Facilitating computer-assisted tagging of object instances in digital images

• US 8,244,069 B1
• Filed: 01/28/2011
• Issued: 08/14/2012
• Est. Priority Date: 02/28/2005
• Status: Active Grant

• Current Assignee: Adobe Inc.
• Original Assignee: Adobe Systems Incorporated (Adobe Inc.)
• Inventors: Bourdev, Lubomir B.
• Primary Examiner(s): PATEL, KANJIBHAI B
• Application Number:
  US13/015,819
• Time in Patent Office: 564 Days
• Field of Search: 382/107, 382/181, 382/205, 382/275, 382/291, 382/305, 382/309, 382/311, 382/312, 345/619
• US Class Current: 382/291
• CPC Class Codes: G06F 16/5866 using information manually generated, e.g. tags, keywords, comments, manually generated location and time information
• CPC Class Codes: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: G06V 10/987 with the intervention of an operator
• CPC Class Codes: Y10S 707/99936 Pattern matching access

Abstract

One embodiment of the present invention provides a system that facilitates computer-assisted tagging of objects in a digital image. During operation, the system receives locations for one or more objects-of-interest in the digital image. Next, the system determines likelihoods of specific tags being assigned to the objects-of-interest. The system then automatically assigns tentative tags to the objects-of-interest based on the determined likelihoods. Next, the system displays the assignments of tentative tags to a user, and receives corrections to the assignments, if any, from the user.

Claims

1. A method, comprising:

performing, by one or more computers;

receiving an indication of an object within an image;

determining a likelihood of a specific tag being assigned to the object, wherein said determining comprises applying one or more heuristics to determine the likelihood of the specific tag being assigned to the object; and

assigning the specific tag to the object based, at least in part, on the determined likelihood.

2. The method of claim 1, wherein assigning the tag to the object comprises associating the tag with the image.

3. The method of claim 1, further comprising:

performing, by the one or more computers,

displaying the assigned tag; and

enabling user modification of the assigned tag.

4. The method of claim 1, wherein determining the likelihood comprises evaluating a similarity between an area of the image and a corresponding area of another image.

5. The method of claim 1, wherein determining the likelihood comprises receiving an indication of a second object within the image and of another instance of the second object within another image.

6. The method of claim 1, wherein determining the likelihood comprises comparing a time stamp of the image with a time stamp of another image.

7. The method of claim 1, wherein determining the likelihood comprises evaluating a probability that the object may occur more than once in a same image.

8. The method of claim 1, wherein determining the likelihood comprises evaluating a probability that a specific combination of objects may occur together in a same image.

9. The method of claim 1, wherein determining the likelihood comprises evaluating a position or a scale of the object within the image.

10. A non-transitory computer-readable storage device storing instructions that when executed by a computer cause the computer to perform a method for facilitating computer-assisted tagging of objects in a digital image, the method comprising:

receiving an indication of an object within a first image;

determining a likelihood of a specific tag being assigned to the object based, at least in part, upon a comparison between a characteristic of the first image and a corresponding characteristic of a second image; and

assigning the specific tag to the object based, at least in part, on the determined likelihood.

11. The non-transitory computer-readable storage device of claim 10, wherein assigning the tag to the object comprises associating the tag with the first image.

12. The non-transitory computer-readable storage device of claim 10, the operations further comprising enabling user modification of the assigned tag.

13. The non-transitory computer-readable storage device of claim 10, wherein determining the likelihood comprises evaluating a similarity between an area neighboring the object within the first image and a corresponding area neighboring another instance of the object within the second image.

14. The non-transitory computer-readable storage device of claim 10, wherein determining the likelihood comprises comparing a time stamp of the first image with a time stamp of the second image.

15. The non-transitory computer-readable storage device of claim 10, wherein determining the likelihood comprises determining that the object is more prominently displayed than another object within the first image.

16. A system, comprising:

one or more processors; and

memory storing program instructions executable by the one or more processors to perform operations comprising;

receiving an indication of an object within an image;

determining a likelihood of a tag being assigned to the object, wherein said determining comprises applying one or more heuristics to determine the likelihood of the tag being assigned to the object; and

assigning the tag to the object based, at least in part, on the determined likelihood.

17. The system of claim 16, the operations further comprising enabling user modification of the assigned tag.

18. The system of claim 16, wherein determining the likelihood comprises comparing an area relative to the object within the image and a corresponding area relative to another instance of the object within another image.

19. The system of claim 16, wherein determining the likelihood comprises comparing a time stamp of the image with a time stamp of another image.

20. The system of claim 16, wherein determining the likelihood comprises determining that the object is more prominently displayed than another object within the image.