Automatic media distribution

• US 9,141,848 B2
• Filed: 09/04/2012
• Issued: 09/22/2015
• Est. Priority Date: 09/04/2012
• Status: Active Grant

• Current Assignee: Tahoe Research Limited (f/k/a Learndale Limited) (Vector Capital Corporation)
• Original Assignee: Intel Corporation
• Inventors: Gong, Michelle X., Sun, Wei, Haussecker, Horst W.
• Primary Examiner(s): Ahmed, Samir
• Assistant Examiner(s): LE, TOTAM HA
• Application Number:
  US13/602,446
• Publication Number:
  US 20140064576A1
• Time in Patent Office: 1,113 Days
• Field of Search: 382/118
• US Class Current: 1/1
• CPC Class Codes: G06V 10/255 Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
• CPC Class Codes: G06V 10/60 relating to illumination properties, e.g. using a reflectance or lighting model
• CPC Class Codes: G06V 10/751 Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
• CPC Class Codes: G06V 2201/10 Recognition assisted with metadata
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

In accordance with some embodiments, wireless devices may automatically form ad hoc networks to enable more efficient sharing of media between the devices and in some cases more efficient facial recognition of captured media. In some embodiments, automatic story development may be implemented at the local level without involving backend servers.

Claims

1. A method comprising:

using facial recognition technology to identify an individual depicted in a digital picture by obtaining information from a light sensor about the lighting when two pictures were taken and also obtaining color information for pixels in the two pictures from an image sensor, said image sensor and light sensor being different devices, and comparing information from said light sensor when two pictures were taken for facial recognition purposes to determine whether different pixel readings in the two different pictures are due to different exposure conditions;

compensating for the different exposure conditions; and

then comparing the compensated pictures.

2. The method of claim 1 including using light sensor information to compare said picture to a stored picture for facial recognition.

3. The method of claim 1 including using a distance of the individual from an imaging device to facilitate the identification of the individual.

4. The method of claim 3 including using a direction to the individual from the imaging device to facilitate the identification of the individual.

5. The method of claim 1 including automatically composing a textural story using information about the identity of an individual depicted in said picture.

6. The method of claim 5 including using sentence templates with instructions for how to fill in at least one of a subject or object of a sentence.

7. The method of claim 1 including developing a clickable list of candidate individuals who may be depicted in the picture, and when an entry is clicked on, tagging the picture with the selected identity.

8. The method of claim 1 further including establishing an ad hoc network of wireless devices.

9. The method of claim 8 including establishing identities of ad hoc network users including obtaining avatars for the users.

10. The method of claim 9 including using the identities of users in the group to define a search field for facial recognition.

11. One or more non-transitory computer readable media storing instructions to enable a computer to perform a method including:

using facial recognition technology to identify an individual depicted in a digital picture by obtaining information from a light sensor about the lighting when two pictures were taken and also obtaining color information for pixels in the two pictures from an image sensor, said image sensor and light sensor being different devices, and comparing information from said light sensor when two pictures were taken for facial recognition purposes to determine whether different pixel readings in the two different pictures are due to different exposure conditions;

compensating for the different exposure conditions; and

then comparing the compensated pictures.

12. The non-transitory computer readable media of claim 11 further storing instructions to perform the method including using light sensor information to compare said picture to a stored picture for facial recognition.

13. The non-transitory computer readable media of claim 11 further storing instructions to perform the method including using a distance of the subject from an imaging device to facilitate the identification of the individual.

14. The non-transitory computer readable media of claim 13 further storing instructions to perform the method including using a direction to the subject from the imaging device to facilitate the identification of the individual.

15. The non-transitory computer readable media of claim 11 further storing instructions to perform a method including automatically composing a textural story using information about the identity of a person depicted in said picture.

16. The non-transitory computer readable media of claim 15 further storing instructions to perform the method including using sentence templates with instructions for how to fill in at least one of a subject or object of a sentence.

17. The non-transitory computer readable media of claim 11 further storing instructions to perform the method including developing a clickable list of candidate individuals who may be depicted in the picture, and when an entry is clicked on, tagging the picture with the selected identity.

18. The non-transitory computer readable media of claim 11 further storing instructions to perform a method including establishing an ad hoc network of wireless devices.

19. The non-transitory computer readable media of claim 18 further storing instructions to perform the method including establishing identities of users of an ad hoc network including obtaining avatars for the users.

20. The non-transitory computer readable media of claim 19 further storing instructions to perform the method including the identities of users in the group to define a search field for facial recognition.

21. An apparatus comprising:

an image sensor;

a light sensor different from said image sensor; and

a processor coupled to said light sensor and said image sensor to perform facial recognition by obtaining information from said sensor about the lighting when two different pictures were taken and also obtaining color information for pixels in the two pictures and comparing information from said light sensor when two pictures were taken, determining whether different pixel readings in the two different pictures are due to different exposure conditions, compensating for the different exposure conditions and then comparing the compensated pictures for facial recognition purposes.

22. The apparatus of claim 21 including a directional light sensor to compensate for lighting effects when comparing two pictures.

23. The apparatus of claim 21 including a processor to use a distance of a subject from an imaging device to facilitate the identification of the individual.

24. The apparatus of claim 23 including a processor to use a direction to the subject from the imaging device to facilitate the identification of the individual.

25. The apparatus of claim 21 said apparatus to perform facial recognition by comparing a picture of a person to an avatar associated with said person.