IP Library Granted Patent US 9,792,714
Granted Patent B2
US 9,792,714 · App. 13/996,002 · Granted Oct 17, 2017

Avatar-based transfer protocols, icon generation and doll animation

Inventors: Wenlong Li (Beijing, CN); Xiaofeng Tong (Beijing, CN); Yangzhou Du (Beijing, CN); Thomas Sachson (Menlo Park, CA); Yunzhen Wang (San Jose, CA)
Assignee: Intel Corporation
G06T13/40G06F3/0482G06F3/04817G06F3/04842G06K9/00315G06T13/80H04L51/046H04N7/157
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,792,714
App. No.
13/996,002
Granted
Oct 17, 2017
Kind
B2
Abstract

Systems and methods may provide for identifying one or more facial expressions of a subject in a video signal and generating avatar animation data based on the one or more facial expressions. Additionally, the avatar animation data may be incorporated into an audio file associated with the video signal. In one example, the audio file is sent to a remote client device via a messaging application. Systems and methods may also facilitate the generation of avatar icons and doll animations that mimic the actual facial features and/or expressions of specific individuals.

Claims (70)

1. An apparatus to manage avatars, comprising:

a camera to capture an image of a subject and an image of a doll;

a recognition module to identify one or more facial expressions of the subject and a doll face in a video signal generated by the camera;

an avatar module to generate avatar animation data based on the one or more facial expressions of the subject;

an audio module to incorporate the avatar animation data into an audio file associated with the video signal, and

a transfer module,

wherein the transfer module is to transfer the avatar animation data of the subject and audible content associated with the audio file to the doll face to obtain a doll animation.

2. The apparatus of claim 1 , further including a communications module to send the audio file to a remote client device via a messaging application.

3. The apparatus of claim 1 , wherein the audio module is to store timestamped facial motion data in a free data field of the audio file to incorporate the avatar animation data into the audio file.

4. The apparatus of claim 1 , wherein the audio module is to store a link to timestamped facial motion data in a sound metadata field of the audio file to incorporate the avatar animation data into the audio file.

5. The apparatus of claim 1 , further including:

an icon module to generate an avatar icon based on the one or more facial expressions;

a list module to add the avatar icon to an icon list;

a user interface to present the icon list to a user and receive a user selection from the icon list; and

a communications module to send the user selection to a remote client device in conjunction with a text message.

6. The apparatus of claim 5 , wherein the list module is to confirm that the avatar icon is not a duplicate on the icon list.

7. The apparatus of claim 1 , wherein the recognition module further includes:

a tone module to identify a voice tone setting and change a tone of the audio file based on the voice tone setting.

8. At least one non-transitory computer readable storage medium comprising a set of instructions which, if executed by a computing device, cause the computing device to:

capture an image of a subject and an image of a doll;

identify one or more facial expressions of the subject and a doll face in a video signal;

generate avatar animation data based on the one or more facial expressions of the subject;

incorporate the avatar animation data into an audio file associated with the video signal, and

transfer the avatar animation data of the subject and audible content associated with the audio file to the doll face to obtain a doll animation.

9. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions, if executed, cause a computing device to send the audio file to a remote client device via a messaging application.

10. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions, if executed, cause a computing device to store timestamped facial motion data in a free data field of the audio file to incorporate the avatar animation data into the audio file.

11. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions, if executed, cause a computing device to store a link to timestamped facial motion data in a sound metadata field of the audio file to incorporate the avatar animation data into the audio file.

12. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions, if executed, cause a computing device to:

generate an avatar icon based on the one or more facial expressions;

add the avatar icon to an icon list;

present the icon list to a user;

receive a user selection from the icon list; and

send the user selection to a remote client device in conjunction with a text message.

13. The at least one non-transitory computer readable storage medium of claim 12 , wherein the instructions, if executed, cause a computing device to confirm that the avatar icon is not a duplicate on the icon list.

14. The at least one non-transitory computer readable storage medium of claim 8 , wherein the instructions, if executed, cause a computing device to:

identify a voice tone setting; and

change a tone of the audio file based on the voice tone setting.

15. A method of managing avatars, comprising:

capturing an image of a subject and an image of a doll;

identifying one or more facial expressions of the subject and a doll face in a video signal;

generating avatar animation data based on the one or more facial expressions of the subject;

incorporating the avatar animation data into an audio file associated with the video signal, and

transferring the avatar animation data of the subject and audible content associated with the audio file to the doll face to obtain a doll animation.

16. The method of claim 15 , further including sending the audio file to a remote client device via a messaging application.

17. The method of claim 15 , wherein incorporating the avatar animation data into the audio file includes storing timestamped facial motion data in a free data field of the audio file.

18. The method of claim 15 , wherein incorporating the avatar animation data into the audio file includes storing a link to timestamped facial motion data in a sound metadata field of the audio file.

19. The method of claim 15 , further including:

generating an avatar icon based on the one or more facial expressions;

adding the avatar icon to an icon list;

presenting the icon list to a user;

receiving a user selection from the icon list; and

sending the user selection to a remote client device in conjunction with a text message.

20. The method of claim 19 , further including confirming that the avatar icon is not a duplicate on the icon list.

21. The method of claim 15 , further including:

identifying a voice tone setting; and

changing a tone of the audio file based on the voice tone setting.

22. At least one non-transitory computer readable storage medium comprising a set of instructions which, if executed by a computing device, cause the computing device to:

capture an image of a subject and an image of a doll;

receive an audio file;

receive a video signal that includes facial expressions of the subject and a doll face;

use the audio file to obtain avatar animation data based on the facial expressions of the subject;

render an avatar animation based on the audio file and the avatar animation data, and

transfer the avatar animation data of the subject and audible content associated with the audio file to the doll face to obtain a doll animation.

23. The at least one non-transitory computer readable storage medium of claim 22 , wherein the audio signal is to be received from a messaging application of a remote client device.

24. The at least one non-transitory computer readable storage medium of claim 22 , wherein the instructions, if executed, cause a computing device to:

retrieve timestamped facial motion data from a free data field of the audio file to obtain the avatar animation data; and

synchronize the timestamped facial motion data with the audio file to render the avatar animation.

25. The at least one non-transitory computer readable storage medium of claim 22 , wherein the instructions, if executed, cause a computing device to:

retrieve timestamped facial motion data from a link stored in a sound metadata field of the audio file to obtain the avatar animation data; and

synchronize the timestamped facial motion data with the audio file to render the avatar animation.

Continuity (1)
Related Publication 20150379752A1 · Dec 31, 2015