Facial recognition system

• US 10,303,929 B2
• Filed: 10/27/2016
• Issued: 05/28/2019
• Est. Priority Date: 10/27/2016
• Status: Active Grant

• Current Assignee: Bose Corporation
• Original Assignee: Bose Corporation
• Inventors: Garrett, George Sean
• Primary Examiner(s): Potts, Ryan P
• Application Number:
  US15/335,774
• Publication Number:
  US 20180121712A1
• Time in Patent Office: 943 Days
• Field of Search: None
• CPC Class Codes: G06F 1/163 Wearable computers, e.g. on a belt
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06V 40/161 Detection; Localisation; Normalisation
• CPC Class Codes: G06V 40/172 Classification, e.g. identification
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: H04N 23/60 Control of cameras or camera modules
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/695 Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
• CPC Class Codes: H04R 1/028 associated with devices performing functions other than acoustics, e.g. electric candles
• CPC Class Codes: H04R 1/406 microphones
• CPC Class Codes: H04R 2499/11 Transducers incorporated or for use in hand-held devices, e.g. mobile phones, PDA's, camera's

Abstract

A recognition system includes a camera, at least one speaker, a microphone, and a processor in communication with the camera, the speaker, and the microphone. The processor is configured to recognize faces or devices and to receive a selection of at least one face or device to be monitored. The processor is also configured to direct the camera and/or the microphone toward the selected face or device and provide audio from the selected face or device to the speaker.

Claims

1. A recognition system comprising:

a camera comprising a body section and a camera section, the body section and the camera section being fixed together at an internal movable joint that is internal to the body section and internal to the camera section and that comprises a controllable servo;

at least one speaker;

a microphone; and

a processor in communication with said camera, said speaker, and said microphone;

wherein said processor is configured to recognize at least one of faces or devices;

wherein said processor is configured to receive a selection of at least one face or device to be monitored; and

wherein said processor is configured to direct at least one of said camera or said microphone toward the at least one selected face or device and provide audio received from the at least one selected face or device to said speaker, wherein said processor is configured to move said camera section relative to said body section at said internal movable joint to direct said camera section toward the at least one selected face or device, using said controllable servo.

2. The recognition system of claim 1, wherein said microphone is an arrayed microphone and said processor is configured to direct said microphone toward the at least one selected face or device using beamforming.

3. The recognition system of claim 1, wherein said processor is further configured to compare at least one pre-recorded image of said at least one selected face or device to be monitored with images captured by said camera in order to determine a position of the at least one selected face or device to be monitored.

4. The recognition system of claim 3, further comprising communications hardware for transferring data over a network.

5. The recognition system of claim 4, wherein said processor is further configured to access said at least one pre-recorded image of said at least one selected face or device to be monitored via said communications hardware.

6. The recognition system of claim 5, wherein said processor is further configured to access said at least one pre-recorded image of said at least one selected face or device to be monitored via a social network.

7. The recognition system of claim 1, wherein said processor is further configured to generate a faceprint based on a facial image.

8. The recognition system of claim 7, wherein said processor is further configured to compare at least one stored faceprint with a faceprint derived from an image captured by said camera in order to determine whether the captured image is a match.

9. The recognition system of claim 1, further comprising a laser pointer mounted to the camera and arranged to point in a direction indicative of an initial direction of the camera.

10. An audio cue system comprising:

a camera comprising a body section and a camera section, the body section and the camera section being fixed together at an internal movable joint that is internal to the body section and internal to the camera section and that comprises a controllable servo;

at least one speaker;

a microphone;

a text-to-speech engine; and

a processor in communication with said camera, said speaker, said microphone, and said text-to-speech engine;

wherein said processor is configured to receive a captured facial image of a face from said camera to identify a person matching said captured facial image;

wherein said processor is further configured to retrieve information about the identified person and generate and provide audio cues to said at least one speaker concerning said retrieved information using said text-to-speech engine; and

wherein said processor is configured to move said camera section relative to said body section at said internal movable joint to direct said camera section toward the face, using said controllable servo.

11. The audio cue system of claim 10, wherein said processor is further configured to compare said captured facial image with a stored facial image to identify said person matching said captured facial image.

12. The audio cue system of claim 11, wherein said processor is further configured to generate a faceprint based on said captured facial image.

13. The audio cue system of claim 12, wherein said processor is further configured to compare said faceprint generated from said captured facial image with a stored faceprint to identify said person matching said captured facial image.

14. The audio cue system of claim 10, further comprising communications hardware for transferring data over a network.

15. The audio cue system of claim 14, wherein said processor is further configured to access stored facial images to identify said person matching said captured facial image.

16. The audio cue system of claim 15, wherein said processor is further configured to access said stored facial images via a social network.

17. The audio cue system of claim 10, wherein said processor is further configured to receive inputs from a user regarding what information should be included within said audio cues.

18. The audio cue system of claim 10, wherein said processor is further configured to receive inputs for identifying or confirming an identity of said person in said captured facial image.

19. The audio cue system of claim 10, configured to recognize language indicative of an introduction and to automatically record a name detected in the language indicative of the introduction in association with the captured facial image.

20. A method for providing audio cues comprising:

capturing an image of at least one individual with a camera comprising a body section and a camera section, the body section and the camera section being fixed together at an internal movable joint that is internal to the body section and internal to the camera section and that comprises a controllable servo;

moving said camera section relative to said body section at said internal movable joint to direct said camera section toward the individual, using said controllable servo;

comparing said image to stored facial data;

matching said image to the stored facial data;

retrieving information related to the stored facial data;

converting said information into an audio cue using a text-to-speech engine; and

transmitting said audio cue to an audio device for presentation to a user.

21. The method of claim 20, wherein said stored facial data comprises a faceprint and the step of comparing said image comprises generating the faceprint based on said captured image.

22. The method of claim 20, further comprising manually guiding the camera to the at least one individual using a laser pointer mounted to the camera.