System to compile landmark image search results

• US 9,171,231 B2
• Filed: 11/22/2011
• Issued: 10/27/2015
• Est. Priority Date: 05/23/2008
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Naaman, Mor, Kennedy, Lyndon
• Primary Examiner(s): TUCKER, WESLEY J
• Application Number:
  US13/302,271
• Publication Number:
  US 20120066219A1
• Time in Patent Office: 1,435 Days
• Field of Search: 382/181, 382305-307
• US Class Current: 1/1
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/9537 Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
• CPC Class Codes: G06F 18/232 Non-hierarchical techniques
• CPC Class Codes: G06V 10/462 Salient features, e.g. scale invariant feature transforms [SIFT]
• CPC Class Codes: G06V 10/763 Non-hierarchical techniques, e.g. based on statistics of modelling distributions

Abstract

This patent discloses a system to compile a landmark image search result. The system may determine a rank of each image within a visual cluster according to at least one of a low-level self-similarity score, a low-level discriminative modeling score, and a point wise linking score. The landmark image search result may be compiled as a function of the rank of each image.

Claims

1. A method comprising:

receiving, at a computing device, a plurality of images and tags for the images, each tag associated with an image and comprising a location corresponding to the image;

grouping, via the computing device, the images into a plurality of clusters based on the location corresponding to the images, each cluster comprising a plurality of images;

analyzing, via the computing device, the images of each cluster to determine visual features of each image;

grouping, via the computing device, the images of the clusters into a plurality of visual clusters based on the visual features of the images, each visual cluster associated with a specific view of the location;

determining, via the computing device, a rank of the images within the visual clusters; and

compiling, via the computing device, an image search result at least partly based on the rank of the images within the visual clusters.

2. The method of claim 1, wherein the images comprise photographs, the location corresponding to the images comprises a location where the photograph was taken by a user.

3. The method of claim 1, wherein the grouping of the images into a plurality of clusters based on the location corresponding to the images comprises:

grouping the images into one of the clusters based on a geographical distance of the location corresponding to the images from a geographical location point associated with one of the clusters.

4. The method of claim 1, wherein the tags further comprise at least one keyword corresponding to the images, the grouping of the images into the plurality of clusters is based on the at least one keyword corresponding to the images.

5. The method of claim 4, wherein the grouping of the images into the clusters based on the at least one keyword further comprises:

determining that the keyword corresponding to the images is event driven or location driven.

6. The method of claim 5, wherein an event driven keyword is associated with a temporal pattern and a location driven keyword is associated with a spatial pattern.

7. The method of claim 1, wherein the rank of the images within the visual clusters is further based on a number of users associated with the visual clusters.

8. A system comprising:

a processor;

a non-transitory computer-readable storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising;

receiving logic executed by the processor for receiving a plurality of images and tags for the images, each tag associated with an image and comprising a location corresponding to the image;

grouping logic executed by the processor for grouping the images into a plurality of clusters based on the location corresponding to the images, each cluster comprising a plurality of images;

analysis logic executed by the processor for analyzing the images of each cluster to determine visual features of each image;

grouping logic executed by the processor for grouping the images of the clusters into a plurality of visual clusters based on the visual features of the images, each visual cluster associated with a specific view of the location;

determination logic executed by the processor for determining a rank of the images within the visual clusters; and

compiling logic executed by the processor for compiling an image search result at least partly based on the rank of the images within the visual clusters.

9. The system of claim 8, wherein the images comprise photographs, the location corresponding to the images comprises a location where the photograph was taken by a user.

10. The system of claim 8, wherein the grouping of the images into a plurality of clusters based on the location corresponding to the images comprises:

grouping logic executed by the processor for grouping the images into one of the clusters based on a geographical distance of the location corresponding to the images from a geographical location point associated with one of the clusters.

11. The system of claim 8, wherein the tags further comprise at least one keyword corresponding to the images, the grouping of the images into the plurality of clusters is based on the at least one keyword corresponding to the images.

12. The system of claim 11, wherein the grouping of the images into the clusters based on the at least one keyword further comprises:

determination logic executed by the processor for determining that the keyword corresponding to the images is event driven or location driven.

13. The system of claim 12, wherein an event driven keyword is associated with a temporal pattern and a location driven keyword is associated with a spatial pattern.

14. The system of claim 8, wherein the rank of the images within the visual clusters is further based on a number of users associated with the visual clusters.

15. A non-transitory computer readable storage medium tangibly encoded with computer-executable instructions that, when executed by a processor associated with a computing device, computer, perform a method comprising:

receiving a plurality of images and tags for the images, each tag associated with an image and comprising a location corresponding to the image;

grouping the images into a plurality of clusters based on the location corresponding to the images, each cluster comprising a plurality of images;

analyzing the images of each cluster to determine visual features of each image;

grouping the images of the clusters into a plurality of visual clusters based on the visual features of the images, each visual cluster associated with a specific view of the location;

determining a rank of the images within the visual clusters; and

compiling an image search result at least partly based on the rank of the images within the visual clusters.

16. The non-transitory computer readable storage medium of claim 15, wherein the images comprise photographs, the location corresponding to the images comprises a location where the photograph was taken by a user.

17. The non-transitory computer readable storage medium of claim 15, wherein the grouping of the images into a plurality of clusters based on the location corresponding to the images comprises:

grouping the images into one of the clusters based on a geographical distance of the location corresponding to the images from a geographical location point associated with one of the clusters.

18. The non-transitory computer readable storage medium of claim 15, wherein the tags further comprise at least one keyword corresponding to the images, the grouping of the images into the plurality of clusters is based on the at least one keyword corresponding to the images.

19. The non-transitory computer readable storage medium of claim 18, wherein the grouping of the images into the clusters based on the at least one keyword further comprises:

determining that the keyword corresponding to the images is event driven or location driven.

20. The non-transitory computer readable storage medium of claim 19, wherein an event driven keyword is associated with a temporal pattern and a location driven keyword is associated with a spatial pattern.