Object Identification in Images

• US 20100034466A1
• Filed: 08/10/2009
• Published: 02/11/2010
• Est. Priority Date: 08/11/2008
• Status: Abandoned Application

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Fink, Michael, Jing, Yushi, Baluja, Shumeet, Covell, Michele
• Application Number:
  US12/538,283
• Publication Number:
  US 20100034466A1
• Time in Patent Office: Days
• US Class Current: 382/195
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting

Abstract

A first indication of a portion of an image presented on a display device associated with a first user is received in response to a prompt to identify an object. A second indication of a portion of the image presented on a display device associated with a second user is received in response to a prompt to identify the object. A region-of-interest in the image is identified based on the first indication and the second indication. The region-of-interest is associated with an identifier of the object. A designator is associated with the region-of-interest in the image, the designator being configured to present information related to the object. Presentation of the designator associated with the region-of-interest in the image is enabled in subsequent presentations of the image.

Claims

1. A computer-implemented method comprising:

receiving, by at least one processor, a first indication of a portion of an image presented on a display device associated with a first user, the first indication being received in response to a prompt to identify an object;

receiving, by at least one processor, a second indication of a portion of the image presented on a display device associated with a second user, the second indication being received in response to a prompt to identify the object;

identifying, by at least one processor, a region-of-interest in the image based on the first indication and the second indication;

associating, by at least one processor, the region-of-interest with an identifier of the object;

associating, by at least one processor, a designator with the region-of-interest in the image, the designator being configured to present information related to the object; and

enabling, by at least one processor, presentation of the designator associated with the region-of-interest in the image in subsequent presentations of the image.

2. A computer-implemented method comprising:

receiving, by at least one processor, a plurality of indications of a portion of an image, wherein the image is part of an image collection and the indications having an associated object identifier;

identifying, by at least one processor, a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier; and

associating, by at least one processor, the common associated object identifier with the identified region-of-interest.

3. The method of claim 2, wherein the indications are further associated with a user, and each user is associated with a user score, and further wherein identifying a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier comprises identifying a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier and having an associated user with an associated user score greater than a threshold user score.

4. The method of claim 2, further comprising:

defining a goal region in one or more of the images in the image collections; and

determining if a received indication of a portion of an image indicates a portion of a goal region.

5. The method of claim 4, wherein the indications are further associated with a user, and further comprising if it is determined that a received indication of a portion of an image indicates a portion of a goal region, awarding a prize to the user associated with the received indication.

6. The method of claim 2, further comprising identifying fraudulent indications, and further wherein identifying a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier comprises identifying a region-of-interest in the image based on non-fraudulent indications of a portion of the image having a common associated object identifier.

7. The method of claim 2, further comprising associating a user-selectable link with the identified region-of-interest.

8. The method of claim 2, wherein the image collection is a video content item.

9. The method of claim 2, wherein the image collection is part of a map application.

10. A system comprising:

a data store adapted to store a plurality of images and associated indications of a portion of the images, wherein indications have an associated object identifier and an associated user; and

a processor adapted to;

identify indications of a portion of an image associated with a common object identifier;

identify a region-of interest in the image, the region-of-interest based on the indicated portions of the image; and

associate the common object identifier with the identified region-of-interest.

11. The system of claim 10, wherein the processor is further adapted to:

identify fraudulent indications stored in the data store; and

remove the fraudulent indications from the data store.

12. The system of claim 10, wherein the processor is further adapted to:

determine a score for each user associated with an indication; and

remove indications from the data store that have an associated user with a determined score less than a threshold score.

13. Instructions encoded on computer readable media that when executed cause a computer to perform operations comprising:

receiving a first indication of a portion of an image presented on a display device associated with a first user, the first indication being received in response to a prompt to identify an object;

receiving a second indication of a portion of the image presented on a display device associated with a second user, the second indication being received in response to a prompt to identify the object;

identifying a region-of-interest in the image based on the first indication and the second indication;

associating the region-of-interest with an identifier of the object;

associating a designator with the region-of-interest in the image, the designator being configured to present information related to the object; and

enabling presentation of the designator associated with the region-of-interest in the image in subsequent presentations of the image.

14. Instructions encoded on computer readable media that when executed cause a computer to perform operations comprising:

receiving a plurality of indications of a portion of an image, wherein the image is part of an image collection and the indications having an associated object identifier;

identifying a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier; and

associating the common associated object identifier with the identified region-of-interest.

15. The method of claim 14, wherein the indications are further associated with a user, and each user is associated with a user score, and further wherein identifying a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier comprises identifying a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier and having an associated user with an associated user score greater than a threshold user score.

16. The method of claim 14, further comprising:

defining a goal region in one or more of the images in the image collections; and

determining if a received indication of a portion of an image indicates a portion of a goal region.

17. The method of claim 16, wherein the indications are further associated with a user, and further comprising if it is determined that a received indication of a portion of an image indicates a portion of a goal region, awarding a prize to the user associated with the received indication.

18. The method of claim 14, further comprising identifying fraudulent indications, and further wherein identifying a region-of-interest in the image based on the indications of a portion of the image having a common associated object identifier comprises identifying a region-of-interest in the image based on non-fraudulent indications of a portion of the image having a common associated object identifier.

19. The method of claim 14, further comprising associating a user-selectable link with the identified region-of-interest.

20. The method of claim 14, wherein the image collection is a video content item.