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

• US 8,744,191 B1
• Filed: 07/29/2013
• Issued: 06/03/2014
• 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:
  US13/953,167
• Time in Patent Office: 309 Days
• Field of Search: 382/159, 382/162, 382/173, 382/218, 382/219, 382/224, 382/305, 382/312, 382/192, 358/1.9, 707706-708, 707/713, 707/723, 707/726, 707/729, 707/731, 707/748, 707/749
• US Class Current: 382/192
• 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;

identifying, by one or more processors, one or more objects from the set of images;

determining, by one or more processors, that at least one of the one or more identified objects occurs in a single particular location of at least one image of the set of images;

ranking, by one or more processors and based on determining that the at least one of the one or more identified objects occurs in the single particular location of the least one image of the set of images, the at least one image with respect to each other image, of the set of images, to create a ranked set of images; and

storing, by one or more processors, the ranked set of images.

2. The method of claim 1, further comprising:

receiving a search query; and

providing, based on the received search query and the ranked set of images, an image from the set of images.

3. The method of claim 1, where, when ranking the at least one image with respect to each other image of the set of images, the method includes:

assigning a respective score to each image of the set of images,

the respective score assigned to the at least one image being greater than the respective score assigned to each other image of the set of images.

4. The method of claim 1, where, when determining that at least one of the one or more identified objects occurs in the single particular location of the at least one image of the set of images, the method includes:

determining that at least one of the one or more identified objects occurs in the single particular location of a first image of the set of images; and

determining that the at least one of the one or more identified objects occurs in the single particular location of a second image of the set of images,

the second image being different than the first image.

5. The method of claim 1, further comprising:

determining that a first quantity of the one or more identified objects occurs in another location of a first image of the set of images;

determining that a second quantity of the one or more identified objects occurs in another location of a second image of the set of images,

the second quantity being greater than the first quantity;

assigning, based on determining that the first quantity of the one or more identified objects occurs in the other location of the first image, a first score to the first image; and

assigning, based on determining that the second quantity of the one or more identified objects occurs in the other location of the second image, a second score to the second image,

the second score being different than the first score.

6. The method of claim 1, where the single particular location of the at least one image corresponds to a center of the at least one image.

7. The method of claim 1, where the single particular location of the at least one image corresponds to an average location of the one or more identified objects with respect to each image of the set of images.

8. A system comprising:

one or more server devices to;

obtain a set of images;

identify one or more objects from the set of images;

determine that at least one of the one or more identified objects occurs in a single particular location of at least one image of the set of images;

rank, based on determining that the at least one of the one or more identified objects occurs in the single particular location of the least one image of the set of images, the at least one image with respect to each other image, of the set of images, to create a ranked set of images; and

store the ranked set of images.

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 and the ranked set of images, an image from the set of images.

10. The system of claim 8, where, when ranking the at least one image with respect to each other image of the set of images, the one or more server devices are further to:

assign a respective score to each image of the set of images,

the respective score assigned to the at least one image being greater than the respective score assigned to each other image of the set of images.

11. The system of claim 8, where, when determining that at least one of the one or more identified objects occurs in the single particular location of the at least one image of the set of images, the one or more server devices are further to:

determine that at least one of the one or more identified objects occurs in the single particular location of a first image of the set of images; and

determine that the at least one of the one or more identified objects occurs in the single particular location of a second image of the set of images,

the second image being different than the first image.

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

determine that a first quantity of the one or more identified objects occurs in another location of a first image of the set of images;

determine that a second quantity of the one or more identified objects occurs in another location of a second image of the set of images,

the second quantity being greater than the first quantity;

assign, based on determining that the first quantity of the one or more identified objects occurs in the other location of the first image, a first score to the first image; and

assign, based on determining that the second quantity of the one or more identified objects occurs in the other location of the second image, a second score to the second image,

the second score being different than the first score.

13. The system of claim 8, where the single particular location of the at least one image corresponds to a center of the at least one image.

14. The system of claim 8, where the single particular location of the at least one image corresponds to an average location of the one or more identified objects with respect to each image of the set of images.

15. A device comprising:

a memory to store instructions; and

one or more processors to execute the instructions to;

obtain a set of images;

identify one or more objects from the set of images;

determine that at least one of the one or more identified objects occurs in a single particular location of at least one image of the set of images;

rank, based on determining that the at least one of the one or more identified objects occurs in the single particular location of the least one image of the set of images, the at least one image with respect to each other image, of the set of images, to create a ranked set of images; and

store the ranked set of images.

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 and the ranked set of images, an image from the set of images.

17. The device of claim 15, where, when ranking the at least one image with respect to each other image of the set of images, the one or more processors are further to:

assign a respective score to each image of the set of images,

the respective score assigned to the at least one image being greater than the respective score assigned to each other image of the set of images.

18. The device of claim 15, where, when determining that at least one of the one or more identified objects occurs in the single particular location of the at least one image of the set of images, the one or more processors are further to:

determine that at least one of the one or more identified objects occurs in the single particular location of a first image of the set of images; and

determine that the at least one of the one or more identified objects occurs in the single particular location of a second image of the set of images,

the second image being different than the first image.

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

determine that a first quantity of the one or more identified objects occurs in another location of a first image of the set of images;

determine that a second quantity of the one or more identified objects occurs in another location of a second image of the set of images,

the second quantity being greater than the first quantity;

assign, based on determining that the first quantity of the one or more identified objects occurs in the other location of the first image, a first score to the first image; and

assign, based on determining that the second quantity of the one or more identified objects occurs in the other location of the second image, a second score to the second image,

the second score being different than the first score.

20. The device of claim 15, where the single particular location of the at least one image corresponds to one of:

a center of the at least one image, or

an average location of the one or more identified objects with respect to each image of the set of images.