Event Matching in Social Networks

• US 20110211737A1
• Filed: 05/24/2010
• Published: 09/01/2011
• Est. Priority Date: 03/01/2010
• Status: Abandoned Application

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: KVIATKOVSKY, Igor, Abramovski, Igor, Krupka, Eyal
• Application Number:
  US12/785,491
• Publication Number:
  US 20110211737A1
• Time in Patent Office: Days
• US Class Current: 382/118
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/587 using geographical or spatial information, e.g. location

Abstract

Images from two image databases may be correlated based on identifying a common event, which may be determined by image metadata as well as image content. The image metadata may include timestamps, geotagging metadata, or other tags, as well as input from a social network application in some embodiments. The image content may include analysis to find common persons based on facial recognition or color histograms, common background components, or other common features. The common event may be used to identify images that may be shared among the participants of the event by a social network application, as well as other purposes.

Claims

1. A method performed on a computer processor, said method comprising:

receiving image metadata for each image in a first image collection, said first image collection being associated with a first user;

receiving image metadata for each image in a second image collection, said second image collection being associated with a second user;

analyzed said image metadata to identify a common event; and

identifying a first image in said second image collection as relating to said common event.

2. The method of claim 1 further comprising:

presenting said first image to said first user.

3. The method of claim 1 further comprising:

presenting said first image to a third user.

4. The method of claim 3, said third user having a first social network connection to said second user.

5. The method of claim 4, said third user having a second social connection to said first user.

6. The method of claim 4, said third user having no second social connection to said first user.

7. The method of claim 1, said metadata comprising tagging from a social network.

8. The method of claim 1 further comprising:

performing image comparisons between said first image collection and said second image collection to identify said common event.

9. The method of claim 8, said image comparisons comprising facial identification.

10. The method of claim 9, said image comparisons comprising color histogram comparisons.

11. The method of claim 10, said color histograms being performed on background areas of said images.

12. The method of claim 10, said color histograms being performed on clothing associated with said facial identification.

13. A system comprising:

a social network comprising;

a first user account having a first image collection;

a second user account having a second image collection;

a comparison engine that;

identifies a common event by analyzing said first image collection and said second image collection.

14. The system of claim 13, said analyzing comprising metadata comparisons of images in said first image collection and said second image collection.

15. The system of claim 14, said metadata comprising at least one of a group composed of:

tags;

timestamps; and

location information.

16. The system of claim 13, said analyzing comprising image analysis of image comparisons in said first image collection and said second image collection.

17. The system of claim 16, said image comparisons comprising at least one of a group composed of:

facial analysis; and

histogram analysis.

18. A method performed on a computer processor, said method comprising:

receiving image metadata for each image in a first image collection, said first image collection being associated with a first user;

receiving image metadata for each image in a second image collection, said second image collection being associated with a second user;

identifying a common event between said first image collection and said second image collection by metadata comparison and image comparison of images in said first image collection and said second image comparison; and

identifying a first image in said second image collection as relating to said common event.

19. The method of claim 18 further comprising:

identifying a set of images relating to said common event;

determining at least one tag associated with at least one images in said set of images; and

associating said tag to at least one image in said set of images.

20. The method of claim 19, said first image collection and said second image collection being defined in a social network.