Systems and methods for building and using social networks in image analysis

• US 9,373,076 B1
• Filed: 08/05/2008
• Issued: 06/21/2016
• Est. Priority Date: 08/08/2007
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: AOL Inc. (Apollo Global Management, Inc.)
• Inventors: Appelman, Barry, Perlmutter, Sharon M., Perlmutter, Keren O.
• Primary Examiner(s): Allison, Andrae S
• Application Number:
  US12/186,270
• Time in Patent Office: 2,877 Days
• Field of Search: 382/100, 382/118, 382/176, 382/190, 382/209, 382/218, 382/224, 382/278, 382/282, 382/289, 382/290, 709204-206, 706/21, 706/999.101, 706/999.104, 706/999.107
• US Class Current: 1/1
• CPC Class Codes: G06F 16/27 Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06N 5/01 Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06V 40/172 Classification, e.g. identification

Abstract

Computer-implemented systems and methods for identifying an object in an image are provided. In one example, the method includes identifying a first object related to an electronic image. The image includes at least a second object. Based at least in part on the identity of the first object, social networking information related to the first object is used to programmatically identify the second object. The first object and/or the second object may be a person. In some embodiments, metadata associated with the image may be used to identify the second object. Based at least in part on the identifications, social networking information may be associated between the first object and the second object.

Claims

1. A computer-implemented method of building a social network based on content in images, the method comprising:

using, at least one processor, to identify a first person in an electronic image;

identifying a second person related to the electronic image;

creating first social network information relating the first person to the second person;

storing, in a storage device, the first social network information;

identifying second social network information relating the first person with a third person; and

creating third social network information relating the second person to the third person based on the relation of the second person to the first person in the first social network information and the relation of the third person to the first person in the second social network information.

2. The method of claim 1, wherein the second person is in the image.

3. The method of claim 1, wherein the second person is related to the image by having taken the image or uploaded the image to a network.

4. The method of claim 1, wherein the first social network information includes a degree of separation between the first person and the second person.

5. The method of claim 1, wherein the third social network information includes a degree of separation between the second person and the third person.

6. The method of claim 5, wherein the second social network information includes a degree of separation between the first person and the third person, wherein the degree of separation between the second person and the third person is greater than the degree of separation between the first person and the third person.

7. The method of claim 1, further comprising:

identifying a relationship between the first person and a second image;

using a computer system to detect the third person in the second image;

creating the second social network information relating the first person to the third person based on the relationship between the first person and the second image and the detection of the third person in the second image; and

storing, in a storage device, the second social network information.

8. The method of claim 1, wherein the first person is identified based, at least in part, on stored social network information.

9. The method of claim 1, wherein a confidence of an identification of a person in an electronic image is increased based on stored social network information.

10. The method of claim 1, wherein the electronic image is one of a digital photograph or video frame.

11. The method of claim 1, wherein the first social network information includes a centrality measure of an importance of the first person in a social network.

12. A computer-implemented method of building a social network based on content in images, the method comprising:

using, at least one processor, to identify a first object in an electronic image;

identifying a second object related to the electronic image;

creating first social network information relating the first object to the second object;

identifying second social network information relating the first object with a third object; and

creating third social network information relating the second object to the third object based on the first social network information and the second social network information.

13. The method of claim 12, wherein the first object is a first person.

14. The method of claim 12, wherein the first object is a first person, the second object is a second person, and the first social network information comprises a picture distance between the first person and the second person.

15. The method of claim 12, wherein the second object is a second person.

16. The method of claim 12, wherein the first object is identified based, at least in part, on stored social network information.

17. The method of claim 12, wherein a confidence of an identification of an object in an electronic image is increased based on stored social network information.

18. The method of claim 12, wherein the electronic image is one of a digital photograph or video frame.

19. The method of claim 12, wherein the first social network information includes a centrality measure of an importance of the first object in a social network.

20. A system for building a social network based on content in images, the system comprising:

at least one storage device storing instructions; and

at least one processor that, when executing the instructions, is configured to;

identify a first person in an electronic image;

identify a second person related to the electronic image;

create first social network information relating the first person to the second person;

identify second social network information relating the first person with a third person; and

create third social network information relating the second person to the third person based on the relation of the second person to the first person in the first social network information and the relation of the third person to the first person in the second social network information.