Facilitating bidding on images

• US 8,156,001 B1
• Filed: 12/28/2007
• Issued: 04/10/2012
• Est. Priority Date: 12/28/2007
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Jing, Yushi, Baluja, Shumeet
• Primary Examiner(s): Patel, Jagdish
• Assistant Examiner(s): HAMILTON, SARA CHANDLER
• Application Number:
  US11/966,518
• Time in Patent Office: 1,565 Days
• Field of Search: 705/14.4, 705/14.71, 705/26.3, 705/37
• US Class Current: 705/14.4
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange

Abstract

Techniques are described for facilitating bidding on images. The techniques may include receiving bids includes presenting a first image and a bid associated with the first image. The first image is similar to a second image for which a bid is to be submitted for presenting sponsored content based on the second image. A bid is received for presenting a sponsored-content item based on the second image. The received bid is stored in association with second image and a sponsored-content item based to be presented based on the bid and the second image.

Claims

1. A method comprising:

receiving, by one or more computers, a reference image;

receiving, by the one or more computers, a bid associated with the reference image, the bid comprising a bid for presenting a sponsored-content item,

storing, by the one or more computers, the received bid in association with the reference image and the sponsored-content item; and

receiving a request for an advertisement, the request including a bid image;

in response to the request for the advertisement, using image or object recognition techniques to compare the reference image to the bid image to determine a match confidence level;

comparing the match confidence level to a threshold; and

presenting the sponsored-content item based on the a determination that the match confidence level exceeds the threshold.

2. The method of claim 1, wherein receiving the reference image comprises receiving a collection of reference images, and the method further comprises:

storing the collection of reference images; and

storing the received bid in association with each of the images in the collection of reference images.

3. The method of claim 1 wherein using image or object recognition techniques to compare the reference image to the bid image comprises comparing the reference image to the bid image to determine whether the bid image is identical to the reference image.

4. The method of claim 1 wherein using image or object recognition techniques to compare the reference image to the bid image comprises comparing the reference image to the bid image to determine whether the bid image is substantially similar to the reference image.

5. The method of claim 1 further comprising:

identifying a sub-image of the bid image by analyzing the bid image,

identifying a sub-image of the reference image by analyzing the reference image; and

wherein using image or object recognition techniques to compare the reference image to the bid image comprises comparing the sub-image of the bid image to the sub-image of the reference image.

6. The method of claim 1 wherein

the match confidence level comprises a likelihood that the bid image is the reference image.

7. The method of claim 1 further comprising receiving an indication of a portion of the reference image that is less than all of the reference image, and the method further comprises:

using image or object recognition techniques to compare the reference image to the bid image by identifying a bid image that includes a portion of the bid image that is similar to the indicated portion of the reference image.

8. The method of claim 1 wherein the received bid represents a maximum bid for presenting the sponsored-content item based on the reference image.

9. The method of claim 1, wherein receiving the request for the advertisement comprises receiving the request for the advertisement from an online photograph application with the bid image comprising a photograph associated with the online photograph application.

10. The method of claim 1, wherein presenting the sponsored-content item based on the determination that the match confidence level exceeds the threshold comprises presenting the sponsored-content item on a web page that includes the bid image.

11. The method of claim 1, wherein using image or object recognition techniques to compare the reference image to the bid image comprises:

decomposing the bid image into one or more regions of interest;

decomposing the one or more regions of interest into one or more local features; and

using image or object recognition techniques to compare the one or more local features to one or more match reference features from the reference image.

12. The method of claim 1, wherein storing the received bid in association with the reference image and the sponsored-content item comprises storing a pointer or link between the reference image and the sponsored-content item.

13. An advertisement targeting system comprising:

an advertisement receiving unit comprising one or more processors operable to;

receive a reference image;

receive a bid associated with the reference image, the bid comprising a bid for presenting a sponsored-content item,

store the received bid in association with the reference image and the sponsored-content item; and

an advertisement selection unit in communication with the advertisement receiving unit, the advertisement selection unit comprising one or more processors operable to;

receive a request for an advertisement, the request including a bid image;

in response to the request for the advertisement, use an image or object recognition unit to compare the reference image to the bid image to determine a match confidence level;

compare the match confidence level to a threshold; and

present the sponsored-content item based on a determination that the match confidence level exceeds the threshold.

14. The system of claim 13, wherein the advertisement receiving unit is further configured to:

store the collection of reference images; and

store the received bid in association with each of the images in the collection of reference images.

15. The system of claim 13, wherein the advertisement selection unit is further configured to compare the reference image to the bid image to determine whether the bid image is identical to the reference image.

16. The system of claim 13, wherein the advertisement selection unit is further configured to compare the reference image to the bid image to determine whether the bid image is substantially similar to the reference image.

17. The system of claim 13, wherein the advertisement selection unit is further configured to:

identify a sub-image of the bid image by analyzing the bid image,

identify a sub-image of the reference image by analyzing the reference image; and

wherein the configurations to use the image or object recognition unit to compare the reference image to the bid image comprise configurations to compare the sub-image of the bid image to the sub-image of the reference image.

18. The system of claim 13, wherein the advertisement selection unit is further configured to receive the request for the advertisement from an online photograph application with the bid image comprising a photograph associated with the online photograph application.

19. The system of claim 13, wherein the advertisement selection unit is further configured to present the sponsored-content item on a web page that includes the bid image.

20. The system of claim 13, wherein the advertisement selection unit is configured to compare the reference image to the bid image by:

decomposing the bid image into one or more regions of interest;

decomposing the one or more regions of interest into one or more local features; and

using image or object recognition techniques to compare the one or more local features to one or more match reference features from the reference image.

21. The system of claim 13, wherein the advertisement receiving unit is configured to store the received bid in association with the reference image and the sponsored-content item by storing a pointer or link between the reference image and the sponsored-content item.

22. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to:

receive a reference image;

receive a bid associated with the reference image, the bid comprising a bid for presenting a sponsored-content item,

store the received bid in association with the reference image and the sponsored-content item; and

receive a request for an advertisement, the request including a bid image;

in response to the request for the advertisement, use image or object recognition techniques to compare the reference image to the bid image to determine a match confidence level;

compare the match confidence level to a threshold; and

present the sponsored-content item based on a determination that the match confidence level exceeds the threshold.

23. The non-transitory computer storage medium of claim 22, wherein the computer storage medium further comprises instructions to:

store the collection of reference images; and

store the received bid in association with each of the images in the collection of reference images.

24. The non-transitory computer storage medium of claim 22, wherein the computer storage medium further comprises instructions to compare the reference image to the bid image to determine whether the bid image is identical to the reference image.

25. The non-transitory computer storage medium of claim 22, wherein the computer storage medium further comprises instructions to compare the reference image to the bid image to determine whether the bid image is substantially similar to the reference image.

26. The non-transitory computer storage medium of claim 22, wherein the computer storage medium further comprises instructions to:

identify a sub-image of the bid image by analyzing the bid image,

identify a sub-image of the reference image by analyzing the reference image; and

wherein the configurations to use the image or object recognition unit to compare the reference image to the bid image comprise configurations to compare the sub-image of the bid image to the sub-image of the reference image.

27. The non-transitory computer storage medium of claim 22, wherein the instructions to receive a request for an advertisement comprise instructions to receive a request for an advertisement from an online photograph application with the bid image comprising a photograph associated with the online photograph application.

28. The non-transitory computer storage medium of claim 22, wherein the instructions to present the sponsored-content item based on the determination that the match confidence level exceeds the threshold comprise instructions to present the sponsored-content item on a web page that includes the bid image.

29. The non-transitory computer storage medium of claim 22, wherein the instructions to use the image or object recognition techniques to compare the reference image to the bid image comprise instructions to:

decompose the bid image into one or more regions of interest;

decompose the one or more regions of interest into one or more local features; and

use image or object recognition techniques to compare the one or more local features to one or more match reference features from the reference image.

30. The non-transitory computer storage medium of claim 22, wherein the instructions to store the received bid in association with the reference image and the sponsored-content item comprise instructions to store a pointer or link between the reference image and the sponsored-content item.