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

• US 9,268,795 B2
• Filed: 05/28/2014
• Issued: 02/23/2016
• 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): Li, Ruiping
• Application Number:
  US14/288,695
• Publication Number:
  US 20150169637A1
• Time in Patent Office: 636 Days
• Field of Search: 382/305, 382/159
• US Class Current: 1/1
• 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:

identifying, by one or more processors, a set of images that depict a particular object;

comparing, by one or more processors, an image in the set of images to another image in the set of images;

associating, by one or more processors and based on the comparing, a first score with the image;

modifying, by one or more processors and based on a location of the particular object within the image, the first score to obtain a modified first score; and

storing, by one or more processors, information associating the modified first score with the image.

2. The method of claim 1, further comprising:

receiving a search query; and

providing, based on the received search query, a plurality of images,

the plurality of images including the image, and

the image being provided as a result of the search query based on the modified first score.

3. The method of claim 1, where, when modifying the first score, the method includes:

increasing the first score when the particular object is located at or near a center of the image.

4. The method of claim 1, where the particular object appears in a plurality of images, and the method further includes:

determining a desired location of the particular object based on an average location of the particular object in the plurality of images; and

using the desired location of the particular object as the location of the particular object.

5. The method of claim 4, where, when modifying the first score, the method includes:

increasing the first score when the particular object is located in the desired location.

6. The method of claim 1, further comprising:

ranking the image with respect to other images, of the set of images, to create a ranked set of images,

the ranked set of images including the image,

the image being ranked based on the modified first score; and

providing, based on receiving a search query, the ranked set of images.

7. The method of claim 1, where, when modifying the first score, the method includes:

modifying the first score based on at least one of;

a metric relating to how much of the image is in focus, or

a metric relating to how well colors in the image are distributed.

8. A system comprising:

one or more server devices to;

identify a set of images that depict a particular object;

compare an image in the set of images to another image in the set of images;

associate, based on the comparing, a first score with the image;

modify, based on a location of the particular object within the image, the first score to obtain a modified first score; and

store information associating the modified first score with the image.

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

receive a search query; and

provide, based on the received search query, a plurality of images,

the plurality of images including the image, and

the image being provided as a result of the search query based on the modified first score.

10. The system of claim 8, where the one or more server devices, when modifying the first score, are further to:

increase the first score when the particular object is located at or near a center of the image.

11. The system of claim 8, where the particular object appears in a plurality of images, and the one or more server devices are further to:

determine a desired location of the particular object based on an average location of the particular object in the plurality of images; and

use the desired location of the particular object as the location of the particular object.

12. The system of claim 11, where the one or more server devices, when modifying the first score, are further to:

increase the first score when the particular object is located in the desired location.

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

rank the image with respect to other images, of the set of images, to create a ranked set of images,

the ranked set of images including the image,

the image being ranked based on the modified first score; and

provide, based on receiving a search query, the ranked set of images.

14. The system of claim 8, where the one or more server devices, when modifying the first score, are further to:

modify the first score based on at least one of;

a metric relating to how much of the image is in focus, or

a metric relating to how well colors in the image are distributed.

15. A device comprising:

a memory to store instructions; and

one or more processors to execute the instructions to;

identify a set of images that depict a particular object;

compare an image in the set of images to another image in the set of images;

associate, based on the comparing, a first score with the image;

modify, based on a location of the particular object within the image, the first score to obtain a modified first score; and

store information associating the modified first score with the image.

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

receive a search query; and

provide, based on the received search query, a plurality of images,

the plurality of images including the image, and

the image being provided as a result of the search query based on the modified first score.

17. The device of claim 15, where the one or more processors, when modifying the first score, are further to:

increase the first score when the particular object is located at or near a center of the image.

18. The device of claim 15, where the particular object appears in a plurality of images, and the one or more processors are further to:

determine a desired location of the particular object based on an average location of the particular object in the plurality of images; and

use the desired location of the particular object as the location of the particular object.

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

rank the image with respect to other images, of the set of images, to create a ranked set of images,

the ranked set of images including the image,

the image being ranked based on the modified first score; and

provide, based on receiving a search query, the ranked set of images.

20. The device of claim 15, where the one or more processors, when modifying the first score, are further to:

modify the first score based on at least one of;

a metric relating to how much of the image is in focus, or

a metric relating to how well colors in the image are distributed.