Selection of an image or images most representative of a set of images

• US 8,498,490 B1
• Filed: 11/21/2011
• Issued: 07/30/2013
• Est. Priority Date: 11/15/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Baluja, Shumeet, Jing, Yushi
• Primary Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US13/301,449
• Time in Patent Office: 617 Days
• Field of Search: 382/162, 382/218, 382/219, 382/224, 382/305, 382/312, 382/190, 382/201, 382/209, 382/214, 345/420, 707705-708, 707/711, 707/713, 707/718, 707/723, 707/748
• US Class Current: 382/218
• CPC Class Codes: G06F 16/583 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/5838 using colour
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9538 Presentation of query results
• CPC Class Codes: G06F 16/955 using information identifiers, e.g. uniform resource locators [URL]

Abstract

Implementations consistent with the principles described herein relate to ranking a set of images based on features of the images determine the most representative and/or highest quality images in the set. In one implementation, an initial set of images is obtained and ranked based on a comparison of each image in the set of images to other images in the set of images. The comparison is performed using at least one predetermined feature of the images.

Claims

1. A method comprising:

obtaining, by one or more processors, a set of images;

comparing, by one or more processors, each image in the set of images to a particular image in the set of images based on at least one predetermined feature;

ranking, by one or more processors and based on the comparing, the set of images;

receiving, by one or more processors and after ranking the set of images, a search query to identify an image;

comparing, by one or more processors, information regarding the search query to the ranked set of images; and

providing for presentation, by one or more processors, at least one image in the ranked set of images.

2. The method of claim 1, where the at least one predetermined feature includes an image feature based on at least one of:

an intensity of the images,

a color of the images,

one or more edges in the images, or

a texture of the images.

3. The method of claim 1, where the at least one predetermined feature includes an intensity of the images, the method further comprising:

dividing each image, in the set of images, into one or more portions; and

determining an intensity histogram for each of the one or more portions, and

where, when comparing each image in the set of images to the particular image in the set of images, the method includes;

comparing each image in the set of images to the particular image in the set of images based on the determined intensity histogram.

4. The method of claim 1, where the at least one predetermined feature includes a color feature of the images, the method further comprising:

dividing each image, in the set of images, into one or more portions; and

determining a color histogram for each of the one or more portions, and

where, when comparing each image in the set of images to the particular image in the set of images, the method includes;

comparing each image in the set of images to the particular image in the set of images based on the determined color histogram.

5. The method of claim 1, further comprising:

determining one or more areas within each image; and

determining a histogram for each of the one or more areas,

where, when comparing each image in the set of images to the particular image in the set of images, the method includes;

comparing each image in the set of images to the particular image in the set of images based on the determined histogram.

6. The method of claim 1, where ranking the set of images includes:

assigning a respective ranking score to each image in the set of images, the respective ranking score representing a similarity between an image in the set of images and the particular image in the set of images based on the at least one predetermined feature.

7. The method of claim 1, where providing, for presentation, the at least one image in the ranked set of images includes at least one of:

providing, for presentation, a document that includes the at least one image;

or

providing, for presentation, a document that includes a link to the at least one image.

8. A system comprising:

one or more server devices to;

obtain a set of images;

compare each image in the set of images to a particular image in the set of images based on at least one predetermined feature;

rank, based on the comparing, the set of images;

receive, after ranking the set of images, a search query to identify an image;

compare information regarding the search query to the ranked set of images; and

provide, for presentation, at least one image in the ranked set of images.

9. The system of claim 8, where the at least one predetermined feature includes an image feature based on at least one of:

an intensity of the images,

a color of the images,

one or more edges in the images, or

a texture of the images.

10. The system of claim 8, where the at least one predetermined feature includes an intensity of the images, and one or more server devices are further to:

divide each image, in the set of images, into one or more portions; and

determine an intensity histogram for each of the one or more portions, and

where, when comparing each image in the set of images to the particular image in the set of images, the one or more server devices are further to;

compare each image in the set of images to the particular image in the set of images based on the determined intensity histogram.

11. The system of claim 8, where the at least one predetermined feature includes a color feature of the images, and one or more server devices are further to:

divide each image, in the set of images, into one or more portions; and

determine a color histogram for each of the one or more portions, and

where, when comparing each image in the set of images to the particular image in the set of images, the one or more server devices are further to;

compare each image in the set of images to the particular image in the set of images based on the determined color histogram.

12. The system of claim 8, where the one or more server devices are further to:

determine one or more areas within each image; and

determine a histogram for each of the one or more areas,

where, when comparing each image in the set of images to the particular image in the set of images, the one or more server devices are further to;

compare each image in the set of images to the particular image in the set of images based on the determined histogram.

13. The system of claim 8, where, when ranking the set of images, the one or more server devices are further to:

assign a respective ranking score to each image in the set of images, the respective ranking score representing a similarity between an image in the set of images and the particular image in the set of images based on the at least one predetermined feature.

14. The system of claim 8, where, when providing, for presentation, the at least one image in the ranked set of images, the one or more server devices are further to:

provide, for presentation, a document that includes the at least one image;

or

provide, for presentation, a document that includes a link to the at least one image.

15. A device comprising:

one or more processors to;

obtain a set of images;

compare each image in the set of images to a particular image in the set of images based on at least one predetermined feature;

rank, based on the comparing, the set of images;

receive, after ranking the set of images, a search query to identify an image;

compare information regarding the search query to the ranked set of images; and

provide, for presentation, at least one image in the ranked set of images.

16. The device of claim 15, where the at least one predetermined feature includes an image feature based on at least one of:

an intensity of the images,

a color of the images,

one or more edges in the images, or

a texture of the images.

17. The device of claim 15, where the at least one predetermined feature includes a color feature of the images, and one or more processors are further to:

divide each image, in the set of images, into one or more portions; and

determine a color histogram for each of the one or more portions, and

where, when comparing each image in the set of images to the particular image in the set of images, the one or more processors are further to;

compare each image in the set of images to the particular image in the set of images based on the determined color histogram.

18. The device of claim 15, where the one or more processors are further to:

determine one or more areas within each image; and

determine a histogram for each of the one or more areas,

where, when comparing each image in the set of images to the particular image in the set of images, the one or more processors are further to;

compare each image in the set of images to the particular image in the set of images based on the determined histogram.

19. The device of claim 15, where, when ranking the set of images, the one or more processors are further to:

assign a respective ranking score to each image in the set of images, the respective ranking score representing a similarity between an image in the set of images and the particular image in the set of images based on the at least one predetermined feature.

20. The device of claim 15, where, when providing, for presentation, the at least one image in the ranked set of images, the one or more processors are further to:

provide, for presentation, a document that includes the at least one image;

or

provide, for presentation, a document that includes a link to the at least one image.