|
S O V A
is designed to form and store a database of those wanted by law enforcement agencies and for the identification of citizens...
|
|
|
|
|
IDENTIFICATION
system for law enforcement authorities intended for prompt identification of a person made by way of remote access to a central server from any type of officers work places.
|
|
|
|
|
VIDEOSTREAM
system is intended for video surveillance in crowded places.
|
|
|
|
|
PHOTOSYSTEM
Facial identification of citizens applying for national ID’s and passports to reveal individuals wanted by the authorities.
|
|
|
|
|
CHECKPOINT
is a automated information storage and retrieval system for detection of persons using forged passports or visas.
|
|
|
|
TECHNOLOGY
The developed biometric technology of face recognition is based on algorithms of recognition and comparison of the images. The basis of these algorithms is the Principal Component Analisys, which is in calculating maximum decorrelation factors, characterizing input images of the human faces.
On the system input the digitalized video photo image is sent. the automated system allows to capture a biometric sample from photo image, to extract biometric data from that sample, to compare the biometric data with that contained in one or more reference templates, to decide how well they match and to indicate whether or not an identification or verification of identity has been achieved.
The size of the biometric templates of attributes constitutes approximately 300 bytes, that allow building recognition systems even on a single-chip COMPUTER.
It should be noted, that process of coding uses the mechanism of self-training based on statistical processing of a large number of images.
Output result of the performance of biometric system is the list of the individuals' faces maximally similar to the input biometic sample and ranked on a degree of correlativeness of the appropriate vectors.
The given approach is a basis of the automated expert systems, where acceptance of the decision is an expert's prerogative.
In case of high degree of vectors correlation, exceeding certain threshold index, it should see as a fact of identification of a definite person.
In this case it is a question of a possibility of constructing completely automatic systems of identification by a non-contact, remote method.
The created technology was the base of the FRS SDK v.2.3; with which help it is possible to create highly reliable biometric systems of face identification.
You can download the Results of tests FRS SDK [here].
|
|
|
|
|
