Method for performing face recognition in a radio access network

1. A method for performing face recognition in a telecommunication system comprising a central repository in which face recognition profiles attached to subscribers signed up for face recognition have been stored, the method comprising:

detecting proximity between at least two subscribers of the subscribers signed up for face recognition, said at least two subscribers being located within a radio coverage area controlled by a network node;

migrating face recognition profiles attached to said at least two subscribers, from the central repository to the network node; and

generating in the network node, an extended synthetic gallery for each migrated face recognition profile.

2. The method for performing face recognition according to claim 1 , further comprising:

capturing by a first subscriber of the at least two subscribers, an image of a second subscriber of the at least two subscribers;

sending a face recognition request comprising the captured image, from the first subscriber to the network node;

starting up of a face recognition process in the network node; and

performing in the network node image matching of the captured image with at least one of the extended synthetic galleries.

3. The method for performing face recognition according to claim 2 , further comprising:

as a result of a successful image matching, forwarding metadata related to the second subscriber, to the first subscriber.

4. The method for performing face recognition according to claim 2 , further comprising:

as a result of an un-successful image matching, forwarding the face recognition request from the network node to a controller of the central repository.

5. The method for performing face recognition according to claim 2 , wherein the face recognition process is started up in a virtual environment.

6. The method for performing face recognition according to claim 1 , wherein a face recognition profile comprises a limited face gallery, an estimated 3D face model and metadata.

7. The method for performing face recognition according to claim 1 , wherein proximity between said at least two subscribers is detected by using inputs from a location server.

8. The method for performing face recognition according to claim 1 , wherein a stored profile is attached to a signed up subscriber's terminal after a dialog between the subscriber and a service provider.

9. The method for performing face recognition according to claim 8 , wherein proximity between said at least two subscribers is detected by using GPS data received from said terminals.

10. The method for performing face recognition according to claim 1 , wherein migrated data is removed from the network node when at least one subscriber of said at least two subscribers leave the radio coverage area.

11. A method for performing face recognition in a telecommunication system comprising a central repository in which face recognition profiles attached to subscribers signed up for face recognition have been stored, the method comprising:

detecting proximity between a first subscriber of the subscribers signed up for face recognition and an entity involved with face recognition, said subscriber being located within a cell coverage area;

migrating a face recognition profile attached to said subscriber, from the central repository to a network node controlling the cell coverage area; and

generating in the network node, an extended synthetic gallery for the migrated face recognition profile.

12. The method for performing face recognition according to claim 11 , said entity being the network node.

13. The method for performing face recognition according to claim 11 , said entity being a second subscriber located within the coverage area.

14. The method for performing face recognition according to claim 13 , said second subscriber being not signed up for face recognition and having an application that can capture images and can make face recognition requests.

15. A network node of a mobile telecommunication network configured to perform face recognition, said node comprising:

a first interface configured to receive migrated face recognition profiles;

a non-transitory computer readable memory configured to implement a caching unit, the caching unit configured to store migrated face recognition profiles; and

a processor running a face recognition process configured to generate an extended synthetic gallery of a migrated face recognition profile.

16. The network node according to claim 15 , the node further comprising:

a second interface configured to receive a face recognition request comprising a captured image; and

the processor configured to perform image matching of the captured image with the extended synthetic galleries.

17. The network node according to claim 16 , wherein the second interface is further configured to transmit at least one of a face recognition request and metadata.

18. The network node according to claim 15 , wherein the processor is configured to run a virtualized environment capable to start or stop the face recognition process.

19. A network node of a mobile telecommunication network configured to migrate face recognition profiles, said node comprising:

a first interface configured to receive location reports;

a processor configured to detect proximity between different entities; and

a second interface configured to forward migrated face recognition profiles.

20. The network node according to claim 19 , wherein the first interface further being configured to receive face recognition profiles.

21. A non-transitory computer program product comprising computer program code, wherein the computer program comprises code adapted to perform the method of claim 1 , when the computer program code is executed in the processor.