Video telephony image processing

• US 20070115350A1
• Filed: 11/03/2005
• Published: 05/24/2007
• Est. Priority Date: 11/03/2005
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: Broadcom Corporation (Broadcom, Inc.)
• Inventors: Currivan, Bruce, Chen, Xuemin
• Granted Patent: US 7,728,866 B2
• Time in Patent Office: Days
• US Class Current: 348/14.80
• CPC Class Codes: H04N 7/14 Systems for two-way working H04N7/12, H04N7/173 take precedence
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q
• CPC Class Codes: H04N 7/157 defining a virtual conference space and using avatars or agents computer conference optimisation or adaptation H04L12/1827

Abstract

Herein described is a system and method for modifying facial video transmitted from a first videophone to a second videophone during a videophone conversation. A videophone comprises a videophone image processing system (VIPS) that stores one or more preferred images. The one or more preferred images may comprise an image of a person presented in an attractive appearance. The one or more preferred images may comprise one or more avatars. Additionally, the VIPS may be used to incorporate one or more facial features of the person into a preferred image or avatar. Furthermore, a replacement background may be incorporated into the preferred image or avatar. The VIPS transmits a preferred image of a first speaker of a first videophone to a second speaker of a second videophone by capturing an actual image of the first speaker and substituting at least a portion of said actual image with a stored image.

Claims

1. A video image processing system for replacing a facial portion of an actual image captured by a videophone, said system comprising:

an image sensor used for capturing said actual image, said actual image comprising a facial portion and a background portion;

a lens for directing said actual image to said image sensor;

a memory;

a graphics processor used for performing video object segmentation of said actual image;

said graphics processor capable of cropping one or more facial objects from said actual image and inserting said facial objects into a stored facial image, said stored facial image selected to generate a preferred image, said preferred image transmitted from said videophone to a receiving videophone for display on said receiving videophone.

2. The video image processing system of claim 1 wherein said one or more facial objects comprise a person'"'"'s lips.

3. The video image processing system of claim 1 wherein said one or more facial objects comprise a person'"'"'s eyes.

4. The video image processing system of claim 1 wherein said preferred image is displayed and monitored by a user of said videophone.

5. The video image processing system of claim 1 wherein said preferred image is generated by substituting the background of said actual image with a background stored within said memory.

6. A method for processing facial video during a videophone conversation between a first videophone and a second videophone, said method comprising:

storing one or more preferred images into said first videophone prior to said videophone conversation;

retrieving an image of said one or more preferred images for use in said first videophone;

using said image to replace an actual image that is captured by said first videophone during said videophone conversation; and

transmitting said image to said second videophone.

7. The method of claim 6 further comprising:

selecting one or more facial features of said actual image;

performing video segmentation of said actual image to isolate one or more images of said one or more facial features;

storing said one or more images of said one or more facial features into a memory of said first videophone; and

incorporating said one or more images of said one or more facial features into said image of said one or more preferred images, such that actual facial movements and/or expressions are retained and transmitted during said videophone conversation.

8. The method of claim 6 further comprising replacing an existing background of said image with a selected background.

9. The method of claim 6 wherein said first videophone is capable of displaying said image during said videophone conversation.

10. The method of claim 6 wherein said one or more preferred images comprises a preferred image of a user of said first videophone.

11. The method of claim 6 wherein said one or more preferred images comprises an avatar.

12. The method of claim 11 wherein said avatar comprises a computer generated character, a cartoon character, a historically significant public figure, a character from a video game, a literary character, a movie character, or an animal.

13. A method of transmitting a preferred image of a first speaker of a first videophone to a second speaker of a second videophone, said method comprising:

capturing an actual image of said first speaker using said first videophone; and

substituting at least a portion of said actual image with a stored image to generate said preferred image, said stored image selected by said first speaker.

14. The method of claim 13 further comprising:

extracting one or more facial images from said actual image; and

incorporating said one or facial images in said actual image into said stored image.

15. The method of claim 13 further comprising replacing an existing background of said actual image with a stored background image.

16. The method of claim 13 wherein said stored image comprises a facial image.

17. The method of claim 13 wherein said stored image comprises an avatar.

18. The method of claim 17 wherein said avatar comprises a computer generated character, a cartoon character, a historically significant public figure, a character from a video game, a literary character, a movie character, or an animal.

19. The method of claim 13 wherein said first videophone transmits said preferred image to said second videophone by way of wireless or cellular transmission.

20. A video image processing system for replacing a facial portion of an actual image captured by a videophone, said system using an image sensor for capturing said actual image, said actual image comprising a facial portion and a background portion, a lens for directing said actual image to said image sensor, and a memory, said system comprising:

a graphics processor used for performing video object segmentation of said actual image;

said graphics processor capable of cropping one or more facial objects from said actual image and inserting said facial objects into a stored facial image, said stored facial image selected to generate a preferred image, said preferred image transmitted from said videophone to a receiving videophone for display on said receiving videophone.

21. The video image processing system of claim 20 wherein said one or more facial objects comprise a person'"'"'s lips.

22. The video image processing system of claim 20 wherein said one or more facial objects comprise a person'"'"'s eyes.