IP Library Granted Patent US 9,218,546
Granted Patent B2
US 9,218,546 · App. 13/486,167 · Granted Dec 22, 2015

Choosing image labels

View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 9,218,546
App. No.
13/486,167
Granted
Dec 22, 2015
Kind
B2
Abstract

Methods, systems and apparatus for choosing image labels. In one aspect, a method includes receiving data specifying a first image, receiving text labels for the first image, receiving search results in response to a web search performed using at least some of the text labels as queries, ranking the text labels, at least in part, based on a number of resources referenced by the received search results, wherein at least some of the resources each include an image matching the first image, and selecting an image label for the image from the ranked text labels, the image label being selected based on the ranking.

Claims (59)

1. A method comprising:

receiving data specifying a first image;

receiving text labels for the first image;

for each of one or more of the text labels:

receiving search results in response to a web search performed using the text label as a query, each search result referencing a web resource;

assigning a text label ranking score to the text label based on a number of the resources referenced by the received search results that include an image matching the first image;

ranking the text labels, at least in part, based on the text label ranking scores assigned to text labels; and

selecting an image label for the first image from the ranked text labels, the image label being selected based on the ranking.

2. The method of claim 1 wherein receiving text labels for the first image includes requesting text labels associated with images identified as near duplicate images of the first image.

3. The method of claim 1 wherein assigning a text label ranking score comprises incrementing the score for each instance of another text label that is identified as being a near duplicate text label of the text label.

4. The method of claim 1 wherein the resources referenced by the received search results that include an image matching the first image include resources containing an image identified as a near duplicate image of the first image.

5. The method of claim 1 wherein the resources referenced by the received search results that include an image matching the first image include resources containing an image identified as residing in a cluster of a database containing the first image.

6. The method of claim 1 further comprising outputting a highest ranked text label as responsive to the first image.

7. The method of claim 1 wherein the data specifying the first image is received from a user device, and

the received text labels are identified based on characteristics of a user of the user device.

8. The method of claim 1 wherein ranking the text labels includes arranging the text labels according to the corresponding text label ranking scores.

9. A method comprising:

receiving data specifying a first image;

receiving text labels for the first image;

receiving search results in response to a web search performed using at least some of the text labels as queries;

ranking the text labels, at least in part, based on a number of resources referenced by the received search results, wherein at least some of the resources each include an image matching the first image, and wherein ranking the text labels includes calculating a text label ranking score for each text label based on

a median search result score calculated according to search result scores associated with the search results,

a number of search results returned by the web search, and

an original rank position of the received text labels; and

selecting an image label for the first image from the ranked text labels, the image label being selected based on the ranking.

10. The method of claim 1 wherein

the text label ranking score for each text label is based on the formula:

median_score*log(1+max(1,docs_matched))*smoothing_factor/(smoothing_factor+original_rank_position),

wherein median_score specifies a median search result score calculated according to search result scores associated with the search results, docs_matched specifies a number of search results returned by the web search, smoothing_factor is a constant value, and original_rank_position specifies an original rank position of the received text labels.

11. A system, comprising:

a data processing apparatus; and

a memory coupled to the data processing apparatus having instructions stored thereon which, when executed by the data processing apparatus cause the data processing apparatus to perform operations comprising:

receiving data specifying a first image;

receiving text labels for the first image;

for each of one or more of the text labels:

receiving search results in response to a web search performed using the text label as a query, each search result referencing a web resource;

assigning a text label ranking score to the text label based on a number of the resources referenced by the received search results that include an image matching the first image;

ranking the text labels, at least in part, based on the text label ranking scores assigned to text labels; and

selecting an image label for the first image from the ranked text labels, the image label being selected based on the ranking.

12. The system of claim 11 wherein receiving text labels for the first image includes requesting text labels associated with images identified as near duplicate images of the first image.

13. The system of claim 11 , wherein assigning a text label ranking score comprises incrementing the score for each instance of another text label that is identified as being a near duplicate text label of the text label.

14. The system of claim 11 wherein the resources referenced by the received search results that include an image matching the first image include resources containing an image identified as a near duplicate image of the first image.

15. The system of claim 11 wherein the resources referenced by the received search results that include an image matching the first image include resources containing an image identified as residing in a cluster of a database containing the first image.

16. The system of claim 11 , the operations further comprising outputting a highest ranked text label as responsive to the first image.

17. The system of claim 11 wherein the data specifying the first image is received from a user device, and

the received text labels are identified based on characteristics of a user of the user device.

18. The system of claim 11 wherein ranking the text labels includes arranging the text labels according to the corresponding text label ranking scores.

19. The system of claim 11 wherein the text label ranking score for each text label is based on

a median search result score calculated according to search result scores associated with the search results,

a number of search results returned by the web search, and

an original rank position of the received text labels.

20. Non-transitory computer readable media storing software comprising instructions executable by a processing device and upon such execution cause the processing device to perform operations comprising:

receiving data specifying a first image;

receiving text labels for the first image;

for each of one or more of the text labels:

receiving search results in response to a web search performed using the text label as a query, each search result referencing a web resource;

assigning a text label ranking score to the text label based on a number of the resources referenced by the received search results that include an image matching the first image;

ranking the text labels, at least in part, based on the text label ranking scores assigned to text labels; and

selecting an image label for the first image from the ranked text labels, the image label being selected based on the ranking.

Assignments (2)
CHANGE OF NAME Recorded Oct 2, 2017
From: GOOGLE INC.
To: GOOGLE LLC
Reel/Frame 044566/0657 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 6, 2012
From: ZHANG, YONG; ROSENBERG, CHARLES J.; WANG, JINGBIN; O'MALLEY, SEAN
To: GOOGLE INC.
Reel/Frame 028917/0854 →