Abstract: Methods of authenticating a user or speaker are provided. These methods include obtaining an input speech signal and user credentials identifying the user or speaker. The input speech signal includes a single-channel signal or a multi-channel speech signal. The methods further include extracting a speech voiceprint from the input speech signal, and retrieving a reference voiceprint associated to the user credentials. The methods still further include determining a voiceprint correspondence between the speech voiceprint and the reference voiceprint, and authenticating the user or speaker depending on said voiceprint correspondence. The methods yet further include updating the reference voiceprint depending on the speech voiceprint corresponding to the authenticated user or speaker. Computer programs, systems and computing systems are also provided which are suitable for performing said methods of authenticating a user or speaker.

Abstract: Methods and devices for biometric verification are disclosed. During registration or encoding, a first vector representing biometric features of a subject is generated. Machine-readable optical labels based on the first vector are then generated. During validation or decoding, physical characteristics representative of the subject are captured, the physical characteristic containing biometric features of the subject. The biometric features are identified in the captured physical characteristics. A second vector representing the identified biometric features is generated. The machine-readable optical label is read to decode the first vector. The first vector is compared with the second vector to compute a match probability.

Abstract: An authenticating method for authenticating a document from obtained images of the document, by determining an authenticity indicator of the document by verifying whether a meta-characteristic satisfies a predefined threshold associated to the meta-characteristic, the meta-characteristic being a measurement of a difference of a parameter of a detected element relative to a reference parameter of a reference model; and also an authenticating method for authenticating an identity of a person comprising performing the authenticating method for authenticating a document of the person, the document being an ID document, and determining an alikeness indicator by comparing a first face image and a second face image, using an image processing method; and authenticating the identity of the person depending on a result of the authenticating method performed for authenticating the ID document and whether the determined alikeness indicator is within an alikeness threshold.

Abstract: Methods and devices for performing user authorisations using biometric features are disclosed. User identifiers and biometric features of the users are registered in an identification server. Users are identified by their user identifiers, the users being in communication range with an authorisation module. A shortlist of users is generated based identified user identifiers. Biometric features of the users are captured at the authorisation module. The biometric features presented are compared with biometric features stored in the identification server to generate a match probability. Users are validated if the match probability exceeds a threshold. User authorisation is performed when the users are identified and validated.

Abstract: Methods and devices for biometric verification are disclosed. During registration or encoding, a first vector representing biometric features of a subject is generated. Machine-readable optical labels based on the first vector are then generated. During validation or decoding, physical characteristics representative of the subject are captured, the physical characteristic containing biometric features of the subject. The biometric features are identified in the captured physical characteristics. A second vector representing the identified biometric features is generated. The machine-readable optical label is read to decode the first vector. The first vector is compared with the second vector to compute a match probability.