Prevent video calls based on appearance

• US 7,564,476 B1
• Filed: 05/13/2005
• Issued: 07/21/2009
• Est. Priority Date: 05/13/2005
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Warta, Ralph, Runcie, Peter D., Forbes, Alexander Quentin, Coughlan, Marc William Joseph, Scholte, Alexander Martin
• Primary Examiner(s): Ramakrishnaiah; Melur
• Application Number:
  US11/129,124
• Time in Patent Office: 1,530 Days
• Field of Search: 348 1404- 1416, 382/254, 382/173, 382/284, 382/232, 382/302
• US Class Current: 348/14.08
• 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 video teleconferencing system is provided that (i) determines whether an image frame of a first participant is appropriate for a second participant to the video call and (ii), when the image frame is not appropriate for the video call, alters the image frame to be appropriate for the second participant; before transmission of the image frame to the second participant, notifies the first participant that the image frame is not appropriate; refocuses a camera receiving an image of the first participant so that the image frame becomes appropriate for the second participant; and/or blocks transmission of the at least one image frame to the second participant.

Claims

1. A video teleconferencing method, comprising:

(a) receiving a video stream comprising at least one image frame depicting a first participant of a video call, the video call being between at least the first participant and a second participant;

(b) determining, by a computer and based on the at least one image frame, whether the at least one image frame is acceptable for the second participant to the video call; and

(c) when the at least one image frame is not acceptable for the video call, performing, by the computer, at least one of the following substeps;

(c1) altering the at least one image frame to be appropriate for the second participant;

(c2) before transmission of the at least one image frame to the second participant, notifying the first participant that the at least one image frame is not appropriate;

(c3) automatically refocusing at least one camera receiving an image of the first participant so that the at least one image frame becomes appropriate for the second participant; and

(c4) blocking transmission of the at least one image frame to the second participant.

2. The video teleconferencing method of claim 1, wherein the determining step (b) comprises the substeps of:

(b1) detecting a portion of the at least one image frame that is in motion;

(b2) locating a head of the first participant in the portion of the at least one image frame;

(b3) comparing the located head to a plurality of references faces to identify the first participant; and

(b4) for the identified recipient and electronic address of the second participant, retrieving a set of rules defining what is image information in the at least one image frame is appropriate for display to the second participant.

3. The video teleconferencing method of claim 1, wherein the determining step (b) comprises the substeps of:

(b1) detecting a portion of the at least one image frame that is in motion;

(b2) locating a head of the first participant in the portion of the at least one image frame;

(b3) identifying a facial feature of the first participant; and

(b4) determining whether the identified facial feature is undesirable for the second participant.

4. The video teleconferencing method of claim 1, wherein the determining step (b) comprises the substeps of:

(b1) detecting a portion of the at least one image frame that is in motion;

(b2) locating a body part of the first participant in the portion of the at least one image frame;

(b3) identifying a movement of the body part; and

(b4) determining whether the identified movement is undesirable for the second participant.

5. The video teleconferencing method of claim 1, wherein the determining step (b) comprises the substeps of:

(b1) locating a body of the first participant in a portion of the at least one image frame;

(b3) identifying at least one of a degree of clothing and an item of clothing worn by the body of the first participant; and

(b4) determining whether the at least one of a degree of clothing and an item of clothing is undesirable for the second participant.

6. The method of claim 5, wherein the determining step (b3) comprises the sub-steps:

determining a skin color of the first participant'"'"'s body;

using the skin color to unclothed skin to determine unclothed areas of the first participant'"'"'s body;

using pattern matching to identify the item of clothing; and

based on the unclothed and clothed areas of the first participant'"'"'s body, determining the degree of clothing of the first participant.

7. The video teleconferencing method of claim 1, wherein the determining step (b) comprises the substeps of:

(b1) locating a background portion of the at least one image frame;

(b3) identifying at least one object in the background portion; and

(b4) determining whether the identified object is undesirable for the second participant.

8. The video teleconferencing method of claim 1, wherein substep (c1) is performed and wherein the first participant'"'"'s face is not altered.

9. The video teleconferencing method of claim 1, wherein substep (c2) is performed.

10. The video teleconferencing method of claim 1, wherein substep (c3) is performed and wherein the first participant'"'"'s face, though refocused is not altered.

11. The video teleconferencing method of claim 10, wherein the at least one camera is automatically refocused to remove undesirable information from the at least one image frame.

12. The video teleconferencing method of claim 1, wherein substep (c4) is performed.

13. A computer readable medium comprising computer executable instructions that, when executed, perform the steps of claim 1.

14. A video teleconferencing system, comprising:

(a) an input operable to receive a video stream comprising at least one image frame depicting a first participant of a video call, the video call being between at least the first participant and a second participant;

(b) a video telephony processing system operable, by computer, to (i) determine, based upon information in the at least one image frame, whether the at least one image frame is appropriate and (ii), when the at least one image frame is not appropriate for the video call, perform at least one of the following suboperations;

(b1) alter the at least one image frame to be appropriate for the second participant;

(b2) before transmission of the at least one image frame to the second participant, notify the first participant that the at least one image frame is not appropriate;

(b3) automatically refocus at least one camera receiving an image of the first participant so that the at least one image frame becomes appropriate for the second participant; and

(b4) block transmission of the at least one image frame to the second participant.

15. The video teleconferencing system of claim 14, wherein the determining operation comprises the suboperations of:

(b5) detect a portion of the at least one image frame that is in motion;

(b6) locate a head of the first participant in the portion of the at least one image frame;

(b7) compare the located head to a plurality of references faces to identify the first participant; and

(b8) for the identified recipient and electronic address of the second participant, retrieve a set of rules defining what is image information in the at least one image frame is appropriate for display to the second participant.

16. The video teleconferencing system of claim 14, wherein the determining operation comprises the suboperations of:

(b5) detect a portion of the at least one image frame that is in motion;

(b6) locate a head of the first participant in the portion of the at least one image frame;

(b7) identify a facial feature of the first participant; and

(b8) determine whether the identified facial feature is undesirable for the second participant.

17. The video teleconferencing system of claim 14, wherein the determining operation comprises the suboperations of:

(b5) detect a portion of the at least one image frame that is in motion;

(b6) locate a body part of the first participant in the portion of the at least one image frame;

(b7) identify a movement of the body part; and

(b8) determine whether the identified movement is undesirable for the second participant.

18. The video teleconferencing system of claim 14, wherein the determining operation comprises the suboperation of:

(b5) locate a body of the first participant in a portion of the at least one image frame;

(b6) identify at least one of a degree of clothing and an item of clothing worn by the body of the first participant; and

(b7) determine whether the at least one of a degree of clothing and an item of clothing is undesirable for the second participant.

19. The video teleconferencing system of claim 14, wherein the determining step (b) comprises the suboperations of:

(b5) locate a background portion of the at least one image frame;

(b6) identify at least one object in the background portion; and

(b7) determine whether the identified object is undesirable for the second participant.

20. The video teleconferencing system of claim 14, wherein suboperation (b1) is performed and wherein the first participant'"'"'s face is not altered.

21. The video teleconferencing system of claim 14, wherein suboperation (b2) is performed.

22. The video teleconferencing system of claim 14, wherein suboperation (b3) is performed and wherein the first participant'"'"'s face, though refocused, is not altered.

23. The video teleconferencing method of claim 14, wherein the at least one camera is automatically refocused to remove undesirable information from the at least one image frame.

24. The video conferencing system of claim 14, wherein suboperation (b4) is performed.

25. A video teleconferencing system, comprising:

(a) an input to receive a video stream comprising at least one image frame depicting a first participant of a video call, the video call being between at least the first participant and a second participant;

(b) a video telephony processing system including;

(B1) a motion detector operable to process the at least one image frame and identify at least one region of the at least one image frame containing motion;

(B2) a head locator operable to select a block of the at least one image frame containing motion and determine whether the selected block comprises a face of the first participant;

(B3) a body locator operable to identify image data in the at least one image frame comprising at least one body part of the first participant other than the face of the first participant;

(B4) a clothing identifier operable to determine at least one of a degree of clothing of the first participant'"'"'s body and an item of clothing worn by the first participant; and

(B5) a video communication controller operable to (i) receive a set of tags from at least one of the head locator, body locator, and clothing identifier, (ii) determine whether the at least one image frame is appropriate for the video call, and (iii), when the at least one image frame is not appropriate for the video call, perform at least one of the following subfunctions;

(B5.1) alter the at least one image frame to be appropriate for the second participant;

(B5.2) before transmission of the at least one image frame to the second participant, notify the first participant that the at least one image frame is not appropriate;

(B5.3) automatically refocus at least one camera receiving an image of the first participant so that the at least one image frame becomes appropriate for the second participant; and

(B5.4) block transmission of the at least one image frame to the second participant.

26. The video teleconferencing system of claim 25, wherein subfunction (B5.1) is performed and wherein the first participant'"'"'s face is not altered.

27. The video teleconferencing system of claim 25, wherein subfunction (B5.2) is performed.

28. The video teleconferencing system of claim 25, wherein subfunction (B5.3) is performed and wherein the first participant'"'"'s face, though refocused, is not altered.

29. The video teleconferencing system of claim 25, wherein subfunction (B5.4) is performed.