Apparatus, system and method of automatically identifying participants at a videoconference who exhibit a particular expression

• US 20050131744A1
• Filed: 12/10/2003
• Published: 06/16/2005
• Est. Priority Date: 12/10/2003
• Status: Abandoned Application

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Paolini, Michael A., Brown, Michael Wayne, Ullmann, Lorin Evan, Ullmann, Cristi Nesbitt, Smith, Newton James Jr.
• Application Number:
  US10/732,780
• Publication Number:
  US 20050131744A1
• Time in Patent Office: Days
• US Class Current: 705/7
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data
• CPC Class Codes: G06V 40/176 Dynamic expression
• CPC Class Codes: H04L 12/1831 Tracking arrangements for later retrieval, e.g. recording contents, participants activities or behavior, network status
• CPC Class Codes: H04N 7/15 Conference systems

Abstract

An apparatus, system and method for automatically identifying participants at a conference who exhibit a particular expression during a speech are provided. To do so, the expression is indicated and the participants are recorded. The recording includes both audio and video signals. Using the recording of the participants in conjunction with an automated facial decoding system, it is determined whether any one of the participants exhibits the expression. If so, the participant is automatically identified. In some instances, the data may be passed through regional/cultural as well as individual filters to ensure the expression is not culturally or individually based. The data may also be stored for future use. In this case, the video data representing the participant that is currently exhibiting the expression and the audio data of what was being said are preferably stored.

Claims

1. A method of automatically identifying participants at a conference who exhibit a particular expression during a speech comprising the steps of:

indicating the particular expression;

recording the participants, the recording including both audio and video signals;

determining, using the recording of the participants in conjunction with an automated facial decoding system, whether at least one participant exhibits the particular expression; and

identifying the at least one participant who exhibits the particular expression.

2. The method of claim 1 wherein the video and audio signals representing the at least one participant are passed through a regional/cultural filter before the at least one participant is identified.

3. The method of claim 2 wherein the video and audio signals representing the at least one participant are further passed through an individual filter before the at least one participant is identified.

4. The method of claim 3 wherein the participants are digitally recorded and the video and data signals are video data.

5. The method of claim 4 wherein the audio and video data identifying the at least one participant is stored for future use.

6. The method of claim 5 wherein the identifying step includes the step of displaying an image as well as name and location of the at least one individual.

7. The method of claim 5 wherein the identifying step includes the step of identifying the at least one individual textually.

8. A computer program product on a computer readable medium for automatically identifying participants at a conference who exhibit a particular expression during a speech comprising:

code means for indicating the particular expression;

code means for recording the participants, the recording including both audio and video signals;

code means for determining, using the recording of the participants in conjunction with an automated facial decoding system, whether at least one participant exhibits the particular expression; and

code means for identifying the at least one participant who exhibits the particular expression.

9. The computer program product of claim 8 wherein the video and audio signals representing the at least one participant are passed through a regional/cultural filter before the at least one participant is identified.

10. The computer program product of claim 9 wherein the video and audio signals representing the at least one participant are further passed through an individual filter before the at least one participant is identified.

11. The computer program product of claim 10 wherein the participants are digitally recorded and the video and data signals are video data.

12. The computer program product of claim 11 wherein the audio and video data identifying the at least one participant is stored for future use.

13. The computer program product of claim 12 wherein the identifying step includes the step of displaying an image as well as name and location of the at least one individual.

14. The computer program product of claim 12 wherein the identifying step includes the step of identifying the at least one individual textually.

15. An apparatus for automatically identifying participants at a conference who exhibit a particular expression during a speech comprising:

means for indicating the particular expression;

means for recording the participants, the recording including both audio and video signals;

means for determining, using the recording of the participants in conjunction with an automated facial decoding system, whether at least one participant exhibits the particular expression; and

means for identifying the at least one participant who exhibits the particular expression.

16. The apparatus of claim 15 wherein the video and audio signals representing the at least one participant are passed through a regional/cultural filter before the at least one participant is identified.

17. The apparatus of claim 16 wherein the video and audio signals representing the at least one participant are further passed through an individual filter before the at least one participant is identified.

18. The apparatus of claim 17 wherein the participants are digitally recorded and the video and data signals are video data.

19. The apparatus of claim 18 wherein the audio and video data identifying the at least one participant is stored for future use.

20. The apparatus of claim 19 wherein the identifying step includes the step of displaying an image as well as name and location of the at least one individual.

21. The apparatus of claim 19 wherein the identifying step includes the step of identifying the at least one individual textually.

22. A system for automatically identifying participants at a conference who exhibit a particular expression during a speech comprising:

at least one storage system for storing code data; and

at least one processor for processing the code data to indicate the particular expression, to record the participants, the recording including both audio and video signals, to determine, using the recording of the participants in conjunction with an automated facial decoding system, whether at least one participant exhibits the particular expression, and to identify the at least one participant who exhibits the particular expression.

23. The system of claim 22 wherein the video and audio signals representing the at least one participant are passed through a regional/cultural filter before the at least one participant is identified.

24. The system of claim 23 wherein the video and audio signals representing the at least one participant are further passed through an individual filter before the at least one participant is identified.

25. The system of claim 24 wherein the participants are digitally recorded and the video and data signals are video data.

26. The system of claim 25 wherein the audio and video data identifying the at least one participant is stored for future use.

27. The system of claim 26 wherein the identifying step includes the step of displaying an image as well as name and location of the at least one individual.

28. The system of claim 26 wherein the identifying step includes the step of identifying the at least one individual textually.