Wireless location and facial/speaker recognition system
An integrated wireless location and facial/speaker-recognition system that provides distinct advantages over facial-recognition systems and speaker-recognition systems of the prior art is disclosed. The integrated system is capable of using information from a wireless location system to improve the performance of the facial recognition and speaker recognition. The system is capable of processing photographs and/or audio samples captured by a camera/microphone at a fixed location (e.g., a digital pan-zoom-tilt (PZT) surveillance camera, etc.) as well as those captured by a mobile camera/microphone (e.g., a digital camera and microphone in a smartphone, etc.). The system also features a feedback mechanism by which the location-informed results can be used to improve the system's recognition abilities.
1. A method comprising:
receiving, by a data-processing system from a facial-recognition system, an assessment A of a photograph taken by a camera, wherein said assessment A comprises a non-empty set of candidate user identifiers, and wherein said photograph is of one or more locations;
transmitting, by said data-processing system, one or more of said non-empty set of candidate user identifiers to a wireless location system;
receiving, by said data-processing system from said wireless location system, a non-empty set of estimated locations, wherein each of said non-empty set of estimated locations is for a respective wireless terminal that is associated with a respective one of said non-empty set of candidate user identifiers; and
generating, by said data-processing system, a new assessment A′ that is based on:
(i) said assessment A,
(ii) said non-empty set of estimated locations, and
(iii) said one or more locations photographed by said camera,
wherein said assessment A′ comprises a non-empty set of candidate user identifiers.
2. The method of claim 1 further comprising transmitting, by said data-processing system, said new assessment A′ to said facial-recognition system.
3. The method of claim 2 further comprising:
receiving, by said facial-recognition system, said new assessment A′; and
in response to said new assessment A′, modifying a parameter of an algorithm of said facial-recognition system.
4. The method of claim 1 further comprising:
receiving, by said facial-recognition system, said new assessment A′; and
in response to said new assessment A′, modifying an algorithm of said facial-recognition system.
5. The method of claim 1 further comprising determining, by said data-processing system, said one or more locations photographed by said camera.
6. The method of claim 5 wherein the determining of said one or more locations photographed by said camera is based on the location of said camera.
7. The method of claim 6 further wherein the determining of said one or more locations photographed by said camera is also based on the orientation of said camera.
8. The method of claim 1 wherein said camera is a pan-zoom-tilt surveillance camera.
9. The method of claim 1 wherein said camera is fixed at a particular location.
10. The method of claim 1 wherein said camera is not fixed at a particular location.
11. A method comprising:
receiving, by a data-processing system from a speaker-recognition system, an assessment A of an audio sample captured by a microphone, wherein said assessment A comprises a non-empty set of candidate user identifiers, and wherein said microphone has an area of coverage that comprises one or more locations;
transmitting, by said data-processing system, one or more of said non-empty set of candidate user identifiers to a wireless location system;
receiving, by said data-processing system from said wireless location system, a non-empty set of estimated locations, wherein each of said non-empty set of estimated locations is for a respective wireless terminal that is associated with a respective one of said non-empty set of candidate user identifiers; and
generating, by said data-processing system, a new assessment A′ that is based on:
(i) said assessment A,
(ii) said non-empty set of estimated locations, and
(iii) said one or more locations of said area of coverage of said microphone,
wherein said assessment A′comprises a non-empty set of candidate user identifiers.
12. The method of claim 1 further comprising transmitting, by said data-processing system, said new assessment A′ to said speaker-recognition system.
13. The method of claim 12 further comprising:
receiving, by said speaker-recognition system, said new assessment A′; and
in response to said new assessment A′, modifying a parameter of an algorithm of said speaker-recognition system.
14. The method of claim 1 further comprising:
receiving, by said speaker-recognition system, said new assessment A′; and
in response to said new assessment A′, modifying an algorithm of said speaker-recognition system.
15. The method of claim 11 further comprising determining, by said data-processing system, said one or more locations of said area of coverage of said microphone.
16. The method of claim 15 wherein the determining of said one or more locations of said area of coverage of said microphone is based on the location of said microphone.
17. The method of claim 16 further wherein the determining of said one or more locations of said area of coverage of said microphone is also based on the orientation of said microphone.
18. The method of claim 1 wherein said microphone is a unidirectional microphone.
19. The method of claim 11 wherein said microphone is fixed at a particular location.
20. The method of claim 11 wherein said microphone is not fixed at a particular location.