FIELD: biometrical identification and authentication; electronic passports, identity cards, systems of electronic documents circulation, access restriction systems.
SUBSTANCE: artificial neural network is trained on the examples of biometrical images of identified human. Description of trained neural network is included into document, which identifies human identity, as a table. When identifying a human his biometrical image is converted into controlled parameters, which are converted into output code using neural network. Output code and defined code are compared. If they match, positive decision is made regarding human identity.
EFFECT: reduced number of communication channels for transferring trained artificial neural networks for identified humans, and reduced memory size on checkpoints for storing named neural networks.
2 cl, 2 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR GENERATION OF ELECTRONIC BIOMETRIC ID CARD | 2008 |
|
RU2391704C1 |
ANONYMOUS BIOMETRIC PERSON'S REGISTRATION METHOD | 2008 |
|
RU2371765C2 |
IDENTIFICATION METHOD OF PERSON AS TO HIS BIOMETRIC IMAGE | 2008 |
|
RU2371764C1 |
METHOD FOR BIOMETRIC PROTECTION OF WITNESS ANONYMITY DURING COURT PROCEEDINGS | 2012 |
|
RU2543956C2 |
METHOD FOR OBTAINING OF INFORMATION FOR BIOMETRIC PERSON IDENTIFICATION | 2016 |
|
RU2640732C2 |
METHOD OF FORMING OF ELECTRONIC DOCUMENTS AND DEVICE FOR ITS REALISATION | 2007 |
|
RU2365047C2 |
METHOD OF GUARANTEED DEPERSONALIZATION OF ELECTRONIC DOCUMENTS | 2014 |
|
RU2629445C2 |
METHOD OF CREATING ELECTRONIC DOCUMENT | 2012 |
|
RU2527731C2 |
METHOD FOR AUTOMATIC FORMATION OF A BIOMETRIC IMAGE BASE "FRIEND" FOR TRAINING AND TESTING OF HIGH-RELIABILITY BIOMETRIC-NEURAL NETWORK AUTHENTICATION OF AN INDIVIDUAL | 2020 |
|
RU2734846C1 |
METHOD FOR PERSONALITY AUTHENTICATION BY FINGERPRINTS AND DEVICE FOR ITS IMPLEMENTATION | 2007 |
|
RU2355307C2 |
Authors
Dates
2007-01-20—Published
2005-02-02—Filed