security Germany Ag

Magnetic Autocontrol Gmbh

L-1 Identity Solutions Ag

Norbert Wendt

Christian Winter

Martin Werner

Michael Brauckmann

Lothar Lais

Stefan Langhammer

Dirk Homberg

The invention refers to a computer-implemented method of analyzing security documents having visible information and at least one of infrared and ultraviolet detectable information, the method comprising the steps of: receiving visible-color data of a first set of pixels of a first region of the security document in a first image of the security document and feeding the visible-color data to a convolutional neural network, CNN; receiving infrared, IR, and/or ultraviolet, UV, data of a second and/or third set of pixels of a respective second and/or third region in a respective second and/or third image of the security document and feeding the IR and/or UV data to the CNN; analyzing the visible-color data of the first set of pixels using the CNN to extract characteristics of the security document from the visible information; and analyzing the IR and/or UV data of the second and/or third set of pixels using the CNN to extract characteristics of the security document from the IR and/or UV information. Further, a corresponding system is provided.

Extended convolutional neural network for document analysis

The invention provides a method for video surveillance in a video-surveillance system comprising the steps of capturing video images by a video camera observing an area of surveillance; wherein the capturing the video images comprises making objects in the area of surveillance irrecognizable or invisible in captured video images; receiving, by a processor, a predetermined signal; based on the received predetermined signal, generating a first control signal by the processor and transmitting the first control signal to the video camera; receiving the first control signal by the video camera; based on the received first control signal, stopping making objects in the area of surveillance irrecognizable or invisible in the captured video images.

Alarm dependent video surveillance

The invention relates to an apparatus for a checkpoint, comprising a controlled access passage, the exit of which is closed by an exit door (gate). Said exit door () opens in response to a signal of a least one biometric unit () which is arranged in the controlled access space () and by which the biometric features of a person desiring passage can be detected, and said biometric unit () is arranged frontally opposite of the entrance to the controlled access space () and preferably integrated in the exit door () of the controlled access space (). A person entering the controlled access space () is therefore immediately located quasi automatically in the correct position for detection by the biometric unit (), which is to say, frontally opposite of the biometric unit.

Apparatus for a checkpoint

Growing community of inventors

Essen, Germany

Norbert Wendt