Forming connections between image collections

• US 7,668,405 B2
• Filed: 04/07/2006
• Issued: 02/23/2010
• Est. Priority Date: 04/07/2006
• Status: Expired due to Fees

• Current Assignee: Monument Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Eastman Kodak Company
• Inventors: Gallagher, Andrew C.
• Primary Examiner(s): Johns; Andrew W
• Assistant Examiner(s): Cunningham; Gregory F
• Application Number:
  US11/399,936
• Publication Number:
  US 20070239778A1
• Time in Patent Office: 1,418 Days
• Field of Search: 382/115, 382/118, 382/305
• US Class Current: 382/305
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 18/2321 using statistics or function optimisation, e.g. modelling of probability density functions
• CPC Class Codes: G06F 18/2323 based on graph theory, e.g. minimum spanning trees [MST] or graph cuts
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06V 10/763 Non-hierarchical techniques, e.g. based on statistics of modelling distributions
• CPC Class Codes: G06V 10/7635 based on graphs, e.g. graph cuts or spectral clustering
• CPC Class Codes: G06V 20/30 in albums, collections or shared content, e.g. social network photos or video
• CPC Class Codes: G06V 40/16 Human faces, e.g. facial parts, sketches or expressions
• CPC Class Codes: G06V 40/179 metadata assisted face recognition

Abstract

A method of establishing a connection between two image collections, the method includes providing a first image collection from a first user; providing a second image collection from a different second user; analyzing the first and second image collections to produce a similarity score between the first and second image collections; and establishing a link for sharing images or collection data between the first and second users based on the similarity score.

Claims

1. A method of establishing a connection between two image collections, comprising a collection controller for performing the following steps:

a) providing a first image collection from a first user;

b) providing a second image collection from a different second user;

c) analyzing the first and second image collections to produce a similarity score between the first and second image collections; and

d) establishing a link for sharing images or collection data between the first and second users based on the similarity score.

2. The method of claim 1, wherein step d) includes one of the users accessing both image collections or both of the users accessing both image collections.

3. The method of claim 1, wherein step c) includes:

i) detecting unique objects from the first and the second image collections;

ii) determining the likelihood that a unique object from the first image collection also appears in the second image collection; and

iii) producing the similarity score based on the determined likelihood.

4. The method of claim 3, wherein step c) includes producing a weight based on the type of unique object that is detected and using the weight and the likelihood to produce the similarity score.

5. The method of claim 1, wherein step c) includes using the image capture time or the image capture location from at least one image from at least one image collection to produce the similarity score.

6. The method of claim 1, wherein step c) further includes using a label from at least one of the image collections.

7. The method of claim 1, wherein the label is a name associated with a person.

8. The method of claim 3, wherein step cii) includes using the image capture time or the image capture location from at least one image from at least one image collection.

9. The method of claim 8, wherein step cii) includes computing a time difference between at least one image from the first image collection and one image from the second image collection.

10. The method of claim 8, wherein step cii) includes computing a distance or estimated travel time between the image capture locations of at least one image from the first image collection and one image from the second image collection.

11. The method of claim 3, wherein step cii) includes using a label from at least one of the image collections to produce the similarity score.

12. The method of claim 11, wherein the label is a name associated with a person.

13. The method of claim 3, wherein step cii) includes producing features associated with the distinct objects and determining the likelihood that a unique object from the first image collection also appears in the second image collection based on the produced features.

14. The method of claim 13, wherein step cii) includes using a label associated with a unique object from at least one of the image collections.

15. The method of claim 14, wherein the label is a name associated with a person and the unique object is a human face.

16. The method of claim 15, wherein the produced features are related to facial geometry.

17. The method of claim 13, wherein step cii) includes using a least one label associated with a unique object from the first image collection and one label associated with a unique object from the second image collection and determining the likelihood that a unique object from the first image collection also appears in the second image collection based on the labels.

18. The method of claim 17, wherein the labels are names associated with people and the unique object is a human face.

19. The method of claim 1, wherein step d) is also based on one or more sharing rules.

20. The method of claim 1, wherein step c) includes:

i) detecting at least one unique object in the first image collection;

ii) producing features associated with the distinct object; and

iii) producing the similarity score based on the features and an analysis of the second image collection.

21. The method of claim 20, wherein a label is provided for the at least one unique object from the first image collection and the similarity score is produced based on the label, the features, and an analysis of the second image collection.

22. The method of claim 21, wherein the label is a name associated with a person and the unique object is a human face.

23. The method of claim 22, wherein the label is the first name of a person.