Facial Recognition for a Videoconference

• US 20070188597A1
• Filed: 01/19/2007
• Published: 08/16/2007
• Est. Priority Date: 01/24/2006
• Status: Active Grant

• Current Assignee: Lifesize, Inc. (Enghouse Systems Limited)
• Original Assignee: Lifesize, Inc. (Enghouse Systems Limited)
• Inventors: Kenoyer, Michael L.
• Granted Patent: US 8,125,509 B2
• Time in Patent Office: Days
• US Class Current: 348/14.80
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q

Abstract

A facial recognition algorithm may be performed in order to identify a participant at a first endpoint in a videoconference. Participant information for the participant may be displayed together with an image of the participant on a display screen at a second endpoint in the videoconference. Displaying the participant information for the participant on the display screen may enable participants at the second endpoint to see the participant information for the participant during the videoconference.

Claims

1. A method, comprising:

receiving video information including a facial image of a first participant at a first endpoint in the videoconference;

displaying the video information on a display screen at a second endpoint in the videoconference;

analyzing the video information to locate the facial image of the first participant; and

performing a facial recognition algorithm to identify the first participant based on the facial image of the first participant.

2. The method of claim 1, further comprising:

determining first participant information for the first participant in response to said identifying the first participant;

displaying the first participant information for the first participant on the display screen at the second endpoint in the videoconference; and

wherein said displaying the first participant information for the first participant on the display screen at the second endpoint in the videoconference enables participants at the second endpoint in the videoconference to see the first participant information for the first participant during the videoconference.

3. The method of claim 2, wherein the first participant information for the first participant comprises one or more of:

a name of the first participant;

a phone number of the first participant;

an email address of the first participant;

a business address of the first participant;

a job title of the first participant; and

/or

an employer of the first participant.

4. The method of claim 1,

wherein said displaying the video information on the display screen at the second endpoint in the videoconference is performed by a videoconferencing device at the second endpoint;

and

wherein said analyzing the video information and said performing the facial recognition algorithm are performed by the videoconferencing device at the second endpoint.

5. The method of claim 1,

wherein said analyzing the video information, said performing the facial recognition algorithm, and said determining the first participant information are performed by a videoconferencing device at the first endpoint;

wherein the method further comprises the videoconferencing device at the first endpoint sending the first participant information to a videoconferencing device at the second endpoint;

wherein said displaying the video information and said displaying the first participant information are performed by the videoconferencing device at the second endpoint.

6. The method of claim 1,

wherein said performing the facial recognition algorithm to identify the first participant based on the facial image of the first participant comprises:

analyzing the facial image of the first participant;

creating information characterizing the facial image of the first participant in response to said analyzing the facial image of the first participant;

determining a first data object specifying facial information that matches the information characterizing the facial image of the first participant, wherein the first data object identifies the first participant; and

wherein the first data object links the facial information to the first participant information.

7. The method of claim 6, wherein said determining the first data object specifying facial information that matches the information characterizing the facial image of the first participant comprises determining a database record specifying facial information that matches the information characterizing the facial image of the first participant, wherein the first database record identifies the first participant.

8. The method of claim 1,

wherein the video information further comprises a facial image of a second participant at the first endpoint in the videoconference;

wherein the method further comprises;

analyzing the video information to locate the facial image of the second participant;

performing the facial recognition algorithm to identify the second participant based on the facial image of the second participant;

determining second participant information for the second participant in response to said identifying the second participant; and

displaying the second participant information for the second participant on the display screen at the second endpoint in the videoconference;

wherein said displaying the first participant information for the first participant comprises displaying the first participant information proximally to the first participant;

wherein said displaying the second participant information for the second participant comprises displaying the second participant information proximally to the second participant.

9. The method of claim 8, further comprising:

tracking movement of the facial image of the first participant; and

re-positioning the first participant information for the first participant on the display screen to maintain proximity of the first participant information to the first participant in response to said tracking movement of the facial image of the first participant.

10. The method of claim 1, further comprising:

tracking movement of the facial image of the first participant; and

controlling a camera at the first endpoint in response to said tracking the movement of the facial image of the first participant to keep the facial image of the first participant within view of the camera.

11. A videoconferencing device, comprising:

an input port operable to receive video information, wherein the video information comprises a facial image of a first participant at a first endpoint in a videoconference;

one or more computational elements operable to;

analyze the video information to locate the facial image of the first participant;

perform a facial recognition algorithm to identify the first participant based on the facial image of the first participant;

determine first participant information for the first participant in response to said identifying the first participant; and

create a composite video output signal operable to be used to display the first participant information with the video information;

wherein the videoconferencing device also includes an output port for displaying the composite video output signal.

12. The videoconferencing device of claim 11, wherein the first participant information for the first participant comprises one or more of:

a name of the first participant;

a phone number of the first participant;

an email address of the first participant;

a business address of the first participant;

a job title of the first participant; and

/or

an employer of the first participant.

13. The videoconferencing device of claim 11,

wherein said performing the facial recognition algorithm to identify the first participant based on the facial image of the first participant comprises:

analyzing the facial image of the first participant;

creating information characterizing the facial image of the first participant in response to said analyzing the facial image of the first participant; and

determining a first data object specifying facial information that matches the information characterizing the facial image of the first participant, wherein the first data object identifies the first participant;

wherein the first data object links the facial information to the first participant information.

14. The videoconferencing device of claim 11,

wherein the video information also includes a facial image of a second participant at the first endpoint in the videoconference;

wherein the one or more computational elements are further operable to;

analyze the video information to locate the facial image of the second participant;

perform the facial recognition algorithm to identify the second participant based on the facial image of the second participant;

determine second participant information for the second participant in response to said identifying the second participant;

combine the second participant information with the video information in the composite video output signal;

wherein the one or more computational elements combine the first participant information for the first participant to be displayed proximally to the first participant; and

wherein the one or more computational elements combine the second participant information with the second participant to be displayed proximally to the second participant.

15. The videoconferencing device of claim 14,

wherein the one or more computational elements are further operable to:

track movement of the facial image of the first participant; and

re-position the first participant information for the first participant within the composite output signal to maintain proximity of the first participant information to the first participant in response to said tracking movement of the facial image of the first participant.

16. A computer-readable storage medium, comprising program instructions, wherein the program instructions are computer-executable to:

receive video information including a facial image of a first participant at a first endpoint in a videoconference;

display the video information on a display screen at a second endpoint in the videoconference;

analyze the video information to locate the facial image of the first participant; and

perform a facial recognition algorithm to identify the first participant based on the facial image of the first participant.

17. The computer-readable storage medium of claim 16, wherein the program instructions are further executable to:

determine first participant information for the first participant in response to said identifying the first participant;

display the first participant information for the first participant on the display screen at the second endpoint in the videoconference; and

wherein said displaying the first participant information for the first participant on the display screen at the second endpoint in the videoconference enables participants at the second endpoint in the videoconference to see the first participant information for the first participant during the videoconference.

18. The computer-readable storage medium of claim 16, wherein the first participant information for the first participant comprises one or more of:

a name of the first participant;

a phone number of the first participant;

an email address of the first participant;

a business address of the first participant;

a job title of the first participant; and

/or

an employer of the first participant.

19. The computer-readable storage medium of claim 16,

wherein said displaying the video information on the display screen at the second endpoint in the videoconference is performed by a videoconferencing device at the second endpoint;

and

wherein said analyzing the video information and said performing the facial recognition algorithm are performed by the videoconferencing device at the second endpoint.

20. The computer-readable storage medium of claim 16,

wherein said analyzing the video information, said performing the facial recognition algorithm, and said determining the first participant information are performed by a videoconferencing device at the first endpoint;

wherein the method further comprises the videoconferencing device at the first endpoint sending the first participant information to a videoconferencing device at the second endpoint;

wherein said displaying the video information and said displaying the first participant information are performed by the videoconferencing device at the second endpoint.

21. The computer-readable storage medium of claim 20, wherein said determining the first data object specifying facial information that matches the information characterizing the facial image of the first participant comprises determining a database record specifying facial information that matches the information characterizing the facial image of the first participant, wherein the first database record identifies the first participant.